Optimal fusion of genotype and drug embeddings in predicting cancer drug response.

Predicting cancer drug response using both genomics and drug features has shown some success compared to using genomics features alone. However, there has been limited research done on how best to combine or fuse the two types of features. Using a visible neural network with two deep learning branches for genes and drug features as the base architecture, we experimented with different fusion functions and fusion points. Our experiments show that injecting multiplicative relationships between gene and drug latent features into the original concatenation-based architecture DrugCell significantly improved the overall predictive performance and outperformed other baseline models. We also show that different fusion methods respond differently to different fusion points, indicating that the relationship between drug features and different hierarchical biological level of gene features is optimally captured using different methods. Considering both predictive performance and runtime speed, tensor product partial is the best-performing fusion function to combine late-stage representations of drug and gene features to predict cancer drug response.

Dynamic clustering via branched deep learning enhances personalization of stress prediction from mobile sensor data.

College students experience ever-increasing levels of stress, leading to a wide range of health problems. In this context, monitoring and predicting students' stress levels is crucial and, fortunately, made possible by the growing support for data collection via mobile devices. However, predicting stress levels from mobile phone data remains a challenging task, and off-the-shelf deep learning models are inapplicable or inefficient due to data irregularity, inter-subject variability, and the "cold start problem". To overcome these challenges, we developed a platform named Branched CALM-Net that aims to predict students' stress levels through dynamic clustering in a personalized manner. This is the first platform that leverages the branching technique in a multitask setting to achieve personalization and continuous adaptation. Our method achieves state-of-the-art performance in predicting student stress from mobile sensor data collected as part of the Dartmouth StudentLife study, with a ROC AUC 37% higher and a PR AUC surpassing that of the nearest baseline models. In the cold-start online learning setting, Branched CALM-Net outperforms other models, attaining an average F1 score of 87% with just 1 week of training data for a new student, which shows it is reliable and effective at predicting stress levels from mobile data.

Computational estimates of annular diameter reveal genetic determinants of mitral valve function and disease.

The fibrous annulus of the mitral valve plays an important role in valvular function and cardiac physiology, while normal variation in the size of cardiovascular anatomy may share a genetic link with common and rare disease. We derived automated estimates of mitral valve annular diameter in the 4-chamber view from 32,220 MRI images from the UK Biobank at ventricular systole and diastole as the basis for GWAS. Mitral annular dimensions corresponded to previously described anatomical norms, and GWAS inclusive of 4 population strata identified 10 loci, including possibly novel loci (GOSR2, ERBB4, MCTP2, MCPH1) and genes related to cardiac contractility (BAG3, TTN, RBFOX1). ATAC-Seq of primary mitral valve tissue localized multiple variants to regions of open chromatin in biologically relevant cell types and rs17608766 to an algorithmically predicted enhancer element in GOSR2. We observed strong genetic correlation with measures of contractility and mitral valve disease and clinical correlations with heart failure, cerebrovascular disease, and ventricular arrhythmias. Polygenic scoring of mitral valve annular diameter in systole was predictive of risk mitral valve prolapse across 4 cohorts. In summary, genetic and clinical studies of mitral valve annular diameter revealed genetic determinants of mitral valve biology, while highlighting clinical associations. Polygenic determinants of mitral valve annular diameter may represent an independent risk factor for mitral prolapse. Overall, computationally estimated phenotypes derived at scale from medical imaging represent an important substrate for genetic discovery and clinical risk prediction.

Cardiac Imaging of Aortic Valve Area From 34 287 UK Biobank Participants Reveals Novel Genetic Associations and Shared Genetic Comorbidity With Multiple Disease Phenotypes.

