arXiv subjects

Nadav Rappoport

Publications and source records attributed to Nadav Rappoport.

13 recordsLinked to original sources

arXiv2026

MedUPS: Towards Diagnostic Assistance in Uncommon Medical Cases with Large Language Models

Uncommon and off-guideline cases are difficult for clinical decision support, because physicians must make a series of management decisions under diagnostic uncertainty and rarely see the full case at once. Most large language model (LLM) benchmarks for medicine score only the final diagnosis, yet much of clinical care turns on the next appropriate action: the next test to order, the imaging study to obtain, the specialist to involve, or the differential to pursue. We introduce MedUPSQA, a dataset of 21,874 mid-stream clinical decision points built from 5,535 real case reports, and MedUPS, an alignment framework that supervises models on these intermediate decisions as they unfold along a patient's trajectory. We segment free-text case presentations into chronologically ordered, accumulating clinical chunks and align models to predict the next step with reinforcement learning (GRPO), using an external LLM-as-a-Judge reward. This objective mirrors how clinicians actually meet patients, reasoning forward from accumulating evidence toward the next decision, rather than committing to a final label. Across three backbones, mid-stream alignment raises next-step accuracy from 55.2 to 66.7 for Qwen3.6-27B, from 47.2 to 57.8 for Qwen3.5-9B, and from 37.8 to 44.4 for HuatuoGPT-3-8B, with 95% CI. In several model scales we test the objective improves accuracy more than scale, with smaller models surpassing larger, frontier models we evaluate. We further train supervised fine-tuning (SFT) baselines on the mid-stream task, SFT improves all backbones above base, indicating the target framwork carries signal independently of the optimizer. We release the dataset, code, and aligned checkpoints.

cs.CL↗

arXiv2026

Cluster Frequency Conformal Prediction for Local Coverage

Conformal prediction provides distribution-free coverage guarantees, but in many-class classification it may still under-cover specific classes or subpopulations, preventing safe deployment in high-stakes applications. We propose Cluster Frequency Conformal Prediction (CFCP), a plug-in framework that adapts conformal prediction to local structure in a learned representation space. CFCP clusters learned embeddings, estimates cluster-level label-frequency distributions from calibration data, and for each test point constructs a sample-specific probability vector by softly mixing nearby cluster distributions regularized with global-prior and reliability-aware shrinkage. This vector is then conformalized using standard set constructors. In the disjoint-split regime, CFCP inherits standard finite-sample marginal validity. Under additional assumptions, CFCP further admits a local-validity interpretation. Since representation clusters aggregate locally similar samples, their empirical class frequencies provide a stable estimate of local label ambiguity. Across image and text benchmarks, CFCP achieves the best class coverage in 15/16 dataset/score-family comparisons and a competitive prediction set size efficiency, with several settings substantially more efficient. Overall, our results show that cluster-frequency information provides an effective localized signal for improving classwise reliability in many-class conformal prediction.

cs.LG↗

arXiv2026

Trajectory-Based Difficulty Scoring for Reliable Learning on Tabular Data

Gradient-boosted trees achieve strong performance on tabular data, yet often leave a long tail of poorly predicted instances. We introduce a Trajectory-based Difficulty Score (TDS), an instance-level difficulty estimator for boosted ensembles derived from per-tree cumulative prediction trajectories. For each instance, we compute interpretable trajectory descriptors (e.g., variance, oscillation peaks, sign switches, and tail stability) and train a lightweight regression model to predict held-out loss. An empirical CDF calibrates the resulting signal into a score in $[0,1]$ that supports ranking hard cases. Across diverse tabular benchmarks and ensemble sizes, TDS exhibits strong rank correlation with error and outperforms established instance-hardness and uncertainty baselines on classification, while remaining competitive on regression. We then show how a single difficulty signal improves multiple data mining workflows: difficulty-driven active learning for label-efficient training, difficulty-thresholded selective prediction for improved risk-coverage trade-offs, and TDS-stratified (Mondrian) conformal prediction for more uniform conditional coverage. Finally, clustering high-TDS instances using SHAP attributions reveals coherent failure modes characterized by compact feature-value ranges, supporting error analysis and targeted data acquisition.

