On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “hypoxemia”

Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learningcs.LG

Deep learning predicts hypoxemia from SpO2 data better than anesthesiologists.

problem Improving hypoxemia prediction for better patient outcomes.

method Trained deep learning model on SpO2 data to predict hypoxemia.

result Deep learning model outperforms anesthesiologists in predicting hypoxemia.

hypoxemia deep learning SpO2 anesthesiology clinical decision support

2017-12-02abs ↗pdf ↗

Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Datacs.LG

Paper combines LSTM and XGB for better hypoxemia prediction.

problem Forecasting hypoxemia in operating rooms using time series data.

method Feature learning via LSTM networks and prediction via gradient boosting trees.

result Augmenting XGB with LSTM features improves prediction performance.

hypoxemia operating room time series LSTM gradient boosting

2018-01-23abs ↗pdf ↗

An MLI-Guided Framework for Subgroup-Aware Modeling in Electronic Health Records (AdaptHetero)cs.LG

AdaptHetero uses MLI to tailor EHR models for subgroup-specific predictions.

problem Lack of subgroup-specific, operationalizable modeling strategies in EHRs.

method Integrates MLI with unsupervised clustering to identify subgroup-specific characteristics.

result Improves predictive performance by up to 174.39 percent across many subpopulations.

Electronic Health Records Subgroup Modeling Machine Learning Interpretation Unsupervised Clustering ICU Mortality

2025-07-28abs ↗pdf ↗

Forecasting adverse surgical events using self-supervised transfer learning for physiological signalscs.LG

PHASE predicts surgical complications from physiological signals.

problem Predicting adverse surgical outcomes from physiological signals.

method Self-supervised transfer learning for physiological signals.

result PHASE outperforms other approaches in predicting five surgical complications.

surgical complications physiological signals transfer learning machine learning adverse events

2020-02-12abs ↗pdf ↗