BACKGROUND: The aortic valve is an important determinant of cardiovascular physiology and anatomic location of common human diseases. METHODS: From a sample of 34 287 white British ancestry participants, we estimated functional aortic valve area by planimetry from prospectively obtained cardiac magnetic resonance imaging sequences of the aortic valve. Aortic valve area measurements were submitted to genome-wide association testing, followed by polygenic risk scoring and phenome-wide screening, to identify genetic comorbidities. RESULTS: A genome-wide association study of aortic valve area in these UK Biobank participants showed 3 significant associations, indexed by rs71190365 (chr13:50764607, DLEU1, P=1.8×10-9), rs35991305 (chr12:94191968, CRADD, P=3.4×10-8), and chr17:45013271:C:T (GOSR2, P=5.6×10-8). Replication on an independent set of 8145 unrelated European ancestry participants showed consistent effect sizes in all 3 loci, although rs35991305 did not meet nominal significance. We constructed a polygenic risk score for aortic valve area, which in a separate cohort of 311 728 individuals without imaging demonstrated that smaller aortic valve area is predictive of increased risk for aortic valve disease (odds ratio, 1.14; P=2.3×10-6). After excluding subjects with a medical diagnosis of aortic valve stenosis (remaining n=308 683 individuals), phenome-wide association of >10 000 traits showed multiple links between the polygenic score for aortic valve disease and key health-related comorbidities involving the cardiovascular system and autoimmune disease. Genetic correlation analysis supports a shared genetic etiology with between aortic valve area and birth weight along with other cardiovascular conditions. CONCLUSIONS: These results illustrate the use of automated phenotyping of cardiac imaging data from the general population to investigate the genetic etiology of aortic valve disease, perform clinical prediction, and uncover new clinical and genetic correlates of cardiac anatomy.

Trends and Focus of Machine Learning Applications for Health Research.

Importance: The use of machine learning applications related to health is rapidly increasing and may have the potential to profoundly affect the field of health care. Objective: To analyze submissions to a popular machine learning for health venue to assess the current state of research, including areas of methodologic and clinical focus, limitations, and underexplored areas. Design, Setting, and Participants: In this data-driven qualitative analysis, 166 accepted manuscript submissions to the Third Annual Machine Learning for Health workshop at the 32nd Conference on Neural Information Processing Systems on December 8, 2018, were analyzed to understand research focus, progress, and trends. Experts reviewed each submission against a rubric to identify key data points, statistical modeling and analysis of submitting authors was performed, and research topics were quantitatively modeled. Finally, an iterative discussion of topics common in submissions and invited speakers at the workshop was held to identify key trends. Main Outcomes and Measures: Frequency and statistical measures of methods, topics, goals, and author attributes were derived from an expert review of submissions guided by a rubric. Results: Of the 166 accepted submissions, 58 (34.9%) had clinician involvement and 83 submissions (50.0%) that focused on clinical practice included clinical collaborators. A total of 97 data sets (58.4%) used in submissions were publicly available or required a standard registration process. Clinical practice was the most common application area (70 manuscripts [42.2%]), with brain and mental health (25 [15.1%]), oncology (21 [12.7%]), and cardiovascular (19 [11.4%]) being the most common specialties. Conclusions and Relevance: Trends in machine learning for health research indicate the importance of well-annotated, easily accessed data and the benefit from greater clinician involvement in the development of translational applications.

Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences.

Biomedical repositories such as the UK Biobank provide increasing access to prospectively collected cardiac imaging, however these data are unlabeled, which creates barriers to their use in supervised machine learning. We develop a weakly supervised deep learning model for classification of aortic valve malformations using up to 4,000 unlabeled cardiac MRI sequences. Instead of requiring highly curated training data, weak supervision relies on noisy heuristics defined by domain experts to programmatically generate large-scale, imperfect training labels. For aortic valve classification, models trained with imperfect labels substantially outperform a supervised model trained on hand-labeled MRIs. In an orthogonal validation experiment using health outcomes data, our model identifies individuals with a 1.8-fold increase in risk of a major adverse cardiac event. This work formalizes a deep learning baseline for aortic valve classification and outlines a general strategy for using weak supervision to train machine learning models using unlabeled medical images at scale.

Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities.

Traditional laboratory experiments, rehabilitation clinics, and wearable sensors offer biomechanists a wealth of data on healthy and pathological movement. To harness the power of these data and make research more efficient, modern machine learning techniques are starting to complement traditional statistical tools. This survey summarizes the current usage of machine learning methods in human movement biomechanics and highlights best practices that will enable critical evaluation of the literature. We carried out a PubMed/Medline database search for original research articles that used machine learning to study movement biomechanics in patients with musculoskeletal and neuromuscular diseases. Most studies that met our inclusion criteria focused on classifying pathological movement, predicting risk of developing a disease, estimating the effect of an intervention, or automatically recognizing activities to facilitate out-of-clinic patient monitoring. We found that research studies build and evaluate models inconsistently, which motivated our discussion of best practices. We provide recommendations for training and evaluating machine learning models and discuss the potential of several underutilized approaches, such as deep learning, to generate new knowledge about human movement. We believe that cross-training biomechanists in data science and a cultural shift toward sharing of data and tools are essential to maximize the impact of biomechanics research.

