505 hot topic(s) found with the query "Machine learning"
Prediction of ciprofloxacin resistance in hospitalized patients using machine learning.
Igor Mintz et al. Communications medicine 2023 3 (1) 43
(Posted: Mar-29-2023 8AM)
Ciprofloxacin is a widely used antibiotic that has lost efficiency due to extensive resistance. We developed machine learning (ML) models that predict the probability of ciprofloxacin resistance in hospitalized patients. The ensemble models’ predictions are well-calibrated, and yield ROC-AUCs (area under the receiver operating characteristic curve) of 0.737 (95%CI 0.715–0.758) and 0.837 (95%CI 0.821–0.854) on independent test-sets for the agnostic and gnostic datasets, respectively. Shapley additive explanations analysis identifies that influential variables are related to resistance of previous infections, where patients arrived from (hospital, nursing home, etc.), and recent resistance frequencies in the hospital.
Multiomic signatures of body mass index identify heterogeneous health phenotypes and responses to a lifestyle intervention.
Kengo Watanabe et al. Nature medicine 2023 3
(Posted: Mar-22-2023 7AM)
We report an atlas of cross-sectional and longitudinal changes in 1,111 blood analytes associated with variation in body mass index (BMI), as well as multiomic associations with host polygenic risk scores and gut microbiome composition, from a cohort of 1,277 individuals enrolled in a wellness program (Arivale). Machine learning model predictions of BMI from blood multiomics captured heterogeneous phenotypic states of host metabolism and gut microbiome composition better than BMI, which was also validated in an external cohort (TwinsUK). Moreover, longitudinal analyses identified variable BMI trajectories for different omics measures in response to a healthy lifestyle intervention.
Automated prioritization of sick newborns for whole genome sequencing using clinical natural language processing and machine learning.
Bennet Peterson et al. Genome medicine 2023 3 (1) 18
(Posted: Mar-20-2023 7AM)
We have developed automated means to prioritize patients for rapid and whole genome sequencing (rWGS and WGS) directly from clinical notes. Our approach combines a clinical natural language processing (CNLP) workflow with a machine learning-based prioritization tool named Mendelian Phenotype Search Engine (MPSE). MPSE accurately and robustly identified NICU patients selected for WGS by clinical experts from Rady Children’s Hospital in San Diego (AUC 0.86) and the University of Utah (AUC 0.85).
An Explainable Host Genetic Severity Predictor Model for COVID-19 Patients
A Onoja et al, MEDRXIV, March 9, 2023
(Posted: Mar-10-2023 3PM)
A host genetic severity predictor (HGSP) model was developed by combining several state-of-the-art machine learning algorithms (decision tree-based models: Random Forest and XGBoost classifiers). These models were trained using a genetic Whole Exome Sequencing (WES) dataset and clinical covariates (age and gender) formulated from a 5-fold stratified cross-validation computational strategy to randomly split the dataset to overcome model instability. Our study validated the HGSP model based on the 18 features (i.e., 16 identified candidate genetic variants and 2 covariates.
Prediction of SARS-CoV-2 transmission dynamics based on population-level cycle threshold values: A Machine learning and mechanistic modeling study
AA Khan et al, MEDRXIV, March 7, 2023
(Posted: Mar-07-2023 6PM)
Predictive models in emergency medicine and their missing data strategies: a systematic review.
Emilien Arnaud et al. NPJ digital medicine 2023 2 (1) 28
(Posted: Feb-26-2023 8AM)
In the field of emergency medicine (EM), the use of decision support tools based on artificial intelligence has increased markedly in recent years. In some cases, data are omitted deliberately and thus constitute “data not purposely collected” (DNPC). This accepted information bias can be managed in various ways: dropping patients with missing data, imputing with the mean, or using automatic techniques (e.g., machine learning) to handle or impute the data. Here, we systematically reviewed the methods used to handle missing data in EM research.
American Life in Realtime: a benchmark registry of health data for equitable precision health.
Ritika R Chaturvedi et al. Nature medicine 2023 2
(Posted: Feb-21-2023 7AM)
Emerging precision health methods use large-scale person-generated health data from smartphones and wearables to better characterize and, ultimately, improve health and well-being through strategies customized to individual context and need3,4. Applying artificial intelligence and machine learning to person-generated health data allows unprecedented assessment of recursive, networked and latent associations between everyday life and health, including social, structural and environmental exposures, behaviors, biometrics, and health outcomes.
Multi-center retrospective cohort study applying deep learning to electrocardiograms to identify left heart valvular dysfunction
A Vaid et al, Comm Med, February 14, 2023
(Posted: Feb-15-2023 7AM)
We use 617,338 ECGs paired to transthoracic echocardiograms from 123,096 patients to develop a deep learning model for detection of Mitral Regurgitation. Area Under Receiver Operating Characteristic curve (AUROC) is 0.88 (95% CI:0.88–0.89) in internal testing, and 0.81 (95% CI:0.80–0.82) in external validation. To develop a model for detection of Aortic Stenosis, we use 617,338 Echo-ECG pairs for 128,628 patients. AUROC is 0.89 (95% CI: 0.88-0.89) in internal testing, going to 0.86 (95% CI: 0.85-0.87) in external validation.
Machine-learning-aided multiplexed nanobiosensor for COVID-19 population immunity profiling
A Beisenova et al, MEDRXIV, February 8, 2023
(Posted: Feb-09-2023 6AM)
Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms
W Sun et al, NPJ Digital Medicine, February 6, 2023,
(Posted: Feb-06-2023 8AM)
We developed ECG-based machine learning models to predict risk of mortality among patients presenting to an emergency department or hospital for any reason. Using the 12-lead ECG traces and measurements from 1,605,268 ECGs from 748,773 healthcare episodes of 244,077 patients (2007–2020) in Alberta, Canada, we developed and validated ResNet-based Deep Learning (DL) and gradient boosting-based XGBoost (XGB) models to predict 30-day, 1-year, and 5-year mortality. The study demonstrates the validity of ECG-based DL mortality prediction models at the population-level that can be leveraged for prognostication at point of care.
Machine learning models for predicting severe COVID-19 outcomes in hospitals
P Wendland et al, MEDRXIV, January 30, 2023
(Posted: Jan-31-2023 8AM)
The aim of this observational retrospective study is to improve early risk stratification of hospitalized Covid-19 patients by predicting in-hospital mortality, transfer to intensive care unit (ICU) and mechanical ventilation from electronic health record data of the first 24 hours after admission. Methods and Results Our machine learning model predicts in-hospital mortality (AUC=0.918), transfer to ICU (AUC=0.821) and the need for mechanical ventilation (AUC=0.654) from a few laboratory data of the first 24 hours after admission.
