Enzyme Promiscuity Prediction Using Hierarchy-Informed Multi-Label Classification.

MOTIVATION: As experimental efforts are costly and time consuming, computational characterization of enzyme capabilities is an attractive alternative. We present and evaluate several machine-learning models to predict which of 983 distinct enzymes, as defined via the Enzyme Commission (EC) numbers, are likely to interact with a given query molecule. Our data consists of enzyme-substrate interactions from the BRENDA database. Some interactions are attributed to natural selection and involve the enzyme's natural substrates. The majority of the interactions however involve non-natural substrates, thus reflecting promiscuous enzymatic activities. RESULTS: We frame this "enzyme promiscuity prediction" problem as a multi-label classification task. We maximally utilize inhibitor and unlabelled data to train prediction models that can take advantage of known hierarchical relationships between enzyme classes. We report that a hierarchical multi-label neural network, EPP-HMCNF, is the best model for solving this problem, outperforming k-nearest neighbours similarity-based and other machine learning models. We show that inhibitor information during training consistently improves predictive power, particularly for EPP-HMCNF. We also show that all promiscuity prediction models perform worse under a realistic data split when compared to a random data split, and when evaluating performance on non-natural substrates compared to natural substrates. AVAILABILITY AND IMPLEMENTATION: We provide Python code for EPP-HMCNF and other models in a repository termed EPP (Enzyme Promiscuity Prediction) at https://github.com/hassounlab/EPP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning.

Aortic stenosis (AS) is a degenerative valve condition that causes substantial morbidity and mortality. This condition is under-diagnosed and under-treated. In clinical practice, AS is diagnosed with expert review of transthoracic echocardiography, which produces dozens of ultrasound images of the heart. Only some of these views show the aortic valve. To automate screening for AS, deep networks must learn to mimic a human expert's ability to identify views of the aortic valve then aggregate across these relevant images to produce a study-level diagnosis. We find previous approaches to AS detection yield insufficient accuracy due to relying on inflexible averages across images. We further find that off-the-shelf attention-based multiple instance learning (MIL) performs poorly. We contribute a new end-to-end MIL approach with two key methodological innovations. First, a supervised attention technique guides the learned attention mechanism to favor relevant views. Second, a novel self-supervised pretraining strategy applies contrastive learning on the representation of the whole study instead of individual images as commonly done in prior literature. Experiments on an open-access dataset and a temporally-external heldout set show that our approach yields higher accuracy while reducing model size.

Automated Detection of Aortic Stenosis Using Machine Learning.

BACKGROUND: Aortic stenosis (AS) is a degenerative valve condition that is underdiagnosed and undertreated. Detection of AS using limited two-dimensional echocardiography could enable screening and improve appropriate referral and treatment of this condition. The aim of this study was to develop methods for automated detection of AS from limited imaging data sets. METHODS: Convolutional neural networks were trained, validated, and tested using limited two-dimensional transthoracic echocardiographic data sets. Networks were developed to accomplish two sequential tasks: (1) view identification and (2) study-level grade of AS. Balanced accuracy and area under the receiver operator curve (AUROC) were the performance metrics used. RESULTS: Annotated images from 577 patients were included. Neural networks were trained on data from 338 patients (average n = 10,253 labeled images), validated on 119 patients (average n = 3,505 labeled images), and performance was assessed on a test set of 120 patients (average n = 3,511 labeled images). Fully automated screening for AS was achieved with an AUROC of 0.96. Networks can distinguish no significant (no, mild, mild to moderate) AS from significant (moderate or severe) AS with an AUROC of 0.86 and between early (mild or mild to moderate AS) and significant (moderate or severe) AS with an AUROC of 0.75. External validation of these networks in a cohort of 8,502 outpatient transthoracic echocardiograms showed that screening for AS can be achieved using parasternal long-axis imaging only with an AUROC of 0.91. CONCLUSION: Fully automated detection of AS using limited two-dimensional data sets is achievable using modern neural networks. These methods lay the groundwork for a novel method for screening for AS.

Predicting In-Hospital Mortality After Acute Myeloid Leukemia Therapy: Through Supervised Machine Learning Algorithms.