cs.LG↗

arXiv2026

ProtSent: Protein Sentence Transformers

Protein language models (pLMs) produce per-residue representations that capture evolutionary and structural information, yet their mean-pooled sequence embeddings are not explicitly trained to reflect functional, evolutionary or structural similarity between proteins. We present Protein Sentence Transformers (ProtSent), a contrastive fine-tuning framework for adapting PLMs into general-purpose embedding models. ProtSent trains with MultipleNegativesRankingLoss across five protein-pair datasets: Pfam families, structurally derived hard negatives, AlphaFold DB structural pairs, and StringDB protein--protein interactions, and Deep Mutational Scanning data. We evaluate on 23~downstream tasks using frozen embeddings with a k-nearest-neighbor probe to measure embedding neighborhood quality. On ESM-2 150M, ProtSent improves 15 of 23 tasks, with gains of +105% on remote homology detection, +17% on variant effect prediction, and +19.9% Recall@1 on SCOPe-40 structural retrieval. The 35M variant improves 16 of 23 tasks with +40.5% on remote homology and +15.5% Recall@1 on SCOPe-40. Contrastive fine-tuning restructures the embedding space to better capture protein function and structure, without any task-specific supervision. We release the models, public data, and training recipe and code.

cs.LG↗

arXiv2025

Clustered Calibration: Representation-Aware Probability Calibration via Learned Subpopulations

Ensuring that predicted probabilities align with observed frequencies is critical in high-stakes domains such as clinical decision support, autonomous driving and financial risk assessment. Existing calibration methods typically apply a single global transformation or rely on post-hoc binning over predicted confidences, limiting their ability to exploit heterogeneous reliability across sub-populations. We propose Clustered Calibration, a representation-aware framework that identifies sub-populations via clustering in learned feature spaces (e.g., coverage vectors, SHAP values, CNN activations, Transformer embeddings) and fits a soft mixture of cluster-specific parametric calibrators under hierarchical shrinkage toward a global mapping. This design yields context-specific calibration while maintaining global stability. Across six tabular datasets and additional image and text benchmarks, clustered calibration consistently improves or matches strong global calibrators in terms of negative log-likelihood and Brier score, while preserving AUC and accuracy. We further show, both analytically and empirically, that fixed-bin Expected Calibration Error (ECE) can mis-rank soft, region-aware calibrators even when proper scoring rules improve, and we advocate for log-loss and Brier as more reliable bases for model selection in such settings.

cs.LG↗

arXiv2025

CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset

Medical benchmark datasets significantly contribute to developing Large Language Models (LLMs) for medical knowledge extraction, diagnosis, summarization, and other uses. Yet, current benchmarks are mainly derived from exam questions given to medical students or cases described in the medical literature, lacking the complexity of real-world patient cases that deviate from classic textbook abstractions. These include rare diseases, uncommon presentations of common diseases, and unexpected treatment responses. Here, we construct Clinically Uncommon Patient Cases and Diagnosis Dataset (CUPCase) based on 3,562 real-world case reports from BMC, including diagnoses in open-ended textual format and as multiple-choice options with distractors. Using this dataset, we evaluate the ability of state-of-the-art LLMs, including both general-purpose and Clinical LLMs, to identify and correctly diagnose a patient case, and test models' performance when only partial information about cases is available. Our findings show that general-purpose GPT-4o attains the best performance in both the multiple-choice task (average accuracy of 87.9%) and the open-ended task (BERTScore F1 of 0.764), outperforming several LLMs with a focus on the medical domain such as Meditron-70B and MedLM-Large. Moreover, GPT-4o was able to maintain 87% and 88% of its performance with only the first 20% of tokens of the case presentation in multiple-choice and free text, respectively, highlighting the potential of LLMs to aid in early diagnosis in real-world cases. CUPCase expands our ability to evaluate LLMs for clinical decision support in an open and reproducible manner.