A large-scale machine learning study of sociodemographic factors contributing to COVID-19 severity
M Tumbas et al, MEDRXIV, January 29, 2023
(Posted: Jan-30-2023 7AM)
We assemble 115 predictors for more than 3000 US counties and employ a well-defined COVID-19 severity measure derived from epidemiological dynamics modeling. We then use a number of advanced feature selection techniques from machine learning to determine which of these predictors significantly impact the disease severity. We obtain a surprisingly simple result, where only two variables are clearly and robustly selected - population density and proportion of African Americans.
Early detection of visual impairment in young children using a smartphone-based deep learning system.
Wenben Chen et al. Nature medicine 2023 1
(Posted: Jan-27-2023 7AM)
Videos from 3,652 children (=48 months in age; 54.5% boys) were prospectively collected to develop and validate this system. For detecting visual impairment, AIS achieved an area under the receiver operating curve (AUC) of 0.940 in an internal validation set and an AUC of 0.843 in an external validation set collected in multiple ophthalmology clinics across China. In a further test of AIS for at-home implementation by untrained parents or caregivers using their smartphones, the system was able to adapt to different testing conditions and achieved an AUC of 0.859.
Making machine learning matter to clinicians: model actionability in medical decision-making
DE Ehrmann et al, NPJ Digital Medicine, January 24, 2023
(Posted: Jan-24-2023 8AM)
Machine learning (ML) has the potential to transform patient care and outcomes. However, there are important differences between measuring the performance of ML models in silico and usefulness at the point of care. One lens to use to evaluate models during early development is actionability, which is currently undervalued. We propose a metric for actionability intended to be used before the evaluation of calibration and ultimately decision curve analysis and calculation of net benefit.
Explainable artificial intelligence for mental health through transparency and interpretability for understandability.
Joyce Dan W et al. NPJ digital medicine 2023 1 (1) 6
(Posted: Jan-21-2023 6AM)
The literature on artificial intelligence (AI) or machine learning (ML) in mental health and psychiatry lacks consensus on what “explainability” means. In the more general XAI (eXplainable AI) literature, there has been some convergence on explainability meaning model-agnostic techniques that augment a complex model (with internal mechanics intractable for human understanding) with a simpler model argued to deliver results that humans can comprehend.
A machine-learning-derived, in silico marker for CAD identifies underdiagnosed patients.
Huynh Karina et al. Nature reviews. Cardiology 2023 1
(Posted: Jan-21-2023 6AM)
Current risk prediction tools for coronary artery disease (CAD) do not measure disease on a continuous scale and use only a small number of variables for risk prediction, disregarding much of the data contained in electronic health records (EHRs). In a new study, a machine learning model trained using clinical data from EHRs generated a novel, in silico quantitative score for CAD that can quantify disease pathophysiology and clinical outcomes on a continuous spectrum.
Wearables and AI better predict the progression of muscular dystrophy
Nature Medicine, January 20, 2023
(Posted: Jan-21-2023 6AM)
Clinical trials in neurological diseases often involve subjective, qualitative endpoints, such ‘by eye’ observations of movement. We developed an artificial intelligence–based method to analyze natural daily behavior data from people with Duchenne muscular dystrophy, using machine-learning algorithms to accurately predict their personal disease trajectories better than conventional clinical assessments.
Machine learning identifies long COVID patterns from electronic health records.
et al. Nature medicine 2023 1
(Posted: Jan-17-2023 9AM)
A machine learning algorithm identifies four reproducible clinical subphenotypes of long COVID from the electronic health records of patients with post-acute sequelae of SARS-CoV-2 infection within 30–180 days of infection; these patterns have implications for the treatment and management of long COVID.
AI in the hands of imperfect users
KMK QUenet et al, NPJ Digital Medicine, December 28, 2022
(Posted: Dec-28-2022 11AM)
As the use of artificial intelligence and machine learning (AI/ML) continues to expand in healthcare, much attention has been given to mitigating bias in algorithms to ensure they are employed fairly and transparently. Less attention has fallen to addressing potential bias among AI/ML’s human users or factors that influence user reliance. We argue for a systematic approach to identifying the existence and impacts of user biases while using AI/ML tools and call for the development of embedded interface design features.
Identifying and evaluating barriers for the implementation of machine learning in the intensive care unit
E D'hondt et al, Comm Med, December 21, 2022
(Posted: Dec-21-2022 8AM)
Dietary metabolic signatures and cardiometabolic risk.
Shah Ravi V et al. European heart journal 2022 11
(Posted: Dec-17-2022 9AM)
Observational studies of diet in cardiometabolic-cardiovascular disease (CM-CVD) focus on self-reported consumption of food or dietary pattern, with limited information on individual metabolic responses to dietary intake linked to CM-CVD. Here, machine learning approaches were used to identify individual metabolic patterns related to diet and relation to long-term CM-CVD in early adulthood. We found that metabolic signatures of diet are associated with long-term CM-CVD independent of lifestyle and traditional risk factors. Metabolomics improves precision to identify adverse consequences and pathways of diet-related CM-CVD.
Deep learning-based age estimation from chest X-rays indicates cardiovascular prognosis.
Ieki Hirotaka et al. Communications medicine 2022 12 (1) 159
(Posted: Dec-12-2022 9AM)
In recent years, there has been considerable research on the use of artificial intelligence to estimate age and disease status from medical images. However, age estimation from chest X-ray (CXR) images has not been well studied and the clinical significance of estimated age has not been fully determined. To address this, we trained a deep neural network (DNN) model using more than 100,000 CXRs to estimate the patients' age solely from CXRs. We applied our DNN to CXRs of 1562 consecutive hospitalized heart failure patients, and 3586 patients admitted to the intensive care unit with cardiovascular disease.
Improving Machine Learning Diabetes Prediction Models for the Utmost Clinical Effectiveness
J Shin et al, J Per Med, November 14, 2022
(Posted: Nov-15-2022 9AM)
An immune dysfunction score for stratification of patients with acute infection based on whole-blood gene expression.
Cano-Gamez Eddie et al. Science translational medicine 2022 11 (669) eabq4433
(Posted: Nov-14-2022 6AM)
Predictors of severe infection could help physicians manage clinical care. Cano-Gamez et al. present an RNA-seq–based gene expression signature derived from patients with sepsis that generally captured patient prognosis with high sensitivity. Biologically, this signature corresponded to immune dysfunction. A machine learning framework based on the gene signature correctly stratified pediatric and adult patients with bacterial or viral sepsis, as well as patients with infection who did not meet sepsis criteria, including H1N1 influenza and COVID-19.