Potential corner case cautions regarding publicly available implementations of the National Cancer Institute's nonwear/wear classification algorithm for accelerometer data.

The National Cancer Institute's (NCI) wear time classification algorithm uses a rule based on the occurrence of physical activity data counts-a cumulative measure of movement, influenced by both magnitude and duration of acceleration-to differentiate between when a physical activity monitoring (PAM) device (ActiGraph accelerometer) is being worn by a participant (wear) from when it is not (nonwear). It was applied to PAM data generated from the 2003-2004 National Health and Nutrition Examination Survey (NHANES 2003-2004). We discuss two corner case conditions that can produce unexpected, and perhaps unintended results when the algorithm is applied. We show, using simulated data of two special cases, how this algorithm classifies a 24-hour period with only 72 total counts as 100% wear in one case, and classifies a 24-hour period with 96,000 counts as 0.1% wear in another. The prevalence of like scenarios in the NHANES 2003-2004 PAM dataset is presented with corresponding summary statistics for varying degrees of the algorithm's nonwear classification threshold (T). The number of participants with valid days, defined as 10 or more hours classified as wear time in a 24-hour day, increased while the mean counts-per-minute (CPM) decreased as the threshold for excluding non-wear was reduced from the allowed 4,000 counts in an hour. The number of participants with four or more valid days increased 2.29% (n = 113) and mean CPM dropped 2.45% (9.5 CPM) when adjusting the nonwear classification threshold to 50 counts an hour. Applying the most liberal criteria, only excluding hours as nonwear which contained 1 count or less, resulted in a 397 more participants (7.83% increase) and 26.5 fewer CPM (6.98% decrease) in NHANES 2003-2004 participants with four or more valid days. The algorithm should be used with caution due to the potential influence of these corner cases.

ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information.

In healthcare applications, temporal variables that encode movement, health status and longitudinal patient evolution are often accompanied by rich structured information such as demographics, diagnostics and medical exam data. However, current methods do not jointly optimize over structured covariates and time series in the feature extraction process. We present ShortFuse, a method that boosts the accuracy of deep learning models for time series by explicitly modeling temporal interactions and dependencies with structured covariates. ShortFuse introduces hybrid convolutional and LSTM cells that incorporate the covariates via weights that are shared across the temporal domain. ShortFuse outperforms competing models by 3% on two biomedical applications, forecasting osteoarthritis-related cartilage degeneration and predicting surgical outcomes for cerebral palsy patients, matching or exceeding the accuracy of models that use features engineered by domain experts.

Using Supervised Machine Learning to Classify Real Alerts and Artifact in Online Multisignal Vital Sign Monitoring Data.

OBJECTIVE: The use of machine-learning algorithms to classify alerts as real or artifacts in online noninvasive vital sign data streams to reduce alarm fatigue and missed true instability. DESIGN: Observational cohort study. SETTING: Twenty-four-bed trauma step-down unit. PATIENTS: Two thousand one hundred fifty-three patients. INTERVENTION: Noninvasive vital sign monitoring data (heart rate, respiratory rate, peripheral oximetry) recorded on all admissions at 1/20 Hz, and noninvasive blood pressure less frequently, and partitioned data into training/validation (294 admissions; 22,980 monitoring hours) and test sets (2,057 admissions; 156,177 monitoring hours). Alerts were vital sign deviations beyond stability thresholds. A four-member expert committee annotated a subset of alerts (576 in training/validation set, 397 in test set) as real or artifact selected by active learning, upon which we trained machine-learning algorithms. The best model was evaluated on test set alerts to enact online alert classification over time. MEASUREMENTS AND MAIN RESULTS: The Random Forest model discriminated between real and artifact as the alerts evolved online in the test set with area under the curve performance of 0.79 (95% CI, 0.67-0.93) for peripheral oximetry at the instant the vital sign first crossed threshold and increased to 0.87 (95% CI, 0.71-0.95) at 3 minutes into the alerting period. Blood pressure area under the curve started at 0.77 (95% CI, 0.64-0.95) and increased to 0.87 (95% CI, 0.71-0.98), whereas respiratory rate area under the curve started at 0.85 (95% CI, 0.77-0.95) and increased to 0.97 (95% CI, 0.94-1.00). Heart rate alerts were too few for model development. CONCLUSIONS: Machine-learning models can discern clinically relevant peripheral oximetry, blood pressure, and respiratory rate alerts from artifacts in an online monitoring dataset (area under the curve > 0.87).