Yukihiro Kondo

Background: Postoperative complications after noncardiac surgery under general anesthesia remain a major cause of morbidity, mortality, and resource-intensive care. Conventional risk assessment tools rely mainly on preoperative information and may not capture perioperative physiological and procedural factors associated with postoperative risk. Objective: This retrospective multicenter observational study aimed to develop and validate electronic health record (EHR)–based machine learning (ML) models for predicting major postoperative complications and to evaluate their discrimination, overall probabilistic performance, calibration, and potential clinical utility. Methods: We analyzed 35,702 adults who underwent noncardiac surgery under general anesthesia at 3 tertiary hospitals between January 2021 and March 2025. Preoperative, intraoperative, and early postoperative variables were extracted from diagnosis procedure combination (DPC) claims, EHRs, and anesthesia information systems. The primary outcome was a 30-day composite of in-hospital death, unplanned reoperation, prolonged mechanical ventilation, new initiation of renal replacement therapy, and postoperative infection. Logistic regression (LR), extreme gradient boosting (XGB), and light gradient boosting machine (LGBM) models were developed using preoperative variables alone or with 7 additional intraoperative and early postoperative variables. Leave-one-facility-out internal-external cross-validation (IECV) was the primary validation framework, with a stratified random 80:20 hold-out analysis as secondary validation. Performance was assessed using the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (PR-AUC), Brier score, scaled Brier score, calibration measures, and decision curve analysis. Results: The primary composite outcome occurred in 3884 of 35,702 patients (10.9%). In pooled IECV, perioperative models consistently outperformed the corresponding preoperative models. AUROC increased from 0.784‐0.791 to 0.810‐0.817, PR-AUC increased from 0.356‐0.361 to 0.405‐0.413, Brier scores decreased from 0.082‐0.083 to 0.078‐0.080, and scaled Brier scores increased from 0.144‐0.151 to 0.175‐0.191. Calibration varied across facilities; pooled calibration slopes for the perioperative models ranged from 0.875 to 0.902, and calibration intercepts ranged from −0.367 to −0.222, indicating overly extreme predictions and overall risk overestimation. Exploratory decision curve analysis generally showed greater net benefit for perioperative models across threshold probabilities of 0.01‐0.30, although the curves overlapped substantially. Secondary and sensitivity analyses were consistent with the primary findings. Conclusions: Adding routinely available intraoperative and early postoperative variables produced modest but consistent improvements in postoperative risk prediction compared with preoperative variables alone. However, facility-specific variation in calibration limits direct transportability of absolute risk estimates. The models may support prioritization for postoperative clinical reassessment, but exploratory decision curve analysis did not establish a specific intervention or triage threshold. Local recalibration and prospective workflow evaluation are required before clinical implementation.

Introduction: Bone marrow carcinomatosis (BMC) is a rare manifestation of metastatic urothelial carcinoma (UC) that may mimic hematologic disease and cause severe cytopenia, diagnostic difficulty, and rapid clinical deterioration. Case Presentation: A 65‐year‐old man presented with back pain, thrombocytopenia, and leukoerythroblastosis. Bone marrow aspiration resulted in a dry tap, but biopsy revealed diffuse carcinoma‐cell infiltration consistent with UC, establishing BMC as the cause of marrow failure. Because of profound marrow dysfunction, reduced‐dose gemcitabine and cisplatin chemotherapy was initiated, leading to hematologic recovery and radiologic improvement. The patient subsequently received standard‐dose chemotherapy and avelumab maintenance and survived for 12.4 months after diagnosis. Conclusion: Histologic confirmation is essential to distinguish UC‐related BMC from primary hematologic disease and may support individualized systemic treatment in carefully selected patients.

