Kishlay Jha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kishlay Jha has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Bijaya Adhikari
University of Iowa, Iowa City, IA, USA
2 shared publications - Ratri Mukherjee
University of Iowa, Iowa City, USA
2 shared publications - Aidong Zhang
Department of Computer Science, University of Virginia, Charlottesville, USA
1 shared publication - Akash Choudhuri
Department of Computer Science, University of Iowa
1 shared publication - Amir Hassan Shariatmadari
Department of Computer Science, University of Virginia, Charlottesville, USA
1 shared publication - Hieu Vu
University of Iowa
1 shared publication
Latest Publications
- Open Access
- 1 June 2026
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 10 (3) , 1-21
Semantic Knowledge Guided Diffusion Model for Biomedical Ontology Definition Generation
Biomedical ontologies such as the Unified Medical Language System (UMLS) play a crucial role in supporting practical applications such as predicting gene–disease associations, drug–drug interactions, and biomedical question answering. However, automatically maintaining and updating them remains a critical barrier as authoring high-quality textual definitions is both time-consuming and labor-intensive. As a result, UMLS ontology updates significantly lag behind the pace of scientific discovery, leaving many concepts without definitions or with outdated descriptions. Despite the pressing need for automated generation of UMLS concept definitions, this problem has largely remained unaddressed in prior research. To address this, we propose a novel diffusion-based approach for generating high-quality definitions of biomedical concepts. A key innovation in our approach is the adaptive semantic modulation mechanism, which dynamically adjusts the influence of semantic priors throughout the denoising process, enabling the model to flexibly balance local lexical fidelity with global semantic alignment. Extensive experiments on the largest available biomedical ontology dataset demonstrate that the proposed approach both significantly and consistently outperforms strong baseline algorithms across multiple evaluation metrics.
- 1 June 2026
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 10 (3) , 1-21
Open AccessSemantic Knowledge Guided Diffusion Model for Biomedical Ontology Definition Generation
Biomedical ontologies such as the Unified Medical Language System (UMLS) play a crucial role in supporting practical applications such as predicting gene–disease associations, drug–drug interactions, and biomedical question answering. However, automatically maintaining and updating them remains a critical barrier as authoring high-quality textual definitions is both time-consuming and labor-intensive. As a result, UMLS ontology updates significantly lag behind the pace of scientific discovery, leaving many concepts without definitions or with outdated descriptions. Despite the pressing need for automated generation of UMLS concept definitions, this problem has largely remained unaddressed in prior research. To address this, we propose a novel diffusion-based approach for generating high-quality definitions of biomedical concepts. A key innovation in our approach is the adaptive semantic modulation mechanism, which dynamically adjusts the influence of semantic priors throughout the denoising process, enabling the model to flexibly balance local lexical fidelity with global semantic alignment. Extensive experiments on the largest available biomedical ontology dataset demonstrate that the proposed approach both significantly and consistently outperforms strong baseline algorithms across multiple evaluation metrics.
- Open Access
- 17 May 2026
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 68 (1) , 157
Automated biomedical hypothesis generation with time-aware hypergraph contrastive learning
Research in scientific domains now generates more than a million articles annually, overwhelming researchers and hindering discovery. This surge has sparked interest in biomedical hypothesis generation (HG), which aims to uncover implicit patterns among biomedical concepts. Most existing methods focus on pairwise link prediction, overlooking the complex, multi-concept relationships underlying many breakthroughs. We introduce HyHG , a temporal Hy pergraph contrastive learning framework for biomedical H ypothesis G eneration, which redefines hypotheses as hyperedges—sets of co-mentioned concepts in an article. By representing articles as hyperedges and organizing them into a temporal hypergraph, HyHG captures the evolution of scientific ideas over time. A transformer-based architecture learns from historical hyperedge sequences to predict future hyperedges—sets of concepts likely to co-occur in the future literature. To distinguish genuine hypotheses from misleading ones, HyHG employs a time-anchored contrastive loss and hard negative sampling based on minimal edits to real hyperedges. We demonstrate that HyHG achieves state-of-the-art performance on three biomedical datasets. Our code and data are available at: https://github.com/amir-hassan25/Temporal-Hypergraph-Contrastive-Learning.
