# Clinical Prediction

Blank Bio has released Ladon, a 3-billion-parameter transcriptomic foundation model pretrained with a self-supervised objective on millions of RNA-seq samples to predict patient prognosis and therapeutic response from pre-treatment expression data. Across six held-out clinical trials in bladder, kidney, lung and liver cancer, Ladon significantly outperformed all baselines for immunotherapy response prediction, including PD-L1 expression; a score built for the POPLAR trial behaved as a predictive rather than merely prognostic biomarker.

Blank Bio has released Ladon, a 3-billion-parameter transcriptomic foundation model pretrained with a self-supervised objective on millions of RNA-seq samples to predict patient prognosis and therapeutic response from pre-treatment expression data. Across six held-out clinical trials in bladder, kidney, lung and liver cancer, Ladon significantly outperformed all baselines for immunotherapy response prediction, including PD-L1 expression; a score built for the POPLAR trial behaved as a predictive rather than merely prognostic biomarker.

Curiosity-0826-4B extends a generative medical event foundation model trained on Epic Cosmos records from adults to pediatric patients and adds explicit representations of death and right-censoring. The model grows from 1B to 4.3B parameters and from an 8K to a 16K context window, generally matching or exceeding Curiosity-0226-1B on tasks both support, with mean absolute error on laboratory value prediction 18–46% lower. Pediatric AUROCs for incident asthma and asthma exacerbation are comparable to an adult reference cohort, while sickle cell crisis is lower in children.

Curiosity-0826-4B extends a generative medical event foundation model trained on Epic Cosmos records from adults to pediatric patients and adds explicit representations of death and right-censoring. The model grows from 1B to 4.3B parameters and from an 8K to a 16K context window, generally matching or exceeding Curiosity-0226-1B on tasks both support, with mean absolute error on laboratory value prediction 18–46% lower. Pediatric AUROCs for incident asthma and asthma exacerbation are comparable to an adult reference cohort, while sickle cell crisis is lower in children.

FERMAT, a 65-million-parameter clinical foundation model pretrained on records from 3.77 million patients, was compared against itself on the same patients: patient representations predicted five-year kidney, fatty liver, and diabetes risk better, while generated trajectories predicted the diagnoses, prescriptions, and procedures recorded together on the next clinical date better.

FERMAT, a 65-million-parameter clinical foundation model pretrained on records from 3.77 million patients, was compared against itself on the same patients: patient representations predicted five-year kidney, fatty liver, and diabetes risk better, while generated trajectories predicted the diagnoses, prescriptions, and procedures recorded together on the next clinical date better.

Clinical prediction models inherit their quality from routine-care training data, yet missingness rates and class ratios are not tied to what happens after deployment. An exploratory benchmark across three MIMIC-IV cohorts and the multi-institution eICU database splits data quality into completeness, label noise, distributional similarity, representativeness and temporal integrity, training a real model under each controlled condition and measuring held-out log-loss and calibration change. The composite moved in the expected direction in all three controlled cohorts, but combined corruptions were sub-additive rather than multiplicative, and across 21 analyzable eICU hospitals it tracked calibration but not detectably discrimination.

Clinical prediction models inherit their quality from routine-care training data, yet missingness rates and class ratios are not tied to what happens after deployment. An exploratory benchmark across three MIMIC-IV cohorts and the multi-institution eICU database splits data quality into completeness, label noise, distributional similarity, representativeness and temporal integrity, training a real model under each controlled condition and measuring held-out log-loss and calibration change. The composite moved in the expected direction in all three controlled cohorts, but combined corruptions were sub-additive rather than multiplicative, and across 21 analyzable eICU hospitals it tracked calibration but not detectably discrimination.

A 123.5-million-parameter generative model, Didymos, was trained once without task labels on 409,297 intensive care stays from seven databases in five countries and answers prediction questions by sampling a patient's futures. On held-out stays it read 13 primary endpoints from those futures at AUROC 0.83–0.98 and ranked first on average among 20 predictors, including label-trained LightGBM and TabPFN-3.5. Its simulated treatment responses agreed with eight of nine observational contrasts, yet at two hospitals in Russia and China that contributed no training data it needed minutes of continued training on unlabelled local stays to match locally supervised models.

A 123.5-million-parameter generative model, Didymos, was trained once without task labels on 409,297 intensive care stays from seven databases in five countries and answers prediction questions by sampling a patient's futures. On held-out stays it read 13 primary endpoints from those futures at AUROC 0.83–0.98 and ranked first on average among 20 predictors, including label-trained LightGBM and TabPFN-3.5. Its simulated treatment responses agreed with eight of nine observational contrasts, yet at two hospitals in Russia and China that contributed no training data it needed minutes of continued training on unlabelled local stays to match locally supervised models.

The work proposes RASPER, a reward-aligned summarizer for EHR prediction: a tunable LLM-based summarizer extracts task-relevant evidence from discharge notes and is trained via reinforcement learning with a reward derived from the downstream predictor's loss, while a longitudinal encoder converts structured codes into soft prompts that inject each patient's clinical context into summarization, so that summaries retain patient-specific evidence complementing structured codes; RASPER consistently outperforms strong baselines on readmission prediction and medication recommendation across MIMIC-III and MIMIC-IV.

The work proposes RASPER, a reward-aligned summarizer for EHR prediction: a tunable LLM-based summarizer extracts task-relevant evidence from discharge notes and is trained via reinforcement learning with a reward derived from the downstream predictor's loss, while a longitudinal encoder converts structured codes into soft prompts that inject each patient's clinical context into summarization, so that summaries retain patient-specific evidence complementing structured codes; RASPER consistently outperforms strong baselines on readmission prediction and medication recommendation across MIMIC-III and MIMIC-IV.