Health, socioeconomic and genetic predictors of COVID-19 vaccination uptake: a nationwide machine-learning study
T Hartonen et al, MEDRXIV, November 11, 2022
(Posted: Nov-12-2022 6AM)
Broad-capture proteomics and machine learning for early detection of type 2 diabetes risk
Nature Medicine, November 10, 2022
(Posted: Nov-11-2022 7AM)
Impaired glucose tolerance (IGT) is a common condition that affects glucose control after sugar consumption. Isolated IGT is undetected by screening and diagnostic strategies, leaving affected individuals at high risk of developing diabetes. Here, a machine-learning framework identifies a three-protein signature for detecting isolated IGT from a single blood sample.
Proteomic signatures for identification of impaired glucose tolerance
JC Zanini et al, Nature Medicine, November 10, 2022
(Posted: Nov-11-2022 7AM)
We applied machine learning to the proteomic profiles of a single fasted sample from 11,546 participants of the Fenland study to test discrimination of iIGT defined using the gold-standard OGTTs. We observed significantly improved discriminative performance by adding only three proteins (RTN4R, CBPM and GHR) to the best clinical model (AUROC = 0.80 (95% confidence interval: 0.79–0.86), P?=?0.004), which we validated in an external cohort. Increased plasma levels of these candidate proteins were associated with an increased risk for future T2D in an independent cohort and were also increased in individuals genetically susceptible to impaired glucose homeostasis and T2D.
A comprehensive knowledgebase of known and predicted human genetic variants associated with COVID-19 susceptibility and severity
Me Kars et al, MEDRXIV, November 7, 2022
(Posted: Nov-08-2022 7AM)
We collated 820 host genetic variants reported to affect COVID-19 susceptibility by means of a systematic literature search and confidence evaluation, and obtained 196 high-confidence variants. We then developed the first machine learning classifier of severe COVID-19 variants to perform a genome-wide prediction of COVID-19 severity for 82,468,698 missense variants in the human genome.
Multimodal machine learning in precision health: A scoping review
A Kline et al, NPJ Digital Medicine, November 7, 2022
(Posted: Nov-08-2022 7AM)
Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research.
Discovering a trans-omics biomarker signature that predisposes high risk diabetic patients to diabetic kidney disease
I W Wu et al, NPJ Digital Medicine, November 2, 2022
(Posted: Nov-03-2022 8AM)
Diabetic kidney disease is the leading cause of end-stage kidney disease worldwide; however, the integration of high-dimensional trans-omics data to predict this diabetic complication is rare. We develop artificial intelligence (AI)-assisted models using machine learning algorithms to identify a biomarker signature that predisposes high risk patients with diabetes mellitus (DM) to diabetic kidney disease based on clinical information, untargeted metabolomics, targeted lipidomics and genome-wide single nucleotide polymorphism (SNP) datasets. This involves 618 individuals who are split into training and testing cohorts of 557 and 61 subjects, respectively.
Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank.
A Papadopolou et al, MEDRXIV, October 30, 2022
(Posted: Oct-31-2022 9AM)
Machine learning models for predicting severe COVID-19 outcomes in hospitals
P Wendland et al, MEDRXIV, October 30, 2022
(Posted: Oct-31-2022 9AM)
The aim of this observational retrospective study is to improve early risk stratification of hospitalized Covid-19 patients by predicting in-hospital mortality, transfer to intensive care unit (ICU) and mechanical ventilation from electronic health record data of the first 24 hours after admission. Methods and Results Our machine learning model predicts in-hospital mortality (AUC=0.918), transfer to ICU (AUC=0.821) and the need for mechanical ventilation (AUC=0.654) from a few laboratory data of the first 24 hours after admission.
Spatio-temporal dynamics of three diseases caused by Aedes-borne arboviruses in Mexico
B Dong et al, Comm Med, October 28, 2022
(Posted: Oct-29-2022 10AM)
We present an integrated analysis of Aedes-borne diseases (ABDs), the local climate, and the socio-demographic profiles of 2469 municipalities in Mexico. We used SaTScan to detect spatial clusters and utilize the Pearson correlation coefficient, Randomized Dependence Coefficient, and SHapley Additive exPlanations to analyze the influence of socio-demographic and climatic factors on the prevalence of ABDs. We also compare six machine learning techniques, including XGBoost, decision tree, Support Vector Machine with Radial Basis Function kernel, K nearest neighbors, random forest, and neural network to predict risk factors of ABDs clusters.
Algorithms and the Future of Work
J Howard, NIOSH Blog, September 2022
(Posted: Oct-28-2022 9AM)
In the future of work, algorithms will provide many beneficial applications in occupational safety and health. While algorithm-enabled systems and devices may reduce sources of human error and enhance worker safety and health, algorithms may also introduce new sources of risks to worker wellbeing.
To ensure that the benefits of algorithm-enabled systems and devices have a prominent place in the future of work, now is the time to study how to effectively manage their risks.
Artificial intelligence and machine learning in cancer imaging
DM Koh, Comm Medicine, October 27, 2022
(Posted: Oct-27-2022 9AM)
An increasing array of tools is being developed using artificial intelligence (AI) and machine learning (ML) for cancer imaging. The development of an optimal tool requires multidisciplinary engagement to ensure that the appropriate use case is met, as well as to undertake robust development and testing prior to its adoption into healthcare systems. This multidisciplinary review highlights key developments in the field
Robust Machine Learning predicts COVID-19 Disease Severity based on Single-cell RNA-seq from multiple hospitals
A Lemsara et al, MEDRXIV, October 22, 2022
(Posted: Oct-24-2022 10AM)
We present a computational workflow based on a Multilayer perceptron network that predicts the necessity of mechanical ventilation from PBMCs single-cell RNA-seq data. The study includes patient cohorts from Bonn, Berlin, Stanford, and three Korean medical centers. Training and model validation are performed using Berlin and Bonn samples, while testing is performed on completely unseen samples from the Stanford and Korean datasets. Our model shows a high area under the receiver operating characteristic (AUROC) curve (Korea: 1 (CI:1-1), Stanford: 0.86 (CI:0.81-0.9)), proving our models robustness.
Intelligent risk prediction in public health using wearable device data
MM Raza et al, NPJ Digital Medicine, October 13, 2022
(Posted: Oct-13-2022 6AM)
A recent study found that machine learning can predict the risk of COVID-19 infection, by combining biometric data from wearable devices like Fitbit, with electronic symptom surveys. In doing so, they aim to increase the efficiency of test allocation when tracking disease spread in resource-limited settings. But the implications of technology that applies data from wearables stretch far beyond infection monitoring into healthcare delivery and research. The adoption and implementation of this type of technology will depend on regulation, impact on patient outcomes, and cost savings.
