PCPrithwish Chakraborty

Prithwish Chakraborty

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Prithwish Chakraborty has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Data-Driven Disease Progression Modeling

    by Kenney Ng, Mohamed Ghalwash, Prithwish Chakraborty, Daby M. Sow, Akira Koseki, Hiroki Yanagisawa, Michiharu Kudo


  • Open Access

    On Machine Learning-Based Short-Term Adjustment of Epidemiological Projections of COVID-19 in US

    by Sarah Kefayati, Fred Roberts, Sayali Pethe, Xuan Liu, Hu Huang, Vishrawas Gopalakrishnan, Piyush Madan, Jianying Hu, Prithwish Chakraborty, Raman Srinivasan, et al.

    Epidemiological models have provided valuable information for the outlook of COVID-19 pandemic and relative impact of different mitigation scenarios. However, more accurate forecasts are often needed at near term for planning and staffing. We present our early results from a systemic analysis of short-term adjustment of epidemiological modeling of COVID 19 pandemic in US during March-April 2020. Our analysis includes the importance of various types of features for short term adjustment of the predictions. In addition, we explore the potential of data augmentation to address the data limitation for an emerging pandemic. Following published literature, we employ data augmentation via clustering of regions and evaluate a number of clustering strategies to identify early patterns from the data. From our early analysis, we used CovidActNow as our underlying epidemiological model and found that the most impactful features for the one-day prediction horizon are population density, workers in commuting flow, number of deaths in the day prior to prediction date, and the autoregressive features of new COVID-19 cases from three previous dates of the prediction. Interestingly, we also found that counties clustered with New York County resulted in best preforming model with maximum of R 2 = 0.90 and minimum of R 2 =0.85 for state-based and COVID-based clustering strategy, respectively.


  • Open Access

    Explicit-Blurred Memory Network for Analyzing Patient Electronic Health Records

    by Prithwish Chakraborty, Fei Wang, Jianying Hu, Daby Sow

    In recent years, we have witnessed an increased interest in temporal modeling of patient records from large scale Electronic Health Records (EHR). While simpler RNN models have been used for such problems, memory networks, which in other domains were found to generalize well, are underutilized. Traditional memory networks involve diffused and non-linear operations where influence of past events on outputs are not readily quantifiable. We posit that this lack of interpretability makes such networks not applicable for EHR analysis. While networks with explicit memory have been proposed recently, the discontinuities imposed by the discrete operations make such networks harder to train and require more supervision. The problem is further exacerbated in the limited data setting of EHR studies. In this paper, we propose a novel memory architecture that is more interpretable than traditional memory networks while being easier to train than explicit memory banks. Inspired by well-known models of human cognition, we propose partitioning the external memory space into (a) a primary explicit memory block to store exact replicas of recent events to support interpretations, followed by (b) a secondary blurred memory block that accumulates salient aspects of past events dropped from the explicit block as higher level abstractions and allow training with less supervision by stabilize the gradients. We apply the model for 3 learning problems on ICU records from the MIMIC III database spanning millions of data points. Our model performs comparably to the state-of the art while also, crucially, enabling ready interpretation of the results.

  • Open Access

    ODVICE: An Ontology-Driven Visual Analytic Tool for Interactive Cohort Extraction

    by Mohamed Ghalwash, Zijun Yao, Prithwish Chakrabotry, James Codella, Daby Sow

    Increased availability of electronic health records (EHR) has enabled researchers to study various medical questions. Cohort selection for the hypothesis under investigation is one of the main consideration for EHR analysis. For uncommon diseases, cohorts extracted from EHRs contain very limited number of records - hampering the robustness of any analysis. Data augmentation methods have been successfully applied in other domains to address this issue mainly using simulated records. In this paper, we present ODVICE, a data augmentation framework that leverages the medical concept ontology to systematically augment records using a novel ontologically guided Monte-Carlo graph spanning algorithm. The tool allows end users to specify a small set of interactive controls to control the augmentation process. We analyze the importance of ODVICE by conducting studies on MIMIC-III dataset for two learning tasks. Our results demonstrate the predictive performance of ODVICE augmented cohorts, showing ~30% improvement in area under the curve (AUC) over the non-augmented dataset and other data augmentation strategies.

  • Open Access

    A Novel Data-Driven Framework for Risk Characterization and Prediction from Electronic Medical Records: A Case Study of Renal Failure

    by Prithwish Chakraborty, Vishrawas Gopalakrishnan, Sharon M. H. Alford, Faisal Farooq

    Electronic medical records (EMR) contain longitudinal information about patients that can be used to analyze outcomes. Typically, studies on EMR data have worked with established variables that have already been acknowledged to be associated with certain outcomes. However, EMR data may also contain hitherto unrecognized factors for risk association and prediction of outcomes for a disease. In this paper, we present a scalable data-driven framework to analyze EMR data corpus in a disease agnostic way that systematically uncovers important factors influencing outcomes in patients, as supported by data and without expert guidance. We validate the importance of such factors by using the framework to predict for the relevant outcomes. Specifically, we analyze EMR data covering approximately 47 million unique patients to characterize renal failure (RF) among type 2 diabetic (T2DM) patients. We propose a specialized L1 regularized Cox Proportional Hazards (CoxPH) survival model to identify the important factors from those available from patient encounter history. To validate the identified factors, we use a specialized generalized linear model (GLM) to predict the probability of renal failure for individual patients within a specified time window. Our experiments indicate that the factors identified via our data-driven method overlap with the patient characteristics recognized by experts. Our approach allows for scalable, repeatable and efficient utilization of data available in EMRs, confirms prior medical knowledge and can generate new hypothesis without expert supervision.