Institution profile

Northwell Health

Academic institutionnorthamerica · us
Official website
Research library4linked papers
Opportunities0open roles
Selected work

Representative Papers

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies

Oct 02, 2026

This study addresses the scarcity of annotated oncological data that constrains deep learning-based biomarker development by proposing a two-stage multimodal AI framework. The approach first infers transcriptomic features from histopathology images and subsequently integrates clinical variables to predict pathological complete response to neoadjuvant therapy in breast cancer. Its core innovation lies in introducing a biologically informed compression strategy that overcomes the target selection constraints of conventional genomic assays, enabling robust generalization under data-sparse conditions while ensuring reliability through spatial consistency validation. Experimental results demonstrate that the model achieves a mixed AUROC of 0.79, outperforming traditional pathology-based biomarkers. Furthermore, it exhibits strong discriminative capacity across molecular subtypes and exceptional sampling robustness, highlighting its potential for precision oncology applications where labeled training data remain limited.

0 citationsRead paper

Overview of BioASQ 2026: The fourteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering

Sep 30, 2026

This work addresses the evaluation challenges of semantic indexing, information extraction, and question answering in biomedical text processing through the 14th BioASQ challenge. The initiative introduces six innovative shared tasks, encompassing multilingual clinical abstracts, nested entity-relation extraction, and cardiology coding. By integrating state-of-the-art methodologies in natural language processing, semantic indexing, automatic question answering, and text summarization, the challenge systematically evaluates existing techniques for biomedical language understanding. The competition attracted 87 participating teams, which collectively submitted over one thousand system runs. Numerous submissions achieved highly competitive performance across multiple evaluation metrics. Ultimately, this large-scale benchmarking effort significantly advances technological progress and methodological innovation within the field of biomedical natural language processing.

0 citationsRead paper

Bias-corrected Cox regression with AI-extracted covariates via calibration summary statistics

Jul 28, 2026

This study addresses the bias in Cox proportional hazards model estimates arising from measurement error in AI-extracted covariates, a setting where downstream users only have access to the extracted data and limited calibration summary statistics. Within a multivariate calibration framework, the work provides the first decomposition of Cox model bias into a dominant, calibratable component and higher-order residual terms. Building on this insight, the authors propose a post-processing correction method that relies solely on calibration summary statistics and can be directly applied to outputs from standard Cox regression software. The approach is accompanied by uncertainty-adjusted confidence intervals and sensitivity diagnostic tools. Empirical evaluations on synthetic data demonstrate substantial bias reduction, with near-nominal coverage maintained even under mild violations of the linear calibration assumption. The paper also recommends a minimal set of calibration statistics that data providers should report to enable effective bias correction.

0 citationsRead paper
Recent publications

Latest Papers

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies

Oct 02, 2026

This study addresses the scarcity of annotated oncological data that constrains deep learning-based biomarker development by proposing a two-stage multimodal AI framework. The approach first infers transcriptomic features from histopathology images and subsequently integrates clinical variables to predict pathological complete response to neoadjuvant therapy in breast cancer. Its core innovation lies in introducing a biologically informed compression strategy that overcomes the target selection constraints of conventional genomic assays, enabling robust generalization under data-sparse conditions while ensuring reliability through spatial consistency validation. Experimental results demonstrate that the model achieves a mixed AUROC of 0.79, outperforming traditional pathology-based biomarkers. Furthermore, it exhibits strong discriminative capacity across molecular subtypes and exceptional sampling robustness, highlighting its potential for precision oncology applications where labeled training data remain limited.

0 citationsRead paper

Overview of BioASQ 2026: The fourteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering

Sep 30, 2026

This work addresses the evaluation challenges of semantic indexing, information extraction, and question answering in biomedical text processing through the 14th BioASQ challenge. The initiative introduces six innovative shared tasks, encompassing multilingual clinical abstracts, nested entity-relation extraction, and cardiology coding. By integrating state-of-the-art methodologies in natural language processing, semantic indexing, automatic question answering, and text summarization, the challenge systematically evaluates existing techniques for biomedical language understanding. The competition attracted 87 participating teams, which collectively submitted over one thousand system runs. Numerous submissions achieved highly competitive performance across multiple evaluation metrics. Ultimately, this large-scale benchmarking effort significantly advances technological progress and methodological innovation within the field of biomedical natural language processing.

0 citationsRead paper

Bias-corrected Cox regression with AI-extracted covariates via calibration summary statistics

Jul 28, 2026

This study addresses the bias in Cox proportional hazards model estimates arising from measurement error in AI-extracted covariates, a setting where downstream users only have access to the extracted data and limited calibration summary statistics. Within a multivariate calibration framework, the work provides the first decomposition of Cox model bias into a dominant, calibratable component and higher-order residual terms. Building on this insight, the authors propose a post-processing correction method that relies solely on calibration summary statistics and can be directly applied to outputs from standard Cox regression software. The approach is accompanied by uncertainty-adjusted confidence intervals and sensitivity diagnostic tools. Empirical evaluations on synthetic data demonstrate substantial bias reduction, with near-nominal coverage maintained even under mild violations of the linear calibration assumption. The paper also recommends a minimal set of calibration statistics that data providers should report to enable effective bias correction.

0 citationsRead paper