Interpretable machine learning prediction of all-cause mortality
Q Qiu et al, Comm Medicine, October 3, 2022
(Posted: Oct-04-2022 8AM)
We propose the IMPACT framework that uses XAI technique to explain a state-of-the-art tree ensemble mortality prediction model. We apply IMPACT to understand all-cause mortality for 1-, 3-, 5-, and 10-year follow-up times within the NHANES dataset, which contains 47,261 samples and 151 features.
Addressing racial disparities in surgical care with machine learning
J Halamka et al, NPJ Digital Medicine, September 30, 2022
(Posted: Oct-03-2022 6AM)
While inequalities will require numerous cultural, ethical, and sociological solutions, artificial intelligence-based algorithms may help address the problem by detecting bias in the data sets currently being used to make medical decisions. However, such AI-based solutions are only in early development.
Measurement of Exhaled Volatile Organic Compounds as a Biomarker for Personalised Medicine: Assessment of Short-Term Repeatability in Severe Asthma
A Azim et al, J Per Medicine, September 29, 2022
(Posted: Oct-02-2022 9AM)
The intra-subject and between-subject variability of each VOC was calculated across the 70 samples and identified 30.35% of VOCs to be erratic: variable between subjects but also variable in the same subject. Exclusion of these erratic VOCs from machine learning approaches revealed no apparent loss of structure to the underlying data or loss of relationship with salient clinical characteristics. Moreover, cluster evaluation by the silhouette coefficient indicates more distinct clustering.
Can Smartphones Help Predict Suicide?
E Barry, NY Times, September 30, 2022
(Posted: Oct-01-2022 7AM)
In the field of mental health, few new areas generate as much excitement as machine learning, which uses computer algorithms to better predict human behavior. There is, at the same time, exploding interest in biosensors that can track a person’s mood in real time, factoring in music choices, social media posts, facial expression and vocal expression. A unique research project is tracking hundreds of people at risk for suicide, using data from smartphones and wearable biosensors to identify periods of high danger — and intervene.
Predicting use of Intensive Care Units during the COVID-19 Pandemic
K Perez et al, Research Square, September 30, 2022
(Posted: Oct-01-2022 7AM)
We propose ten approaches to represent the dynamics and predict the number of additional ICU beds required in the future. Machine learning models and classical time series analysis algorithms allow upper and lower bounds to be set for the number of units needed. Evaluating the predictions with 2020 and 2021 data in three representative geographic regions produces lower errors in the largest of the regions.
A machine learning approach identifies unresolving secondary pneumonia as a contributor to mortality in patients with severe pneumonia, including COVID-19
CA Gao et al, MEDRXIV, September 25, 2022
(Posted: Sep-27-2022 8AM)
Integrated multimodal artificial intelligence framework for healthcare applications
LR Soenksen et al, NPJ Digital Medicine, September 20, 2022
(Posted: Sep-21-2022 7AM)
AI systems leveraging multiple data sources and input modalities are poised to become a viable method to deliver more accurate results and deployable pipelines across a wide range of applications. In this work, we propose and evaluate a unified Holistic AI in Medicine (HAIM) framework to facilitate the generation and testing of AI systems that leverage multimodal inputs. Our approach uses generalizable data pre-processing and machine learning modeling stages that can be readily adapted for research and deployment in healthcare environments.
Machine Learning Algorithms for Prediction of Survival by Stress Echocardiography in Chronic Coronary Syndromes
L Cortiginai et al, J Per Med, September 16, 2022
(Posted: Sep-18-2022 5AM)
Stress echocardiography (SE) is based on regional wall motion abnormalities and coronary flow velocity reserve (CFVR). Their independent prognostic capabilities could be better studied with a machine learning (ML) approach. The study aims to assess the SE outcome data by conducting an analysis with an ML approach. We included 6881 prospectively recruited and retrospectively analyzed patients with suspected (n = 4279) or known (n = 2602) coronary artery disease.
Steps to avoid overuse and misuse of machine learning in clinical research
V Volovici et al, Nature Medicine, September 12, 2022,
(Posted: Sep-12-2022 1PM)
Machine learning algorithms are a powerful tool in healthcare, but sometimes perform no better than traditional statistical techniques. Steps should be taken to ensure that algorithms are not overused or misused, in order to provide genuine benefit for patients. The lackluster performance of many machine learning (ML) systems in healthcare has been well documented. In healthcare, as in other areas, AI algorithms can even perpetuate human prejudices such as sexism and racism when trained on biased datasets.
Subpopulation-specific machine learning prognosis for underrepresented patients with double prioritized bias correction
S Afrose et al, Comm Medicine, September 1, 2022
(Posted: Sep-01-2022 2PM)
Biases exist in the widely accepted one-machine-learning-model-fits-all-population approach. We invent a bias correction method that produces specialized machine learning prognostication models for underrepresented racial and age groups. This technique may reduce potentially life-threatening prediction mistakes for minority populations.
Clinical trial design in the era of precision medicine
E Fountzilas et al, Genome Medicine, August 31, 2022
(Posted: Aug-31-2022 7AM)
Multiple new trial designs, including basket and umbrella trials, master platform trials, and N-of-1 patient-centric studies, are beginning to supplant standard phase I, II, and III protocols, allowing for accelerated drug evaluation and approval and molecular-based individualized treatment. Furthermore, real-world data, as well as exploitation of digital apps and structured observational registries, and the utilization of machine learning and/or artificial intelligence, may further accelerate knowledge acquisition.
Development and Validation of a Deep Learning Model for Predicting Treatment Response in Patients With Newly Diagnosed Epilepsy
H Hakim et al, JAMA Neurology, August 29, 2022
(Posted: Aug-29-2022 1PM)
Can a machine learning model predict treatment success of the initial antiseizure medication? With the use of routinely collected clinical information, this cohort study developed a deep learning model on a pooled cohort of 1798 adults with newly diagnosed epilepsy seen in 5 centers in 4 countries. The model showed potential in predicting treatment success on the first prescribed antiseizure medication.
A Machine Learning Approach to Predict SARS-CoV-2 Infection by Clinical Symptoms
R Yang et al, SSRN, August 24, 2022
(Posted: Aug-26-2022 8AM)
A machine learning framework supporting prospective clinical decisions applied to risk prediction in oncology
L Coombs et al, NPJ Digital Medicine, August 16, 2022
(Posted: Aug-17-2022 10AM)
We present a general framework for developing a machine learning (ML) tool that supports clinician assessment of patient risk using electronic health record-derived real-world data and apply the framework to a quality improvement use case in an oncology setting to identify patients at risk for a near-term (60 day) emergency department (ED) visit who could potentially be eligible for a home-based acute care program.
Artificial intelligence was supposed to transform health care. It hasn’t.