PURPOSE: Despite careful patient selection, induction chemotherapy for acute myeloid leukemia (AML) is associated with a considerable risk for treatment-related mortality (5%-20%). We evaluated machine learning (ML) algorithms trained using factors available at the time of admission for AML therapy to predict death during the hospitalization. METHODS: We included AML discharges with age > 17 years who received inpatient chemotherapy from State Inpatient Database from Arizona, Florida, New York, Maryland, Washington, and New Jersey for years 2008-2014. The primary objective was to predict inpatient mortality in patients undergoing chemotherapy using covariates present before initiation of chemotherapy. ML algorithms logistic regression (LR), decision tree, and random forest were compared. RESULTS: 29,613 hospitalizations for patients with AML were included in the analysis each with 4,177 features. The median age was 58.9 (18-101) years, 13,689 (53.7%) were male, and 20,203 (69%) were White. The mean time from admission to chemotherapy was 3 days (95% CI, 2.9 to 3.1), and 2,682 (9.1%) died during the hospitalization. Both LR and random forest models achieved an area under the curve (AUC) score of 0.78, whereas decision tree achieved an AUC of 0.70. The baseline LR model with age yielded an AUC of 0.62. To clinically balance and minimize false positives, we selected a decision threshold of 0.7 and at this threshold, 51 of our test set of 5,923 could have potentially averted treatment-related mortality. CONCLUSION: Using readily accessible variables, inpatient mortality of patients on track for chemotherapy to treat AML can be predicted through ML algorithms. The model also predicted inpatient mortality when tested on different data representations and paves the way for future research.

Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation.

We aimed to develop and validate classification models able to identify individuals at high risk for transition from a diagnosis of depressive disorder to one of bipolar disorder. This retrospective health records cohort study applied outpatient clinical data from psychiatry and nonpsychiatry practice networks affiliated with two large academic medical centers between March 2008 and December 2017. Participants included 67,807 individuals with a diagnosis of major depressive disorder or depressive disorder not otherwise specified and no prior diagnosis of bipolar disorder, who received at least one of the nine antidepressant medications. The main outcome was at least one diagnostic code reflective of a bipolar disorder diagnosis within 3 months of index antidepressant prescription. Logistic regression and random forests using diagnostic and procedure codes as well as sociodemographic features were used to predict this outcome, with discrimination and calibration assessed in a held-out test set and then a second academic medical center. Among 67,807 individuals who received at least one antidepressant medication, 925 (1.36%) subsequently received a diagnosis of bipolar disorder within 3 months. Models incorporating coded diagnoses and procedures yielded a mean area under the receiver operating characteristic curve of 0.76 (ranging from 0.73 to 0.80). Standard supervised machine learning methods enabled development of discriminative and transferable models to predict transition to bipolar disorder. With further validation, these scores may enable physicians to more precisely calibrate follow-up intensity for high-risk patients after antidepressant initiation.

The role of machine learning in clinical research: transforming the future of evidence generation.

BACKGROUND: Interest in the application of machine learning (ML) to the design, conduct, and analysis of clinical trials has grown, but the evidence base for such applications has not been surveyed. This manuscript reviews the proceedings of a multi-stakeholder conference to discuss the current and future state of ML for clinical research. Key areas of clinical trial methodology in which ML holds particular promise and priority areas for further investigation are presented alongside a narrative review of evidence supporting the use of ML across the clinical trial spectrum. RESULTS: Conference attendees included stakeholders, such as biomedical and ML researchers, representatives from the US Food and Drug Administration (FDA), artificial intelligence technology and data analytics companies, non-profit organizations, patient advocacy groups, and pharmaceutical companies. ML contributions to clinical research were highlighted in the pre-trial phase, cohort selection and participant management, and data collection and analysis. A particular focus was paid to the operational and philosophical barriers to ML in clinical research. Peer-reviewed evidence was noted to be lacking in several areas. CONCLUSIONS: ML holds great promise for improving the efficiency and quality of clinical research, but substantial barriers remain, the surmounting of which will require addressing significant gaps in evidence.

A Framework for Sensorimotor Cross-Perception and Cross-Behavior Knowledge Transfer for Object Categorization.