- 17 May 2026
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 68 (1) , 157
Open AccessAutomated biomedical hypothesis generation with time-aware hypergraph contrastive learning
Research in scientific domains now generates more than a million articles annually, overwhelming researchers and hindering discovery. This surge has sparked interest in biomedical hypothesis generation (HG), which aims to uncover implicit patterns among biomedical concepts. Most existing methods focus on pairwise link prediction, overlooking the complex, multi-concept relationships underlying many breakthroughs. We introduce HyHG , a temporal Hy pergraph contrastive learning framework for biomedical H ypothesis G eneration, which redefines hypotheses as hyperedges—sets of co-mentioned concepts in an article. By representing articles as hyperedges and organizing them into a temporal hypergraph, HyHG captures the evolution of scientific ideas over time. A transformer-based architecture learns from historical hyperedge sequences to predict future hyperedges—sets of concepts likely to co-occur in the future literature. To distinguish genuine hypotheses from misleading ones, HyHG employs a time-anchored contrastive loss and hard negative sampling based on minimal edits to real hyperedges. We demonstrate that HyHG achieves state-of-the-art performance on three biomedical datasets. Our code and data are available at: https://github.com/amir-hassan25/Temporal-Hypergraph-Contrastive-Learning.
- 15 June 2025
- Published by Springer Nature
- Vol. 15870, 319-330
Semantic Knowledge Augmented Hypergraph Contrastive Representation Learning for Zero-Shot Biomedical Text Classification
Zero-shot biomedical text classification is a fundamental problem in text mining that assigns scientific articles with labels that are unseen during the training time but available during inference. This learning paradigm has practical implications for domains such as biomedicine where new labels or concepts (i.e., novel diseases, genes, drugs) emerge every now and then. While the existing approaches have made significant advances, they fail to effectively leverage the complex semantic relationships between biomedical entities and thus yield unsatisfactory results. To address this issue, we propose a new approach that leverages a hypergraph structure to capture the high-order semantic relationships between biomedical entities. To further enhance the expressive power of hypergraphs, we propose a novel augmentation strategy that leverages semantic knowledge present in the biomedical domain to generate augmented hypergraph views. Taken together, the proposed approach generates robust feature representation of biomedical entities needed for achieving better generalization performance in unseen labels. Extensive experiments on the largest biomedical corpus validate the effectiveness of proposed approach.
- 15 June 2025
- Published by Springer Nature
- Vol. 15870, 319-330
Semantic Knowledge Augmented Hypergraph Contrastive Representation Learning for Zero-Shot Biomedical Text Classification
Zero-shot biomedical text classification is a fundamental problem in text mining that assigns scientific articles with labels that are unseen during the training time but available during inference. This learning paradigm has practical implications for domains such as biomedicine where new labels or concepts (i.e., novel diseases, genes, drugs) emerge every now and then. While the existing approaches have made significant advances, they fail to effectively leverage the complex semantic relationships between biomedical entities and thus yield unsatisfactory results. To address this issue, we propose a new approach that leverages a hypergraph structure to capture the high-order semantic relationships between biomedical entities. To further enhance the expressive power of hypergraphs, we propose a novel augmentation strategy that leverages semantic knowledge present in the biomedical domain to generate augmented hypergraph views. Taken together, the proposed approach generates robust feature representation of biomedical entities needed for achieving better generalization performance in unseen labels. Extensive experiments on the largest biomedical corpus validate the effectiveness of proposed approach.
- Open Access
Domain Knowledge Augmented Contrastive Learning on Dynamic Hypergraphs for Improved Health Risk Prediction
Accurate health risk prediction is crucial for making informed clinical decisions and assessing the appropriate allocation of medical resources. While recent deep learning based approaches have shown great promise in risk prediction, they primarily focus on modeling the sequential information in Electronic Health Records (EHRs) and fail to leverage the rich mobility interactions among health entities. As a result, the existing approaches yield unsatisfactory performance in downstream risk prediction tasks, especially tasks such as Clostridioides difficile Infection (CDI) incidence prediction that are primarily spread through mobility interactions. To address this issue, we propose a new approach that leverages Hypergraphs to explicitly model mobility interactions to improve predictive performance in health risk prediction tasks. Unlike regular graphs that are limited to modeling pairwise relationships, hypergraphs can effectively characterize the complex high-order semantic relationships between health entities. Moreover, we introduce a new contrastive learning strategy that exploits the domain knowledge to generate semantically meaningful positive (homologous) and negative (heterologous) pairs needed for contrastive learning. This unique contrastive pair augmentation strategy boosts the power of contrastive learning by generating feature representations that are both robust and well-aligned with the domain knowledge. Experiments on two real-world datasets demonstrate the advantage of our approach in both short-term and long-term risk prediction tasks, such as Clostridioides difficile infection incidence prediction and MICU transfer prediction. Our framework obtains gains in performance up to 29.49 % for PHOP, 30.64 % for MIMIC-IV for MICU transfer prediction, 13.17 % for PHOP, and 4.45 % for MIMIC-IV for CDI Incidence Prediction.