B Leonard et al, Politico, August 15, 2022
(Posted: Aug-16-2022 6PM)
Machine learning could improve medicine by analyzing data to improve diagnoses and target cures, but technological, bureaucratic, and regulatory obstacles have slowed progress. AI hasn’t lived up to the hype, medical experts said, because health systems’ infrastructure isn’t ready for it yet. And the government is just beginning to grapple with its regulatory role.
Deep learning predicts all-cause mortality from longitudinal total-body DXA imaging
Y Glaser et al, Comm Medicine, August 16, 2022
(Posted: Aug-16-2022 10AM)
This study tests two hypotheses to improve all-cause mortality prediction. The first hypothesis is that features derived from raw total-body DXA imaging using deep learning are predictive of all-cause mortality with and without clinical risk factors, meanwhile, the second hypothesis states that sequential total-body DXA scans and recurrent neural network models outperform comparable models using only one observation with and without clinical risk factors.
A systems approach towards remote health-monitoring in older adults: Introducing a zero-interaction digital exhaust
N Shutz et al, NPJ Digital Medicine, August 16, 2022
(Posted: Aug-16-2022 10AM)
We introduce and describe a zero-interaction digital exhaust: a set of 1268 digital measures that cover large parts of a person’s activity, behavior and physiology. Making this approach more inclusive of older adults, we base this set entirely on contactless, zero-interaction sensing technologies. Applying the resulting digital exhaust to real-world data, we then demonstrate the possibility to create multiple ageing relevant digital clinical outcome assessments. Paired with modern machine learning, we find these assessments to be surprisingly powerful and often on-par with mobile approaches
Fast and noninvasive electronic nose for sniffing out COVID-19 based on exhaled breath-print recognition
DK Nurputra et al, NPJ Digital Medicine, August 16, 2022
(Posted: Aug-16-2022 10AM)
Here, we report on the development and use of a low cost, noninvasive method to rapidly sniff out COVID-19 based on a portable electronic nose (GeNose C19) integrating an array of metal oxide semiconductor gas sensors, optimized feature extraction, and machine learning models. This approach was evaluated in profiling tests involving a total of 615 breath samples composed of 333 positive and 282 negative samples. Our results suggest that GeNose C19 can be considered a highly potential breathalyzer for fast COVID-19 screening.
Interactive exploration of a global clinical network from a large breast cancer cohort
N Sella et al, NPJ Diital Medicine, August 10, 2022
(Posted: Aug-10-2022 8AM)
Despite unprecedented amount of information now available in medical records, health data remain underexploited due to their heterogeneity and complexity. Simple charts and hypothesis-driven statistics can no longer apprehend the content of information-rich clinical data. There is, therefore, a clear need for powerful interactive visualization tools enabling medical practitioners to perceive the patterns and insights gained by state-of-the-art machine learning algorithms. Here, we report an interactive graphical interface for use as the front end of a machine learning causal inference server (MIIC), to facilitate the visualization and comprehension by clinicians of relationships between clinically relevant variables.
Developing machine learning algorithms for dynamic estimation of progression during active surveillance for prostate cancer.
Lee Changhee et al. NPJ digital medicine 2022 8 (1) 110
(Posted: Aug-08-2022 10AM)
Active Surveillance (AS) for prostate cancer is a management option that continually monitors early disease and considers intervention if progression occurs. A robust method to incorporate “live” updates of progression risk during follow-up has hitherto been lacking. To address this, we developed a deep learning-based individualised longitudinal survival model using Dynamic-DeepHit-Lite (DDHL) that learns data-driven distribution of time-to-event outcomes.
Exploring Links Between Psychosis and Frontotemporal Dementia Using Multimodal Machine Learning: Dementia Praecox Revisited.
Koutsouleris Nikolaos et al. JAMA psychiatry 2022 8
(Posted: Aug-05-2022 8AM)
In this diagnostic/prognostic study including 1870 patients, patients with schizophrenia expressed the neuroanatomical pattern of behavioral-variant frontotemporal dementia more strongly (41%) than that of Alzheimer disease (17%), and at lower levels, this difference was also encountered in those with major depression (22% vs 3%). Already in clinical high-risk states for psychosis the high expression of the behavioral-variant frontotemporal dementia pattern was linked to severe phenotypes, unfavorable courses, and elevated polygenic risks for schizophrenia and dementia, with further pattern progression being present in those patients who did not recover over time.
Identification of robust deep neural network models of longitudinal clinical measurements
H Javidi et al, NPJ Digital Medicine, July 27, 2022
(Posted: Jul-28-2022 6AM)
Deep learning (DL) from electronic health records holds promise for disease prediction, but systematic methods for learning from simulated longitudinal clinical measurements have yet to be reported. We compared nine DL frameworks using simulated body mass index (BMI), glucose, and systolic blood pressure trajectories, independently isolated shape and magnitude changes, and evaluated model performance across various parameters (e.g., irregularity, missingness).
Machine learning for real-time aggregated prediction of hospital admission for emergency patients
Z King et al, NPJ Digital Medicine, July 27, 2022
(Posted: Jul-27-2022 10AM)
Machine learning for hospital operations is under-studied. We present a prediction pipeline that uses live electronic health-records for patients in a UK teaching hospital’s emergency department (ED) to generate short-term, probabilistic forecasts of emergency admissions. A set of XGBoost classifiers applied to 109,465 ED visits yielded AUROCs from 0.82 to 0.90 depending on elapsed visit-time at the point of prediction.
Machine Learning Analysis of Handgun Transactions to Predict Firearm Suicide Risk.
Laqueur Hannah S et al. JAMA network open 2022 7 (7) e2221041
(Posted: Jul-24-2022 11AM)
Can handgun purchasing records, coupled with machine learning techniques, be used to forecast firearm suicide risk?
In this prognostic study of nearly 2 million individuals with handgun transaction records, among transactions classified in the riskiest 5%, close to 40% were associated with a purchaser who died by firearm suicide within 1 year. Among the small number of transactions with a random forest score of 0.95 and above, more than two-thirds were affiliated with a purchaser who died by firearm suicide within 1 year (24 of 35).
Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis
R Adams et al, Nature Medicine, July 21, 2022
(Posted: Jul-22-2022 8AM)
Early recognition and treatment of sepsis are linked to improved patient outcomes. Machine learning-based early warning systems may reduce the time to recognition, but few systems have undergone clinical evaluation. In this prospective, multi-site cohort study, we examined the association between patient outcomes and provider interaction with a deployed sepsis alert system called the Targeted Real-time Early Warning System (TREWS). Our findings indicate that early warning systems have the potential to identify sepsis patients early and improve patient outcomes and that sepsis patients who would benefit the most from early treatment can be identified and prioritized at the time of the alert.
Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing
KE Henry et al, Nature Medicine, July 21, 2022
(Posted: Jul-22-2022 8AM)
We analyzed provider interactions with a sepsis early detection tool (Targeted Real-time Early Warning System), which was deployed at five hospitals over a 2-year period. Among 9,805 retrospectively identified sepsis cases, the early detection tool achieved high sensitivity (82% of sepsis cases were identified) and a high rate of adoption: 89% of all alerts by the system were evaluated by a physician or advanced practice provider and 38% of evaluated alerts were confirmed by a provider. Patients with sepsis whose alert was confirmed by a provider within 3?h had a 1.85-h (95% CI 1.66–2.00) reduction in median time to first antibiotic order compared to patients with sepsis whose alert was either dismissed, confirmed more than 3?h after the alert or never addressed in the system.
Human–machine teaming is key to AI adoption: clinicians’ experiences with a deployed machine learning system
KE Henry et al, NPJ Digital Medicine, July 21, 2022
(Posted: Jul-21-2022 7AM)
Based on a qualitative analysis of coded interviews with clinicians who use an ML-based system for sepsis, we found that, rather than viewing the system as a surrogate for their clinical judgment, clinicians perceived themselves as partnering with the technology. Our findings suggest that, even without a deep understanding of machine learning, clinicians can build trust with an ML system through experience, expert endorsement and validation, and systems designed to accommodate clinicians’ autonomy and support them across their entire workflow.
Generalizable Long COVID Subtypes: Findings from the NIH N3C and RECOVER Programs
J Reese et al, MEDRXIV, July 20, 2022
(Posted: Jul-21-2022 7AM)
The natural history of long COVID is incompletely understood and characterized by an extremely wide range of manifestations that are difficult to analyze computationally. In addition, the generalizability of machine learning classification of COVID-19 clinical outcomes has rarely been tested. We present a method for computationally modeling PASC phenotype data based on electronic healthcare records (EHRs) and for assessing pairwise phenotypic similarity between patients using semantic similarity.
Dynamic prediction of mortality after traumatic brain injury using a machine learning algorithm
R Rai et al, NPJ Digital Medicine, July 18, 2022
(Posted: Jul-18-2022 11AM)
We retrained and externally validated a machine learning model to dynamically predict the risk of mortality in patients with TBI. Retraining was done in 686 patients with 62,000?h of data and validation was done in two international cohorts including 638 patients with 60,000?h of data. The area under the receiver operating characteristic curve increased with time to 0.79 and 0.73 and the precision recall curve increased with time to 0.57 and 0.64 in the Swedish and American validation cohorts, respectively.
Multisite implementation of a workflow-integrated machine learning system to optimize COVID-19 hospital admission decisions
JS Hinson et la, NPJ Digital Medicine, July 16, 2022
(Posted: Jul-17-2022 2PM)
In this study, we developed, implemented and evaluated an electronic health record (EHR) embedded clinical decision support (CDS) system that leverages machine learning (ML) to estimate short-term risk for clinical deterioration in patients with or under investigation for COVID-19. The system translates model-generated risk for critical care needs within 24?h and inpatient care needs within 72?h into rapidly interpretable COVID-19 Deterioration Risk Levels made viewable within ED clinician workflow. ML models were derived in a retrospective cohort of 21,452 ED patients who visited one of five ED study sites and were prospectively validated in 15,670 ED visits.
Development of a multiomics model for identification of predictive biomarkers for COVID-19 severity: a retrospective cohort study
SK Byeon et al, The Lancet Digital Health, July 11, 2022
(Posted: Jul-14-2022 6AM)
We quantified 1463 cytokines and circulatory proteins, along with 902 lipids and 1018 metabolites. By developing a machine-learning-based prediction model, a set of 102 biomarkers, which predicted severe and clinical COVID-19 outcomes better than the traditional set of cytokines, were discovered. These predictive biomarkers included several novel cytokines and other proteins, lipids, and metabolites.
Machine learning-based quantitative prediction of drug exposure in drug-drug interactions using drug label information
HY Jang et al, NPJ Digital Medicine, July 11, 2022
(Posted: Jul-13-2022 7AM)
Many machine learning techniques provide a simple prediction for drug-drug interactions (DDIs). However, a systematically constructed database with pharmacokinetic (PK) DDI information does not exist, nor is there a machine learning model that numerically predicts PK fold change (FC) with it. Therefore, we propose a PK DDI prediction (PK-DDIP) model for quantitative DDI prediction with high accuracy, while constructing a highly reliable PK-DDI database.
Multi-center validation of machine learning model for preoperative prediction of postoperative mortality
SW Lee et al, NPJ Digital Medicine, July 12, 2022
(Posted: Jul-13-2022 7AM)
This study aimed to create a machine-learning prediction model for 30-day mortality after a non-cardiac surgery that adapts to the manageable amount of clinical information as input features and is validated against multi-centered rather than single-centered data. Data were collected from 454,404 patients over 18 years of age who underwent non-cardiac surgeries from four independent institutions.
Automated sequence-based annotation and interpretation of the human genome.
Kundaje Anshul et al. Nature genetics 2022 7
(Posted: Jul-13-2022 7AM)
A machine-learning model produces summarized sequence representations of genomic regulatory activity, and provides a functional view of regulatory DNA variation in the human genome, with the aim of better understanding the role of sequence variation in health and disease.
Machine learning to support visual auditing of home-based lateral flow immunoassay self-test results for SARS-CoV-2 antibodies
NCK Wong et al, Comm Medicine, July 6, 2022
(Posted: Jul-07-2022 7AM)
Lateral flow immunoassays (LFIAs) are being used worldwide for COVID-19 mass testing and antibody prevalence studies. Relatively simple to use and low cost, these tests can be self-administered at home, but rely on subjective interpretation of a test line by eye, risking false positives and false negatives. Here, we report on the development of ALFA (Automated Lateral Flow Analysis) to improve reported sensitivity and specificity.
Shifting machine learning for healthcare from development to deployment and from models to data
A Zhang et al, Nat Biomed Engineering, July 4, 2022
(Posted: Jul-05-2022 7AM)
In this Review, we provide a data-centric view of the innovations and challenges that are defining ML for healthcare. We discuss deep generative models and federated learning as strategies to augment datasets for improved model performance, as well as the use of the more recent transformer models for handling larger datasets and enhancing the modelling of clinical text. We also discuss data-focused problems in the deployment of ML, emphasizing the need to efficiently deliver data to ML models for timely clinical predictions.
Measuring biological age using omics data.