From an early age, humans learn to develop an intuition for the physical nature of the objects around them by using exploratory behaviors. Such exploration provides observations of how objects feel, sound, look, and move as a result of actions applied on them. Previous works in robotics have shown that robots can also use such behaviors (e.g., lifting, pressing, shaking) to infer object properties that camera input alone cannot detect. Such learned representations are specific to each individual robot and cannot currently be transferred directly to another robot with different sensors and actions. Moreover, sensor failure can cause a robot to lose a specific sensory modality which may prevent it from using perceptual models that require it as input. To address these limitations, we propose a framework for knowledge transfer across behaviors and sensory modalities such that: (1) knowledge can be transferred from one or more robots to another, and, (2) knowledge can be transferred from one or more sensory modalities to another. We propose two different models for transfer based on variational auto-encoders and encoder-decoder networks. The main hypothesis behind our approach is that if two or more robots share multi-sensory object observations of a shared set of objects, then those observations can be used to establish mappings between multiple features spaces, each corresponding to a combination of an exploratory behavior and a sensory modality. We evaluate our approach on a category recognition task using a dataset in which a robot used 9 behaviors, coupled with 4 sensory modalities, performed multiple times on 100 objects. The results indicate that sensorimotor knowledge about objects can be transferred both across behaviors and across sensory modalities, such that a new robot (or the same robot, but with a different set of sensors) can bootstrap its category recognition models without having to exhaustively explore the full set of objects.

Assessment of a Prediction Model for Antidepressant Treatment Stability Using Supervised Topic Models.

Importance: In the absence of readily assessed and clinically validated predictors of treatment response, pharmacologic management of major depressive disorder often relies on trial and error. Objective: To assess a model using electronic health records to identify predictors of treatment response in patients with major depressive disorder. Design, Setting, and Participants: This retrospective cohort study included data from 81 630 adults with a coded diagnosis of major depressive disorder from 2 academic medical centers in Boston, Massachusetts, including outpatient primary and specialty care clinics from December 1, 1997, to December 31, 2017. Data were analyzed from January 1, 2018, to March 15, 2020. Exposures: Treatment with at least 1 of 11 standard antidepressants. Main Outcomes and Measures: Stable treatment response, intended as a proxy for treatment effectiveness, defined as continued prescription of an antidepressant for 90 days. Supervised topic models were used to extract 10 interpretable covariates from coded clinical data for stability prediction. With use of data from 1 hospital system (site A), generalized linear models and ensembles of decision trees were trained to predict stability outcomes from topic features that summarize patient history. Held-out patients from site A and individuals from a second hospital system (site B) were evaluated. Results: Among the 81 630 adults (56 340 women [69%]; mean [SD] age, 48.46 [14.75] years; range, 18.0-80.0 years), 55 303 reached a stable response to their treatment regimen during follow-up. For held-out patients from site A, the mean area under the receiver operating characteristic curve (AUC) for discrimination of the general stability outcome was 0.627 (95% CI, 0.615-0.639) for the supervised topic model with 10 covariates. In evaluation of site B, the AUC was 0.619 (95% CI, 0.610-0.627). Building models to predict stability specific to a particular drug did not improve prediction of general stability even when using a harder-to-interpret ensemble classifier and 9256 coded covariates (specific AUC, 0.647; 95% CI, 0.635-0.658; general AUC, 0.661; 95% CI, 0.648-0.672). Topics coherently captured clinical concepts associated with treatment response. Conclusions and Relevance: The findings suggest that coded clinical data available in electronic health records may facilitate prediction of general treatment response but not response to specific medications. Although greater discrimination is likely required for clinical application, the results provide a transparent baseline for such studies.

Predicting intervention onset in the ICU with switching state space models.

The impact of many intensive care unit interventions has not been fully quantified, especially in heterogeneous patient populations. We train unsupervised switching state autoregressive models on vital signs from the public MIMIC-III database to capture patient movement between physiological states. We compare our learned states to static demographics and raw vital signs in the prediction of five ICU treatments: ventilation, vasopressor administra tion, and three transfusions. We show that our learned states, when combined with demographics and raw vital signs, improve prediction for most interventions even 4 or 8 hours ahead of onset. Our results are competitive with existing work while using a substantially larger and more diverse cohort of 36,050 patients. While custom classifiers can only target a specific clinical event, our model learns physiological states which can help with many interventions. Our robust patient state representations provide a path towards evidence-driven administration of clinical interventions.

Recurrent abdominal pain and childhood depression: clinical observations of 23 children and their families.

Children with recurrent abdominal pain without demonstrable organic etiology are studied with their mothers during pediatric hospitalization. Major childhood depressive illness is found which is not masked by the somatic complaint. The mother-child relationship is shown to reflect mutual themes of depression and loss within families where experience with illness and death contributes to a hypochondriacal response to psychic pain.