小野 将平

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.

IMPORTANCE: The optimal intensity of care for older patients (age ≥80 years) in intensive care units (ICUs) remains uncertain. Although institutional variation in critical care practice has been described, less is known about case-mix-adjusted variation in life-sustaining treatment use among older patients admitted to ICUs and whether greater institutional treatment intensity is associated with improved survival. OBJECTIVE: To quantify institutional variation in the use of life-sustaining treatments for older patients among ICUs and examine the association of treatment intensity with in-hospital mortality. DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study used nationwide data from the Japanese Intensive Care Patient Database (JIPAD) for patients aged 80 years or older admitted to 127 ICUs at JIPAD-participating institutions in Japan between April 1, 2015, and March 31, 2023. EXPOSURES: Intensive care unit admission and age 80 years or older. MAIN OUTCOMES AND MEASURES: Institutional treatment intensity was quantified using standardized treatment ratio (STR), defined as the ratio of observed-to-expected life-sustaining treatment use after adjustment for patient-level characteristics. The association between STR category and in-hospital mortality was evaluated using both logistic regression and hierarchical bayesian multilevel logistic regression models. RESULTS: Among 60 713 patients (median age, 84 years [IQR, 82-87 years]; 32 302 male [53.2%]), the crude institutional rate of life-sustaining treatment use ranged from 4.8% (8 of 167 patients) to 38.0% (322 of 847 patients). After adjustment for patient case mix, the STR ranged from 0.24 (95% CI, 0.11-0.48) to 2.34 (95% CI, 1.91-2.85) across participating ICUs. In multilevel analyses adjusted for patient- and institution-level factors, higher institutional treatment intensity was not associated with in-hospital survival compared with intermediate treatment intensity (high STR category: odds ratio, 1.17; 95% credible interval, 0.91-1.39). CONCLUSIONS AND RELEVANCE: In this cohort study of older patients admitted to ICUs, institutional use of life-sustaining treatments varied substantially even after case-mix adjustment and higher institutional treatment intensity was not associated with better in-hospital survival. These findings suggest that increasing treatment intensity alone may not be associated with improved outcomes in this population and support the need for better approaches to identify patients most likely to benefit from intensive treatment.

OBJECTIVE: The aim of this study was to identify factors that predict admission to the intensive care unit (ICU) after activation of a rapid response system (RRS). METHODS: We conducted a retrospective observational study using data from 12,306 RRS activations recorded in the In-Hospital Emergency Registry in Japan database between November 2017 and September 2023. Patients aged under 18 years, noninpatients, and those who died or were transferred immediately after RRS activation were excluded. The primary outcome was ICU admission after RRS activation. Predictive factors were identified using multivariable logistic regression models: Model 1 included all available data, while model 2 was restricted to data available at the time of RRS activation. RESULTS: We analysed data from 8532 patients; 2298 (26.9%) were admitted to the ICU following RRS activation. Significant factors of ICU admission in model 1 included weekend activation (odds ratio [OR] = 1.17; 95% confidence interval [CI] = 1.02, 1.34), oxygen administration prior to activation (OR = 1.23; 95% CI = 1.08, 1.4), ICU discharge within 72 h before the index event (OR = 1.65; 95% CI = 1.28, 2.11), physician-initiated activation (OR = 2.16; 95% CI = 1.87, 2.50), and multiple abnormal vital signs. Model 2, which was limited to information available at the time of RRS activation, identified a similar pattern of associations. CONCLUSION: This study identified several important factors associated with ICU admission following RRS activation. These findings may support improved clinical decision-making regarding ICU transfers and provide a foundation for future work to develop and validate prediction models tailored to this setting.