Rutledge Jarod et al. Nature reviews. Genetics 2022 6
(Posted: Jun-20-2022 10AM)
Spurred by recent advances in high-throughput omics technologies, a new generation of tools to measure biological ageing now enables the quantitative characterization of ageing at molecular resolution. Epigenomic, transcriptomic, proteomic and metabolomic data can be harnessed with machine learning to build ‘ageing clocks’ with demonstrated capacity to identify new biomarkers of biological ageing.
Two-Step Machine Learning to Diagnose and Predict Involvement of Lungs in COVID-19 and Pneumonia using CT Radiomics
CM Khaniabadi et al, MEDRXIV, June 16, 2022
(Posted: Jun-17-2022 9AM)
Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms
M Bernhardt et al, Nature Medicine, June 16, 2022
(Posted: Jun-16-2022 0PM)
An increasing number of reports raise concerns about the risk that machine learning algorithms could amplify health disparities due to biases embedded in the training data. We argue that the experimental setup in the study is insufficient to study algorithmic underdiagnosis. In the absence of specific knowledge (or assumptions) about the extent and nature of the dataset bias, it is difficult to investigate model bias. Importantly, their use of test data exhibiting the same bias as the training data (due to random splitting) severely complicates the interpretation of the reported disparities.
Usability of deep learning and H&E images predict disease outcome-emerging tool to optimize clinical trials
T Qaiser et al, NPJ Precision Oncology, June 15, 2022
(Posted: Jun-15-2022 8AM)
Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening
J Yang et al, NPJ Digital Medicine, June 7, 2022
(Posted: Jun-07-2022 10AM)
As patient health information is highly regulated due to privacy concerns, most machine learning (ML)-based healthcare studies are unable to test on external patient cohorts, resulting in a gap between locally reported model performance and cross-site generalizability. Different approaches have been introduced for developing models across multiple clinical sites, however less attention has been given to adopting ready-made models in new settings. We introduce three methods to do this—(1) applying a ready-made model “as-is” (2); readjusting the decision threshold on the model’s output using site-specific data and (3); finetuning the model using site-specific data via transfer learning.
Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data
S Li et al, NPJ Digital Medicine, June 6, 2022
(Posted: Jun-06-2022 7AM)
We assessed whether information routinely collected in electronic medical records (EMR) could enhance the prediction of preeclampsia risk beyond what is achieved in standard of care assessments. We developed a digital phenotyping algorithm to curate 108,557 pregnancies from EMRs across the Mount Sinai Health System, accurately reconstructing pregnancy journeys and normalizing these journeys across different hospital EMR systems. We then applied machine learning approaches to a training dataset (N?=?60,879) to construct predictive models of preeclampsia across three major pregnancy time periods (ante-, intra-, and postpartum). The resulting models predicted preeclampsia with high accuracy across the different pregnancy periods, with areas under the receiver operating characteristic curves (AUC) of 0.92, 0.82, and 0.89 at 37 gestational weeks, intrapartum and postpartum, respectively.
Contrastive machine learning reveals the structure of neuroanatomical variation within autism.
Aglinskas Aidas et al. Science (New York, N.Y.) 2022 6 (6597) 1070-1074
(Posted: Jun-04-2022 7AM)
Autism spectrum disorder (ASD) is highly heterogeneous. Identifying systematic individual differences in neuroanatomy could inform diagnosis and personalized interventions. The challenge is that these differences are entangled with variation because of other causes: individual differences unrelated to ASD and measurement artifacts. We used contrastive deep learning to disentangle ASD-specific neuroanatomical variation from variation shared with typical control participants. ASD-specific variation correlated with individual differences in symptoms. The structure of this ASD-specific variation also addresses a long-standing debate about the nature of ASD: At least in terms of neuroanatomy, individuals do not cluster into distinct subtypes; instead, they are organized along continuous dimensions that affect distinct sets of regions.
Applying machine-learning to rapidly analyse large qualitative text datasets to inform the COVID-19 pandemic response: Comparing human and machine-assisted topic analysis techniques
L Towler et al, MEDRXIV, June 1, 2022
(Posted: Jun-02-2022 6AM)
Machine learning paves the way toward the prevention of mental health crises
Nature Medicine, May 18, 2022
(Posted: May-19-2022 10AM)
Experiencing a mental health crisis has a detrimental impact on a patient’s life. A machine learning algorithm trained retrospectively with electronic health records can predict almost 60% of mental health crises 4 weeks in advance. Prospective evaluation of the algorithm in clinical practice reveals its potential to enable preemptive interventions.
Machine learning model to predict mental health crises from electronic health records
R Garriga et al, Nature Medicine, May 16, 2022
(Posted: May-17-2022 11AM)
We developed a machine learning model that uses electronic health records to continuously monitor patients for risk of a mental health crisis over a period of 28?days. The model achieves an area under the receiver operating characteristic curve of 0.797 and an area under the precision-recall curve of 0.159, predicting crises with a sensitivity of 58% at a specificity of 85%. A follow-up 6-month prospective study evaluated our algorithm’s use in clinical practice and observed predictions to be clinically valuable in terms of either managing caseloads or mitigating the risk of crisis in 64% of cases.
Machine learning uncovers blood test patterns subphenotypes at hospital admission discerning increased 30-day ICU mortality rates in COVID-19 elderly patients
L Zhou et al, MEDRXIV, May 10, 2022
(Posted: May-11-2022 7AM)
Machine learning assisted analysis on TCR profiling data from COVID-19-convalescent and healthy individuals unveils cross-reactivity between SARS-CoV-2 and a wide spectrum of pathogens and other diseases
GK Georgakilas et al, MEDRXIV, May 10, 2022
(Posted: May-11-2022 7AM)
Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disorder
JK Megerian et al, NPJ DIgital Medicine, May 5, 2022
(Posted: May-05-2022 6AM)
This double-blinded, multi-site, prospective, active comparator cohort study tested the accuracy of an artificial intelligence-based Software as a Medical Device designed to aid primary care healthcare providers (HCPs) in diagnosing ASD. The Device combines behavioral features from three distinct inputs (a caregiver questionnaire, analysis of two short home videos, and an HCP questionnaire) in a gradient boosted decision tree machine learning algorithm to produce either an ASD positive, ASD negative, or indeterminate output. This study compared Device outputs to diagnostic agreement by two or more independent specialists in a cohort of 18–72-month-olds with developmental delay concerns.
Machine learning and health need better values
M Ghassemi et al, NPJ Digital Medicine, April 22, 2022
(Posted: Apr-25-2022 9AM)
For machine learning to achieve its aims of supporting healthier living while minimizing harm, we believe that a deeper introspection of our field’s values and contentions is overdue. In this perspective, we highlight notable areas in need of attention within the field. We believe deliberate and informed introspection will lead our community to renewed opportunities for understanding disease, new partnerships with clinicians and patients, and allow us to better support people and communities to live healthier, dignified lives.