OBJECTIVES: To determine whether early total bilirubin (T-Bil) trajectories during the first 72 hours after intubation identify trajectory-defined groups with distinct prognostic profiles associated with short-term mortality in mechanically ventilated ICU patients. DESIGN: Multicenter retrospective cohort study with a prespecified day 3 landmark design to mitigate immortal-time bias. SETTING: Mixed medical-surgical ICUs at four tertiary centers. PATIENTS: Adults receiving invasive mechanical ventilation who survived to the day 3 landmark and had serial T-Bil measurements on day 0 and day 3 (± 24 hr). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Patients were classified according to baseline T-Bil (≤ 1.2 vs. > 1.2 mg/dL) and the direction of change between day 0 and day 3 (change in T-Bil [ΔT-Bil]), yielding four trajectory-defined groups. The primary outcome was 30-day all-cause mortality after the day 3 landmark; 90-day mortality was secondary. Conditional survival was assessed using Kaplan-Meier methods with log-rank tests. Multivariable Cox models adjusted for prespecified covariates available by day 3 (age, sex, body mass index, intubating department, baseline mean arterial pressure, log-transformed aspartate aminotransferase/alanine aminotransferase ratio and platelet count, creatinine, renal replacement therapy, and vasoactive support). Rising T-Bil trajectories were independently associated with higher 30-day mortality, with the strongest association among patients with normal baseline T-Bil who exhibited early increases. In contrast, elevated baseline T-Bil followed by early decline was not associated with excess risk. Findings were consistent in complete-case analyses, in models incorporating day 3 partial Sequential Organ Failure Assessment for severity adjustment, and in analyses of 90-day mortality. Restricted cubic spline analyses demonstrated a nonlinear dose-response relationship between ΔT-Bil and mortality. CONCLUSIONS: Early T-Bil dynamics within 72 hours after intubation were associated with distinct prognostic profiles beyond baseline bilirubin levels and may provide a pragmatic marker for early risk stratification in mechanically ventilated ICU patients.

Introduction: The combination of enzalutamide and radium‐223 has demonstrated clinical efficacy in metastatic castration‐resistant prostate cancer; however, real‐world evidence remains limited, particularly with PSA–discordant progression. Case Presentation: A 74‐year‐old man with high‐risk localized prostate cancer was treated with androgen deprivation therapy followed by definitive external beam radiotherapy. Eight months later, the disease progressed radiographically with extensive bone, nodal, and solitary liver metastases, while prostate‐specific antigen levels remained persistently low, consistent with prostate‐specific antigen–discordant progression. Bone turnover markers and disease activity markers were markedly elevated. Combination therapy with enzalutamide and radium‐223 was initiated, and six cycles of radium‐223 were completed. Following treatment, skeletal disease activity and bone turnover markers improved markedly. Apart from grade 3 anemia requiring transfusion, no severe adverse events occurred. Conclusion: This case suggests that enzalutamide combined with radium‐223 may provide clinical benefit in metastatic castration‐resistant prostate cancer with PSA–discordant progression.

Background: Falls among hospitalized patients are a critical issue that often leads to prolonged hospital stays and increased health care costs. Traditional fall risk assessments typically rely on standardized scoring systems; however, these may fail to capture the complex and multifactorial nature of fall risk factors. Objective: This retrospective observational multicenter study aimed to develop and validate a machine learning–based model to predict in-hospital falls and to evaluate its performance in terms of discrimination and calibration. Methods: We analyzed the data of 83,917 inpatients aged 65 years and older with a hospital stay of at least 3 days. Using Diagnosis Procedure Combination data and laboratory results, we extracted demographic, clinical, functional, and pharmacological variables. Following the selection of 30 key features, 4 predictive models were constructed: logistic regression, extreme gradient boosting, light gradient boosting machine (LGBM), and categorical boosting (CatBoost). The synthetic minority oversampling technique and isotonic regression calibration were applied to improve the prediction quality and address class imbalance. Results: Falls occurred in 2173 (2.6%) patients. CatBoost achieved the highest F1-score (0.189, 95% CI 0.162-0.215) and area under the precision-recall curve (0.112, 95% CI 0.091-0.136), whereas LGBM had the best calibration slope (0.964, 95% CI 0.858-1.070) with good discrimination (F1-score 0.182, 95% CI 0.156-0.209; area under the precision-recall curve 0.094, 95% CI 0.078-0.113). Logistic regression had the lowest discrimination (F1-score 0.120, 95% CI 0.100-0.143). Shapley Additive Explanations analysis consistently identified low albumin, impaired transfer ability, and the use of sedative-hypnotics or diabetes medications as major contributors to fall risk. In incident report analysis (n=435), 49.2% of falls were toileting-related, peaking between 4 and 6 AM, with bedside falls predominating in high or very high risk groups. Conclusions: CatBoost and LGBM offer clinically valuable prediction performance, with CatBoost favored for high-risk patient identification and LGBM for probability-based intervention thresholds. Integrating such models into electronic health records could enable real-time risk scoring and trigger targeted interventions (eg, toileting assistance and mobility support). Future work should incorporate dynamic, time-varying patient data to improve real-time risk prediction.

