深野 賢太朗

OBJECTIVES: To operationalize and temporally validate an electronic medical record (EMR)-integrated machine learning system (Big data-driven Evaluation of Survival and Treatment in Acute Illness [BEST-AI]) that generates hourly predictions for multiple ICU outcomes, with emphasis on discrimination, calibration, and workflow integration. DESIGN: Single-center hybrid study with stepwise clinical deployment and forward-in-time temporal validation. SETTING: Thirty-bed tertiary mixed medical-surgical ICU in Japan. PATIENTS: All ICU admissions from August 2017 to March 2025. Exclusions: age younger than 16 years or ICU stay less than 4 hours. Development cohort (n = 11,176; from August 2017 to July 2024) and temporal validation cohort (n = 1,127; from August 2024 to March 2025). INTERVENTIONS: EMR-integrated deployment of BEST-AI providing hourly probabilistic predictions to clinicians within the EMR; no protocolized clinical interventions were mandated. MEASUREMENTS AND MAIN RESULTS: Six prediction tasks (in-hospital mortality, ICU mortality, ICU discharge ≤ 72 hr, intubation ≤ 72 hr, extubation ≤ 72 hr, tracheostomy at ICU discharge) were evaluated. In temporal validation, the area under the receiver operating characteristic curves ranged from 0.856 to 0.960, and the area under the precision-recall curves from 0.302 to 0.786. Decile-based calibration showed overall good agreement; hospital mortality was slightly overestimated at higher predicted probabilities, whereas ICU mortality remained well aligned. The intubation task had comparatively lower discrimination and greater deviation from perfect calibration, consistent with low event counts and heterogeneous timing. A 24-hour landmark sensitivity analysis (one prediction per patient at 24 hr after ICU admission) preserved discrimination and calibration relative to the main analysis, supporting robustness beyond repeated-measures evaluation. The system was successfully maintained with automated hourly updates and EMR-embedded patient- and unit-level visualizations, without prescriptive alerts. CONCLUSIONS: A continuously deployed, EMR-integrated ICU prediction system achieved strong temporal discrimination and generally good calibration. Embedding real-time predictions into routine workflow was feasible, and the system was maintained with automated hourly updates. Prospective multicenter studies are warranted to assess transportability and clinical impact.

INTRODUCTION: With the rapid increase in the ageing population, the use of procedural sedation and analgesia (PSA) for diagnostic procedures such as prostate biopsy in older adults is increasing. However, elderly patients are particularly susceptible to respiratory depression during PSA testing and have a significantly higher risk of hypoxaemia during procedures requiring deep sedation. Although propofol combined with fentanyl is commonly used, it frequently causes hypoxaemia and apnoea. Remimazolam, a novel ultrashort-acting benzodiazepine, may be a safer alternative with less respiratory compromise; however, the supporting evidence remains limited. This study aims to assess whether remimazolam combined with fentanyl reduces the incidence of respiratory depression compared with propofol combined with fentanyl in elderly patients undergoing prostate biopsy under deep sedation requiring immobility. METHODS AND ANALYSIS: This is a single-centre, participant and assessor-blinded (with pragmatic blinding of participants), parallel-group, superiority randomised controlled trial conducted at the Jichi Medical University Saitama Medical Centre, Japan. Eligible participants are men aged ≥70 years who are scheduled to undergo prostate biopsy under intravenous sedation. Participants will be randomised in a 1:1 ratio to receive either remimazolam or propofol, each administered in combination with fentanyl at a fixed effect-site concentration. The primary outcome is the incidence of severe apnoea (≥1 min). The primary analysis will follow the intention-to-treat principle, implemented practically as a full analysis set analysed using a complete case approach. Sensitivity analyses will include a per-protocol analysis and multiple imputations of missing data. A subgroup analysis of patients aged ≥75 years was performed. ETHICS AND DISSEMINATION: This study was approved by the Jichi Medical University Central Clinical Research Ethics Committee (approval number: 24JMU001S-2) and was registered with the Japan Registry of Clinical Trials on 11 November 2024. Written informed consent was obtained from all participants before enrolment. These findings will be disseminated through publications in peer-reviewed journals and presentations at scientific conferences. TRIAL REGISTRATION NUMBER: jRCTs031240478.

Procedural sedation and analgesia (PSA) is generally considered safe, yet fatal events remain poorly characterised across procedures and specialties. We retrospectively reviewed the Japan Council for Quality Health Care nationwide adverse-event database (2012-2021), searching narrative reports with 40 Japanese keywords for sedation terms and drug names. Only reports in which PSA was deemed the primary cause of death were included; non-procedural sedation, planned general anaesthesia and procedure-induced injuries were excluded. Among 10 011 reports identified via keyword search, 805 described deaths and 23 were attributed to PSA. Fatalities clustered in gastroenterology (73.9%), particularly endoscopic retrograde cholangiopancreatography (ERCP; 34.8%). Most cases were high-risk patients aged 70-89 years (65.2%) and retrospectively classified as American Society of Anesthesiologists Physical Status III/IV (87%), yet no anaesthetist involvement was documented. Oxygen desaturation was the earliest sign of deterioration (56.5%), and capnography was not documented in any case. When PSA fatalities in Japan are examined across procedures and specialties, gastrointestinal interventions-especially ERCP-predominate in our cohort; however, the absence of procedure-specific denominators warrants cautious interpretation. Targeted safety measures, in line with current national sedation guidelines, including enhanced presedation evaluation, anaesthetist involvement for high-risk patients and routine capnography, may help to reduce PSA-related mortality.