HPHinesh Patel

Hinesh Patel

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hinesh Patel has a total of 100 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    Holistic evaluation of large language models for medical tasks with MedHELM

    by Suhana Bedi, Hejie Cui, Miguel Fuentes, Alyssa Unell, Michael Wornow, Juan M. Banda, Nikesh Kotecha, Timothy Keyes, Yifan Mai, Mert Oez, et al.

    While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinical practice. Here we introduce MedHELM, an extensible evaluation framework with three contributions. First, a clinician-validated taxonomy organizing medical AI applications into five categories that mirror real clinical tasks—clinical decision support (diagnostic decisions, treatment planning), clinical note generation (visit documentation, procedure reports), patient communication (education materials, care instructions), medical research (literature analysis, clinical data analysis) and administration (scheduling, workflow coordination). These encompass 22 subcategories and 121 specific tasks reflecting daily medical practice. Second, a comprehensive benchmark suite of 37 evaluations covering all subcategories. Third, systematic comparison of nine frontier LLMs—Claude 3.5 Sonnet, Claude 3.7 Sonnet, DeepSeek R1, Gemini 1.5 Pro, Gemini 2.0 Flash, GPT-4o, GPT-4o mini, Llama 3.3 and o3-mini—using an automated LLM-jury evaluation method. Our LLM-jury uses multiple AI evaluators to assess model outputs against expert-defined criteria. Advanced reasoning models (DeepSeek R1, o3-mini) demonstrated superior performance with win rates of 66%, although Claude 3.5 Sonnet achieved comparable results at 15% lower computational cost. These results not only highlight current model capabilities but also demonstrate how MedHELM could enable evidence-based selection of medical AI systems for healthcare applications.


  • Phasor Analysis of Fluorescence Lifetime Enables Quantitative Multiplexed Molecular Imaging of Three Probes

    by Maha K. Rahim, Jinghui Zhao, Hinesh V. Patel, Hauna A. Lagouros, Rajesh Kota, Irma Fernandez, Enrico Gratton, Jered B. Haun

    The excited-state lifetime is an intrinsic property of fluorescent molecules that can be leveraged for multiplexed imaging. An advantage of fluorescence lifetime-based multiplexing is that signals from multiple probes can be gathered simultaneously, whereas traditional spectral fluorescence imaging typically requires multiple images at different excitation and emission wavelengths. Additionally, lifetime and spectra could both be utilized to expand the multiplexing capacity of fluorescence. However, resolving exogenous molecular probes based exclusively on the fluorescence lifetime has been limited by technical challenges in analyzing lifetime data. The phasor approach to lifetime analysis offers a simple, graphical solution that has increasingly been used to assess endogenous cellular autofluorescence to quantify metabolic factors. In this study, we employed the phasor analysis of FLIM to quantitatively resolve three exogenous, antibody-targeted fluorescent probes with similar spectral properties based on lifetime information alone. First, we demonstrated that three biomarkers that were spatially restricted to the cell membrane, cytosol, or nucleus could be accurately distinguished using FLIM and phasor analysis. Next, we successfully resolved and quantified three probes that were all targeted to cell surface biomarkers. Finally, we demonstrated that lifetime-based quantitation accuracy can be improved through intensity matching of various probe-biomarker combinations, which will expand the utility of this technique. Importantly, we reconstructed images for each individual probe, as well as an overlay of all three probes, from a single FLIM image. Our results demonstrate that FLIM and phasor analysis can be leveraged as a powerful tool for simultaneous detection of multiple biomarkers with high sensitivity and accuracy.


  • Open Access

    Amplification-Free Detection of Circulating microRNA Biomarkers from Body Fluids Based on Fluorogenic Oligonucleotide-Templated Reaction between Engineered Peptide Nucleic Acid Probes: Application to Prostate Cancer Diagnosis

    by Gavin A. D. Metcalf, Akifumi Shibakawa, Hinesh Patel, Ailsa Sita-Lumsden, Andrea Zivi, Nona Rama, Charlotte L. Bevan, Sylvain Ladame

    Highly abundant in cells, microRNAs (or miRs) play a key role as regulators of gene expression. A proportion of them are also detectable in biofluids making them ideal noninvasive biomarkers for pathologies in which miR levels are aberrantly expressed, such as cancer. Peptide nucleic acids (PNAs) are engineered uncharged oligonucleotide analogues capable of hybridizing to complementary nucleic acids with high affinity and high specificity. Herein, novel PNA-based fluorogenic biosensors have been designed and synthesized that target miR biomarkers for prostate cancer (PCa). The sensing strategy is based on oligonucleotide-templated reactions where the only miR of interest serves as a matrix to catalyze an otherwise highly unfavorable fluorogenic reaction. Validated in vitro using synthetic RNAs, these newly developed biosensors were then shown to detect endogenous concentrations of miR in human blood samples without the need for any amplification step and with minimal sample processing. This low-cost, quantitative, and versatile sensing technology has been technically validated using gold-standard RT-qPCR. Compared to RT-qPCR however, this enzyme-free, isothermal blood test is amenable to incorporation into low-cost portable devices and could therefore be suitable for widespread public screening.


  • The effect of biceps adhesions on glenohumeral range of motion: a cadaveric study

    by Patrick J. McGahan, Hinesh Patel, Ephraim Dickinson, Jeremi Leasure, William Montgomery