We introduce an innovative approach that incorporates a Distributionally Robust Learning (DRL) approach into Cox regression to enhance the robustness and accuracy of survival predictions. By formulating a DRL framework with a Wasserstein distance-based ambiguity set, we develop a variant Cox model that is less sensitive to assumptions about the underlying data distribution and more resilient to model misspecification and data perturbations. By leveraging Wasserstein duality, we reformulate the original min-max DRL problem into a tractable regularized empirical risk minimization problem, which can be computed by exponential conic programming. We provide guarantees on the finite sample behavior of our DRL-Cox model. Moreover, through extensive simulations and real world case studies, we demonstrate that our regression model achieves superior performance in terms of prediction accuracy and robustness compared with traditional methods.

A new AI program can accurately and efficiently detect cognitive impairment from voice recordings. Scientists develop an artificial intelligence program that detects cognitive impairment accurately and efficiently from voice recordings. A lot of time--and money--is required to diagnose Alzheimer's disease. After running lengthy in-person neuropsychological exams, clinicians have to transcribe, review, and analyze every response in detail. However, researchers at Boston University (BU) have developed a new tool that could automate the process and eventually allow it to move online.

A new artificial intelligence language-processing tool could potentially help detect cognitive impairment and mental degenerative diseases like Alzheimer's, researchers at Boston University say. Their findings, which were published in The Journal of the Alzheimer's Association, suggest that a machine-learning computational model could identify cognitive decline through audio recordings of neuropsychological tests. "It can form the basis of an online tool that could reach everyone and could increase the number of people who get screened early," said Ioannis Paschalidis, a professor of engineering and one of the researchers at Boston University, in a news release. The computational model, which does not require in-person assessments, could ultimately help clinicians triage the urgency of patients' symptoms more efficiently, allowing them to allocate resources without replacing follow-up processes for diagnosis, she said. Using automated speech recognition software, the program transcribes interviews and, by encoding them into numbers, detects patterns that assess the likelihood and severity of a patient's cognitive impairment.

Antimicrobial resistance (AMR) is a risk for patients and a burden for the healthcare system. However, AMR assays typically take several days. This study develops predictive models for AMR based on easily available clinical and microbiological predictors, including patient demographics, hospital stay data, diagnoses, clinical features, and microbiological/antimicrobial characteristics and compares those models to a naive antibiogram based model using only microbiological/antimicrobial characteristics. The ability to predict the resistance accurately prior to culturing could inform clinical decision-making and shorten time to action. The machine learning algorithms employed here show improved classification performance (area under the receiver operating characteristic curve 0.88-0.89) versus the naive model (area under the receiver operating characteristic curve 0.86) for 6 organisms and 10 antibiotics using the Philips eICU Research Institute (eRI) database. This method can help guide antimicrobial treatment, with the objective of improving patient outcomes and reducing the usage of unnecessary or ineffective antibiotics.

We propose a Distributionally Robust Optimization (DRO) formulation with a Wasserstein-based uncertainty set for selecting grouped variables under perturbations on the data for both linear regression and classification problems. The resulting model offers robustness explanations for Grouped Least Absolute Shrinkage and Selection Operator (GLASSO) algorithms and highlights the connection between robustness and regularization. We prove probabilistic bounds on the out-of-sample loss and the estimation bias, and establish the grouping effect of our estimator, showing that coefficients in the same group converge to the same value as the sample correlation between covariates approaches 1. Based on this result, we propose to use the spectral clustering algorithm with the Gaussian similarity function to perform grouping on the predictors, which makes our approach applicable without knowing the grouping structure a priori. We compare our approach to an array of alternatives and provide extensive numerical results on both synthetic data and a real large dataset of surgery-related medical records, showing that our formulation produces an interpretable and parsimonious model that encourages sparsity at a group level and is able to achieve better prediction and estimation performance in the presence of outliers.

While debate drags on about legislation, regulations, and other measures to improve the U.S. health care system, a new wave of analytics and technology could help cut costly and unnecessary hospitalizations while improving outcomes for patients, according to an article in the Harvard Business Review. In an ongoing effort with Boston-area hospitals, including the Boston Medical Center and Brigham and Women's Hospital, Dr. Yannis Paschalidis and his colleagues at Boston University's Center for Information and Systems Engineering found that they could use machine-learning algorithms to predict hospitalizations due to heart disease or diabetes approximately one year in advance with an accuracy rate of up to 82%. The team is also working with the Department of Surgery at the Boston Medical Center and can predict readmissions within 30 days of general surgery. The hospitals provide Paschalidis and his colleagues with patients' anonymous electronic health records, which include information on demographics, diagnoses, admissions, procedures, vital signs at doctor visits, prescribed medications, and laboratory results. The investigators then use their algorithms to predict who might have to be hospitalized.

We augment linear Support Vector Machine (SVM) classifiers by adding three important features: (i) we introduce a regularization constraint to induce a sparse classifier; (ii) we devise a method that partitions the positive class into clusters and selects a sparse SVM classifier for each cluster; and (iii) we develop a method to optimize the values of controllable variables in order to reduce the number of data points which are predicted to have an undesirable outcome, which, in our setting, coincides with being in the positive class. The latter feature leads to personalized prescriptions/recommendations. We apply our methods to the problem of predicting and preventing hospital readmissions within 30-days from discharge for patients that underwent a general surgical procedure. To that end, we leverage a large dataset containing over 2.28 million patients who had surgeries in the period 2011--2014 in the U.S. The dataset has been collected as part of the American College of Surgeons National Surgical Quality Improvement Program (NSQIP).