Open AccessDomain Knowledge Augmented Contrastive Learning on Dynamic Hypergraphs for Improved Health Risk Prediction
Accurate health risk prediction is crucial for making informed clinical decisions and assessing the appropriate allocation of medical resources. While recent deep learning based approaches have shown great promise in risk prediction, they primarily focus on modeling the sequential information in Electronic Health Records (EHRs) and fail to leverage the rich mobility interactions among health entities. As a result, the existing approaches yield unsatisfactory performance in downstream risk prediction tasks, especially tasks such as Clostridioides difficile Infection (CDI) incidence prediction that are primarily spread through mobility interactions. To address this issue, we propose a new approach that leverages Hypergraphs to explicitly model mobility interactions to improve predictive performance in health risk prediction tasks. Unlike regular graphs that are limited to modeling pairwise relationships, hypergraphs can effectively characterize the complex high-order semantic relationships between health entities. Moreover, we introduce a new contrastive learning strategy that exploits the domain knowledge to generate semantically meaningful positive (homologous) and negative (heterologous) pairs needed for contrastive learning. This unique contrastive pair augmentation strategy boosts the power of contrastive learning by generating feature representations that are both robust and well-aligned with the domain knowledge. Experiments on two real-world datasets demonstrate the advantage of our approach in both short-term and long-term risk prediction tasks, such as Clostridioides difficile infection incidence prediction and MICU transfer prediction. Our framework obtains gains in performance up to 29.49 % for PHOP, 30.64 % for MIMIC-IV for MICU transfer prediction, 13.17 % for PHOP, and 4.45 % for MIMIC-IV for CDI Incidence Prediction.
- Open Access
Bridging The Evolving Semantics: A Data Driven Approach to Knowledge Discovery In Biomedicine
Recent progress in biological, medical and health-care technologies, and innovations in wearable sensors provide us with unprecedented opportunities to accumulate massive data to understand disease prognosis and develop personalized treatments and interventions. These massive data supplemented with rapid growth in computing infrastructure has enabled bio-medical researchers to perform more comprehensive experiments and detailed case-studies. At the same time, performing these experiments are not only monetarily expensive but also time consuming. Thus, there is a growing need to provide tools to the researchers that will allow them to pose queries that will assist them in focusing on interesting “hypotheses”. However, such a tool would require capabilities to derive inferences based on existing known relationship between medical concepts. In this paper, we tackle this problem as one of non-factoid question answering wherein we try to answer the user-post questions by leveraging both authoritative as well as social media posts. While the former provides us with well knowledge on well researched topics, the latter provides us with real-time feedback on variety of topics like adverse drug effect (ADE), symptoms-drug relationship, etc. The challenge with leveraging the authoritative sources to infer answers for non-factoid question lies in: (a) The effective navigation of the answer search-space for timely response to the queries, (b) Ranking the candidate answers derived in step-(a) to enable non-trivial and novel discoveries, and (c) Being robust to perform confirmatory as well as discovery type of tasks.
Open AccessBridging The Evolving Semantics: A Data Driven Approach to Knowledge Discovery In Biomedicine
Recent progress in biological, medical and health-care technologies, and innovations in wearable sensors provide us with unprecedented opportunities to accumulate massive data to understand disease prognosis and develop personalized treatments and interventions. These massive data supplemented with rapid growth in computing infrastructure has enabled bio-medical researchers to perform more comprehensive experiments and detailed case-studies. At the same time, performing these experiments are not only monetarily expensive but also time consuming. Thus, there is a growing need to provide tools to the researchers that will allow them to pose queries that will assist them in focusing on interesting “hypotheses”. However, such a tool would require capabilities to derive inferences based on existing known relationship between medical concepts. In this paper, we tackle this problem as one of non-factoid question answering wherein we try to answer the user-post questions by leveraging both authoritative as well as social media posts. While the former provides us with well knowledge on well researched topics, the latter provides us with real-time feedback on variety of topics like adverse drug effect (ADE), symptoms-drug relationship, etc. The challenge with leveraging the authoritative sources to infer answers for non-factoid question lies in: (a) The effective navigation of the answer search-space for timely response to the queries, (b) Ranking the candidate answers derived in step-(a) to enable non-trivial and novel discoveries, and (c) Being robust to perform confirmatory as well as discovery type of tasks.