cs.CL↗

arXiv2024

MedConceptsQA: Open Source Medical Concepts QA Benchmark

We present MedConceptsQA, a dedicated open source benchmark for medical concepts question answering. The benchmark comprises of questions of various medical concepts across different vocabularies: diagnoses, procedures, and drugs. The questions are categorized into three levels of difficulty: easy, medium, and hard. We conducted evaluations of the benchmark using various Large Language Models. Our findings show that pre-trained clinical Large Language Models achieved accuracy levels close to random guessing on this benchmark, despite being pre-trained on medical data. However, GPT-4 achieves an absolute average improvement of nearly 27%-37% (27% for zero-shot learning and 37% for few-shot learning) when compared to clinical Large Language Models. Our benchmark serves as a valuable resource for evaluating the understanding and reasoning of medical concepts by Large Language Models. Our benchmark is available at https://huggingface.co/datasets/ofir408/MedConceptsQA

cs.CL↗

arXiv2024

CPLLM: Clinical Prediction with Large Language Models

We present Clinical Prediction with Large Language Models (CPLLM), a method that involves fine-tuning a pre-trained Large Language Model (LLM) for clinical disease and readmission prediction. We utilized quantization and fine-tuned the LLM using prompts. For diagnosis prediction, we predict whether patients will be diagnosed with a target disease during their next visit or in the subsequent diagnosis, leveraging their historical diagnosis records. We compared our results to various baselines, including RETAIN, and Med-BERT, the current state-of-the-art model for disease prediction using temporal structured EHR data. In addition, We also evaluated CPLLM for patient hospital readmission prediction and compared our method's performance with benchmark baselines. Our experiments have shown that our proposed method, CPLLM, surpasses all the tested models in terms of PR-AUC and ROC-AUC metrics, showing state-of-the-art results for diagnosis prediction and patient hospital readmission prediction. Such a method can be easily implemented and integrated into the clinical process to help care providers estimate the next steps of patients

cs.CL↗

arXiv2024

DSF-GAN: DownStream Feedback Generative Adversarial Network

Utility and privacy are two crucial measurements of the quality of synthetic tabular data. While significant advancements have been made in privacy measures, generating synthetic samples with high utility remains challenging. To enhance the utility of synthetic samples, we propose a novel architecture called the DownStream Feedback Generative Adversarial Network (DSF-GAN). This approach incorporates feedback from a downstream prediction model during training to augment the generator's loss function with valuable information. Thus, DSF-GAN utilizes a downstream prediction task to enhance the utility of synthetic samples. To evaluate our method, we tested it using two popular datasets. Our experiments demonstrate improved model performance when training on synthetic samples generated by DSF-GAN, compared to those generated by the same GAN architecture without feedback. The evaluation was conducted on the same validation set comprising real samples. All code and datasets used in this research will be made openly available for ease of reproduction.

cs.LG↗

arXiv2024

Surgery duration prediction using multi-task feature selection

Efficient optimization of operating room (OR) activity poses a significant challenge for hospital managers due to the complex and risky nature of the environment. The traditional "one size fits all" approach to OR scheduling is no longer practical, and personalized medicine is required to meet the diverse needs of patients, care providers, medical procedures, and system constraints within limited resources. This paper aims to introduce a scientific and practical tool for predicting surgery durations and improving OR performance for maximum benefit to patients and the hospital. Previous works used machine-learning models for surgery duration prediction based on preoperative data. The models consider covariates known to the medical staff at the time of scheduling the surgery. Given a large number of covariates, model selection becomes crucial, and the number of covariates used for prediction depends on the available sample size. Our proposed approach utilizes multi-task regression to select a common subset of predicting covariates for all tasks with the same sample size while allowing the model's coefficients to vary between them. A regression task can refer to a single surgeon or operation type or the interaction between them. By considering these diverse factors, our method provides an overall more accurate estimation of the surgery durations, and the selected covariates that enter the model may help to identify the resources required for a specific surgery. We found that when the regression tasks were surgeon-based or based on the pair of operation type and surgeon, our suggested approach outperformed the compared baseline suggested in a previous study. However, our approach failed to reach the baseline for an operation-type-based task.

