skip to main content

Title: Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR
Electronic Health Record modeling is crucial for digital medicine. However, existing models ignore higher-order interactions among medical codes and their causal relations towards downstream clinical predictions. To address such limitations, we propose a novel framework CACHE, to provide effective and insightful clinical predictions based on hypergraph representation learning and counterfactual and factual reasoning techniques. Experiments on two real EHR datasets show the superior performance of CACHE. Case studies with a domain expert illustrate a preferred capability of CACHE in generating clinically meaningful interpretations towards the correct predictions.
Authors:
; ; ; ; ;
Award ID(s):
1838200 2145411
Publication Date:
NSF-PAR ID:
10391649
Journal Name:
Proceedings of the 2nd Machine Learning for Health symposium
Volume:
193
Page Range or eLocation-ID:
259-278
Sponsoring Org:
National Science Foundation
More Like this
  1. Viruses such as the novel coronavirus, SARS-CoV-2, that is wreaking havoc on the world, depend on interactions of its own proteins with those of the human host cells. Relatively small changes in sequence such as between SARS-CoV and SARS-CoV-2 can dramatically change clinical phenotypes of the virus, including transmission rates and severity of the disease. On the other hand, highly dissimilar virus families such as Coronaviridae, Ebola, and HIV have overlap in functions. In this work we aim to analyze the role of protein sequence in the binding of SARS-CoV-2 virus proteins towards human proteins and compare it to that of the above other viruses. We build supervised machine learning models, using Generalized Additive Models to predict interactions based on sequence features and find that our models perform well with an AUC-PR of 0.65 in a class-skew of 1:10. Analysis of the novel predictions using an independent dataset showed statistically significant enrichment. We further map the importance of specific amino-acid sequence features in predicting binding and summarize what combinations of sequences from the virus and the host is correlated with an interaction. By analyzing the sequence-based embeddings of the interactomes from different viruses and clustering them together we find somemore »functionally similar proteins from different viruses. For example, vif protein from HIV-1, vp24 from Ebola and orf3b from SARS-CoV all function as interferon antagonists. Furthermore, we can differentiate the functions of similar viruses, for example orf3a’s interactions are more diverged than orf7b interactions when comparing SARS-CoV and SARS-CoV-2.« less
  2. A schizophrenia relapse has severe consequences for a patient’s health, work, and sometimes even life safety. If an oncoming relapse can be predicted on time, for example by detecting early behavioral changes in patients, then interventions could be provided to prevent the relapse. In this work, we investigated a machine learning based schizophrenia relapse prediction model using mobile sensing data to characterize behavioral features. A patient-independent model providing sequential predictions, closely representing the clinical deployment scenario for relapse prediction, was evaluated. The model uses the mobile sensing data from the recent four weeks to predict an oncoming relapse in the next week. We used the behavioral rhythm features extracted from daily templates of mobile sensing data, self-reported symptoms collected via EMA (Ecological Momentary Assessment), and demographics to compare different classifiers for the relapse prediction. Naive Bayes based model gave the best results with an F2 score of 0.083 when evaluated in a dataset consisting of 63 schizophrenia patients, each monitored for up to a year. The obtained F2 score, though low, is better than the baseline performance of random classification (F2 score of 0.02 ± 0.024). Thus, mobile sensing has predictive value for detecting an oncoming relapse and needs furthermore »investigation to improve the current performance. Towards that end, further feature engineering and model personalization based on the behavioral idiosyncrasies of a patient could be helpful.« less
  3. Summary In many clinical settings, a patient outcome takes the form of a scalar time series with a recovery curve shape, which is characterized by a sharp drop due to a disruptive event (e.g., surgery) and subsequent monotonic smooth rise towards an asymptotic level not exceeding the pre-event value. We propose a Bayesian model that predicts recovery curves based on information available before the disruptive event. A recovery curve of interest is the quantified sexual function of prostate cancer patients after prostatectomy surgery. We illustrate the utility of our model as a pre-treatment medical decision aid, producing personalized predictions that are both interpretable and accurate. We uncover covariate relationships that agree with and supplement that in existing medical literature.
  4. We introduce a statistical procedure that integrates survival data from multiple biomedical studies, to improve the accuracy of predictions of survival or other events, based on individual clinical and genomic profiles, compared to models developed leveraging only a single study or meta-analytic methods. The method accounts for potential differences in the relation between predictors and outcomes across studies, due to distinct patient populations, treatments and technologies to measure outcomes and biomarkers. These differences are modeled explicitly with study-specific parameters. We use hierarchical regularization to shrink the study-specific parameters towards each other and to borrow information across studies. Shrinkage of the study-specific parameters is controlled by a similarity matrix, which summarizes differences and similarities of the relations between covariates and outcomes across studies. We illustrate the method in a simulation study and using a collection of gene-expression datasets in ovarian cancer. We show that the proposed model increases the accuracy of survival prediction compared to alternative meta-analytic methods.
  5. Abstract

    We introduce a statistical procedure that integrates datasets from multiple biomedical studies to predict patients' survival, based on individual clinical and genomic profiles. The proposed procedure accounts for potential differences in the relation between predictors and outcomes across studies, due to distinct patient populations, treatments and technologies to measure outcomes and biomarkers. These differences are modeled explicitly with study‐specific parameters. We use hierarchical regularization to shrink the study‐specific parameters towards each other and to borrow information across studies. The estimation of the study‐specific parameters utilizes a similarity matrix, which summarizes differences and similarities of the relations between covariates and outcomes across studies. We illustrate the method in a simulation study and using a collection of gene expression datasets in ovarian cancer. We show that the proposed model increases the accuracy of survival predictions compared to alternative meta‐analytic methods.