Krithik Vishwanath

Reply to: Limited benchmarks constrain the conclusions of a general-purpose versus clinical AI comparison

Krithik Vishwanath, Yindalon Aphinyanaphongs, Eric K. Oermann

us (code pays fourni par la source)

Big data in U.S. neuro-oncology: trends and translational priorities

Anjali Kapoor, Anton Alyakin, John Markert, Ari Arias et autres

us (code pays fourni par la source)

General-purpose large language models outperform specialized clinical AI tools on medical benchmarks

Krithik Vishwanath, Anton Alyakin, Mrigayu Ghosh, Ali Hage et autres

Specialized clinical artificial intelligence (AI) tools are entering medical practice despite scarce independent evaluation. We quantitatively evaluate two clinical AI tools, OpenEvidence and UpToDate Expert AI, built on large language models (LLMs) against three frontier LLMs: GPT-5.2, Gemini 3.1 Pro and Claude …

us (code pays fourni par la source)

Abstract 6832: Toward personalized rotational multi-agent therapies to overcome treatment resistance in pancreatic cancer: A virtual trial framework in mice.

Krithik Vishwanath, Hoon Choi, Mamta Gupta, Rong Zhou et autres

Abstract Introduction. Pancreatic ductal adenocarcinoma (PDAC) is highly lethal in part because tumors rapidly evolve resistance to potent regimens. Rotational, multi-agent schedules have emerged as a promising approach to outpace this adaptive escape. To attack this problem, we propose a mechanistic “virtual-trial” …

us (code pays fourni par la source)

Abstract PS3-04-22: A mathematical framework to optimize combination therapy for triple-negative breast cancer in obese mice

Krithik Vishwanath, C. I. Crawford, A. G. Sorace, T. E. Yankeelov et autres

Abstract Introduction. Triple-negative breast cancer (TNBC) disproportionately affects obese individuals, with emerging evidence suggesting that obesity may decrease or paradoxically enhance the efficacy of certain immunotherapies. However, obesity-driven intratumoral hypoxia presents additional challenges for treatment, motivating the use of evofosfamide (a hypoxia-activated …

us (code pays fourni par la source)

Large Language Models Predict Functional Outcomes after Acute Ischemic Stroke

Anjali K. Kapoor, Anton Alyakin, Jin Vivian Lee, Eunice Yang et autres

Accurate prediction of functional outcomes after acute ischemic stroke can inform clinical decision-making and resource allocation. Prior work on modified Rankin Scale (mRS) prediction has relied primarily on structured variables (e.g., age, NIHSS) and conventional machine learning. The ability of large language …

us, es, kr (code pays fourni par la source)

Evaluating the Performance and Fragility of Large Language Models on the Self-Assessment for Neurological Surgeons

Krithik Vishwanath, Anton Alyakin, Mrigayu Ghosh, Jin Ha Lee et autres

BACKGROUND AND OBJECTIVES: The Congress of Neurological Surgeons Self-Assessment for Neurological Surgeons questions are widely used by neurosurgical residents to prepare for written board examinations. Recently, these questions have also served as benchmarks for evaluating large language models' (LLMs) neurosurgical knowledge. LLMs …

us (code pays fourni par la source)

Modeling tumor dynamics and predicting response to therapies in a murine pancreatic cancer model

Krithik Vishwanath, Hoon Choi, Mamta Gupta, Rong Zhou et autres

Abstract We seek to establish a parsimonious mathematical framework for understanding the interaction and dynamics of the response of pancreatic cancer to the NGC triple chemotherapy regimen (mNab-paclitaxel, gemcitabine, and cisplatin), stromal-targeting drugs (calcipotriol and losartan), and an immune checkpoint inhibitor (anti-PD-L1). …

us, ru (code pays fourni par la source)

MedMobile: a mobile-sized language model with clinical capabilities

Krithik Vishwanath, Jaden Stryker, Anton Alyakin, Daniel Alexander Alber et autres

Objective: Language models (LMs) have demonstrated expert-level reasoning and recall abilities in medicine. However, computational costs and privacy concerns are mounting barriers to wide-scale implementation. To address these significant limitations, we introduce a parsimonious adaptation of phi-3-mini, MedMobile, a 3.8 billion parameter …

us (code pays fourni par la source)

Evaluating the performance and fragility of large language models on the self-assessment for neurological surgeons

Krithik Vishwanath, Anton Alyakin, Mrigayu Ghosh, Jin Ha Lee et autres

The Congress of Neurological Surgeons Self-Assessment for Neurological Surgeons (CNS-SANS) questions are widely used by neurosurgical residents to prepare for written board examinations. Recently, these questions have also served as benchmarks for evaluating large language models' (LLMs) neurosurgical knowledge. This study aims …

PO-05-141 IN VIVO PHOTOACOUSTIC IMAGING CAN ACCURATELY DETERMINE TRANSMURAL TISSUE CHARACTERIZATION

Nilesh Mathuria, Blake C. Fallon, Krithik Vishwanath, Antonio Martino et autres

Modeling tumor dynamics and predicting response to chemo-, targeted-, and immune-therapies in a murine model of pancreatic cancer

Krithik Vishwanath, Hoon Choi, Mamta Gupta, Rong Zhou et autres

We seek to establish a parsimonious mathematical framework for understanding the interaction and dynamics of the response of pancreatic cancer to the NGC triple chemotherapy regimen (mNab-paclitaxel, gemcitabine, and cisplatin), stromal-targeting drugs (calcipotriol and losartan), and an immune checkpoint inhibitor (anti-PD-L1). We …

us, ru (code pays fourni par la source)