COVID-19 GPH: tracking the contribution of genomics and precision health to the COVID-19 pandemic response
W Yu et al, BMC Infectious Diseases, April 25, 2022
(Posted: Apr-25-2022 8AM)
To quantify and track the ongoing contributions of genomics and precision health to the COVID-19 response, the Office of Genomics and Precision Public Health at the Centers for Disease Control and Prevention created the COVID-19 Genomics and Precision Health database (COVID-19 GPH), an open access knowledge management system and publications database that is continuously updated through machine learning and manual curation.
This unique knowledge management database makes it easier to explore, describe, and track how the pandemic response is accelerating the applications of genomics and precision health technologies.
Machine learning approaches to predicting no-shows in pediatric medical appointment
D Liu et al, NPJ Digital Medicine, April 20, 2022
(Posted: Apr-20-2022 7AM)
The retrospective study was conducted in an academic pediatric teaching hospital with a 20% no-show rate. Our approach tackles several challenges in the design of a predictive model by (1) adopting a data imputation method for patients with missing information in their records (77% of the population), (2) exploiting local weather information to improve predictive accuracy, and (3) developing an interpretable approach that explains how a prediction is made for each individual patient. Our proposed neural network-based and logistic regression-based methods outperformed persistence baselines. In an unobserved set of patients, our method correctly identified 83% of no-shows at the time of scheduling and led to a false alert rate less than 17%.
Using AI to predict future cardiac arrest
K O'Leary, Nature Medicine, April 14, 2022
(Posted: Apr-18-2022 9AM)
Sudden cardiac death from arrhythmia (SCDA) is a leading cause of mortality worldwide, especially among people with heart disease. Although implantable devices can effectively prevent SCDA, assessment tools for identifying those at risk are hugely inadequate. A new study developed a machine-learning model for predicting SCDA risk (at all times up to 10 years) in people with ischemic heart disease. The model uses neural networks that learn from scarring patterns on magnetic resonance images and from clinical covariates. It was developed and tested on an internal cohort (N = 156) and an external multi-center cohort (N = 113), and was shown to outperform current risk-prediction models.
Evaluation of machine learning for predicting COVID-19 outcomes from a national electronic medical records database
S Browning et al, MEDRXIV, April 14, 2022
(Posted: Apr-16-2022 1PM)
When novel diseases such as COVID-19 emerge, predictors of clinical outcomes might be unknown. Using data from electronic medical records (EMR) allows evaluation of potential predictors without selecting specific features a priori for a model. We evaluated different machine learning models for predicting outcomes among COVID-19 inpatients using raw EMR data. We found that predictive models using raw EMR data are promising because they can use many observations and encompass a large feature space; however, traditional and deep learning models may perform similarly when few features are available at the individual patient level.
A high-generalizability machine learning framework for predicting the progression of Alzheimer’s disease using limited data
C Wang et al, NPJ Digital Medicine, April 12, 2022
(Posted: Apr-12-2022 0PM)
Alzheimer’s disease is a neurodegenerative disease that imposes a substantial financial burden on society. A number of machine learning studies have been conducted to predict the speed of its progression, which varies widely among different individuals, for recruiting fast progressors in future clinical trials. However, because the data in this field are very limited, two problems have yet to be solved: the first is that models built on limited data tend to induce overfitting and have low generalizability, and the second is that no cross-cohort evaluations have been done.
Machine learning for medical imaging: methodological failures and recommendations for the future
G Varoqueaux et al, NPJ Digital Medicine, April 12, 2022
(Posted: Apr-12-2022 0PM)
Research in computer analysis of medical images bears many promises to improve patients’ health. However, a number of systematic challenges are slowing down the progress of the field, from limitations of the data, such as biases, to research incentives, such as optimizing for publication. In this paper we review roadblocks to developing and assessing methods. Building our analysis on evidence from the literature and data challenges, we show that at every step, potential biases can creep in
A machine-learning based objective measure for ALS disease severity
FG Vieira et al, NPJ Digital Medicine, April 8, 2022
(Posted: Apr-09-2022 2PM)
We developed a machine learning (ML) based objective measure for ALS disease severity based on voice samples and accelerometer measurements from a four-year longitudinal dataset. 584 people living with ALS consented and carried out prescribed speaking and limb-based tasks. 542 participants contributed 5814 voice recordings, and 350 contributed 13,009 accelerometer samples, while simultaneously measuring ALSFRS-R scores.
Elucidation of Infection Asperity of CT Scan Images of COVID-19 Positive Cases: A Machine Learning Perspectives
DS Vinod et al, Research Square, April 8, 2022
(Posted: Apr-09-2022 1PM)
Validation and algorithmic audit of a deep learning system for the detection of proximal femoral fractures in patients in the emergency department: a diagnostic accuracy study
LO Rayner et al, Lancet Digital Health, April 5, 2022
(Posted: Apr-07-2022 10AM)
Covid-19's influence on cardiac function: a machine learning perspective on ECG analysis
JC Gomes et al, Research Square, April 5, 2022
(Posted: Apr-06-2022 8AM)
The principles of whole-hospital predictive analytics monitoring for clinical medicine originated in the neonatal ICU
JD Moorman, NPJ Digital Medicine, March 31, 2022
(Posted: Apr-02-2022 8AM)
In 2011, a multicenter group spearheaded at the University of Virginia demonstrated reduced mortality from real-time continuous cardiorespiratory monitoring in the neonatal ICU using what we now call Artificial Intelligence, Big Data, and Machine Learning. The large, randomized heart rate characteristics trial made real, for the first time that we know of, the promise that early detection of illness would allow earlier and more effective intervention and improved patient outcomes.
An 8-gene machine learning model improves clinical prediction of severe dengue progression
YE Liu et al, Genome Medicine, March 28, 2022
(Posted: Mar-30-2022 7AM)
The 8-gene XGBoost model, trained on heterogeneous public datasets, accurately predicted progression to SD in a large, independent, prospective cohort, including during the early febrile stage when SD prediction remains clinically difficult. The model has potential to be translated to a point-of-care prognostic assay to reduce dengue morbidity and mortality without overwhelming limited healthcare resources.
Machine learning of language use on Twitter reveals weak and non-specific predictions
SW Kelley et al, NPJ Digital Medicine, March 25, 2022
(Posted: Mar-26-2022 3PM)
Depressed individuals use language differently than healthy controls and it has been proposed that social media posts can be used to identify depression. Much of the evidence behind this claim relies on indirect measures of mental health and few studies have tested if these language features are specific to depression versus other aspects of mental health. We analysed the Tweets of 1006 participants who completed questionnaires assessing symptoms of depression and 8 other mental health conditions.