stat.AP↗

arXiv2024

Subpopulation-Specific Synthetic EHR for Better Mortality Prediction

Electronic health records (EHR) often contain different rates of representation of certain subpopulations (SP). Factors like patient demographics, clinical condition prevalence, and medical center type contribute to this underrepresentation. Consequently, when training machine learning models on such datasets, the models struggle to generalize well and perform poorly on underrepresented SPs. To address this issue, we propose a novel ensemble framework that utilizes generative models. Specifically, we train a GAN-based synthetic data generator for each SP and incorporate synthetic samples into each SP training set. Ultimately, we train SP-specific prediction models. To properly evaluate this method, we design an evaluation pipeline with 2 real-world use case datasets, queried from the MIMIC database. Our approach shows increased model performance over underrepresented SPs. Our code and models are given as supplementary and will be made available on a public repository.

cs.LG↗

arXiv2023

Federated Learning of Medical Concepts Embedding using BEHRT

Electronic Health Records (EHR) data contains medical records such as diagnoses, medications, procedures, and treatments of patients. This data is often considered sensitive medical information. Therefore, the EHR data from the medical centers often cannot be shared, making it difficult to create prediction models using multi-center EHR data, which is essential for such models' robustness and generalizability. Federated Learning (FL) is an algorithmic approach that allows learning a shared model using data in multiple locations without the need to store all data in a central place. An example of a prediction model's task is to predict future diseases. More specifically, the model needs to predict patient's next visit diagnoses, based on current and previous clinical data. Such a prediction model can support care providers in making clinical decisions and even provide preventive treatment. We propose a federated learning approach for learning medical concepts embedding. This pre-trained model can be used for fine-tuning for specific downstream tasks. Our approach is based on an embedding model like BEHRT, a deep neural sequence transduction model for EHR. We train using federated learning, both the Masked Language Modeling (MLM) and the next visit downstream model. We demonstrate our approach on the MIMIC-IV dataset. We compare the performance of a model trained with FL against a model trained on centralized data. We find that our federated learning approach reaches very close to the performance of a centralized model, and it outperforms local models in terms of average precision. We also show that pre-trained MLM improves the model's average precision performance in the next visit prediction task, compared to an MLM model without pre-training. Our code is available at https://github.com/nadavlab/FederatedBEHRT.

cs.LG↗

arXiv2016

An expanded evaluation of protein function prediction methods shows an improvement in accuracy

Background: The increasing volume and variety of genotypic and phenotypic data is a major defining characteristic of modern biomedical sciences. At the same time, the limitations in technology for generating data and the inherently stochastic nature of biomolecular events have led to the discrepancy between the volume of data and the amount of knowledge gleaned from it. A major bottleneck in our ability to understand the molecular underpinnings of life is the assignment of function to biological macromolecules, especially proteins. While molecular experiments provide the most reliable annotation of proteins, their relatively low throughput and restricted purview have led to an increasing role for computational function prediction. However, accurately assessing methods for protein function prediction and tracking progress in the field remain challenging. Methodology: We have conducted the second Critical Assessment of Functional Annotation (CAFA), a timed challenge to assess computational methods that automatically assign protein function. One hundred twenty-six methods from 56 research groups were evaluated for their ability to predict biological functions using the Gene Ontology and gene-disease associations using the Human Phenotype Ontology on a set of 3,681 proteins from 18 species. CAFA2 featured significantly expanded analysis compared with CAFA1, with regards to data set size, variety, and assessment metrics. To review progress in the field, the analysis also compared the best methods participating in CAFA1 to those of CAFA2. Conclusions: The top performing methods in CAFA2 outperformed the best methods from CAFA1, demonstrating that computational function prediction is improving. This increased accuracy can be attributed to the combined effect of the growing number of experimental annotations and improved methods for function prediction.

q-bio.QM↗