Background/Objectives: The Vesical Imaging-Reporting and Data System (VI-RADS) provides high diagnostic accuracy for muscle-invasive bladder cancer; however, its prognostic value remains limited. We propose serum cytokeratin 19 fragment (CYFRA 21-1) and tumor contact length (TCL) as complementary prognostic factors. We aimed to construct a composite risk score integrating VI-RADS, CYFRA 21-1, and TCL for prognostic stratification. Methods: We retrospectively analyzed data from 101 patients with bladder cancer (BC) who underwent transurethral resection of bladder tumor (TURBT), magnetic resonance imaging, and postoperative serum CYFRA 21-1 measurement. For each factor, cut-off values were determined using receiver operating characteristic (ROC) analysis; meeting each threshold contributed one point (score range, 0–3). Overall survival (OS) was assessed using Kaplan–Meier and Cox regression analyses. Results: ROC analysis identified cut-offs of VI-RADS ≥ 3 (area under the curve [AUC] 0.779), TCL ≥ 40 mm (AUC 0.817), and CYFRA 21-1 ≥ 2.1 ng/mL (AUC 0.875). Based on these, patients were stratified into low- (0–1, n = 81), intermediate- (2, n = 12), and high-risk (3, n = 8) groups with 3-year OS rates of 95.1%, 75.0%, and 25.0%, respectively (p < 0.001). In univariate Cox regression, all factors significantly predicted poor OS: VI-RADS ≥ 3 (hazard ratio [HR], 6.51; p = 0.015), TCL ≥ 40 mm (HR, 8.36; p < 0.001), and CYFRA 21-1 ≥ 2.1 ng/mL (HR, 14.02; p < 0.001). In multivariate analysis, only CYFRA 21-1 remained independently significant (HR, 11.80; p < 0.001). Conclusions: A composite risk score combining VI-RADS, TCL, and CYFRA 21-1 effectively stratified patients with BC into distinct groups using minimally invasive, peri-TURBT assessments. Prospective multicenter validation is warranted.

We investigated the clinical significance of positive surgical margins (PSMs) in index tumors following radical prostatectomy (RP), with particular attention to the tumor’s zonal origin. Among 1148 patients with localized prostate cancer who underwent RPs, 973 were included after excluding those who received perioperative therapy or had incomplete data. Index tumors were categorized by zonal origin: transition zone, peripheral zone, or central zone (CZ). Overall, PSMs were observed in 26.4% of index tumors. Although CZ index tumors were relatively uncommon (6.5%), they exhibited the highest PSM rate (42.9%) and showed the most aggressive pathological features. The 5-year biochemical recurrence (BCR)-free survival rate was significantly lower in patients with PSMs in index tumors than in those with negative surgical margins (45.6% vs. 86.8%, p < 0.0001). Notably, patients with PSMs in CZ index tumors had the worst outcomes, with a 5-year BCR-free survival rate of 22.0%. Multivariate analysis identified PSMs in index tumors as an independent predictor of BCR (HR: 3.4; 95% CI: 2.5–4.5), with a similar trend observed in early recurrence. These findings highlight the prognostic significance of PSMs in index tumors during RP, especially in CZ tumors, and emphasize the importance of securing local control in these cases.

The Vesical Imaging Reporting and Data System (VI-RADS) is used to detect muscle-invasive bladder cancer, with emerging prognostic implications. Integrating imaging parameters with molecular biomarkers may improve risk stratification in bladder cancer. This study evaluated whether combining VI-RADS scores with serum cytokeratin fragment 19 (CYFRA 21-1) levels—a clinically relevant biomarker for bladder cancer—could improve overall survival (OS) prediction. We retrospectively analyzed 134 patients who underwent transurethral resection of bladder tumors, magnetic resonance imaging, and postoperative serum CYFRA 21-1 measurements. In total, 15 cancer-specific deaths were observed during follow-up. Receiver operating characteristic curve analysis identified optimal prognostic cut-off values: VI-RADS score ≥ 4 and CYFRA 21-1 level ≥ 1.8 ng/mL. The 1-, 2-, and 3-year OS in patients with both high VI-RADS scores and CYFRA 21-1 levels were 42.9%, 16.7%, and 8.3%, respectively, significantly lower than those in other groups (p < 0.001, 0.002, and 0.003, respectively). Multivariate Cox proportional hazards analysis demonstrated that such patients had the poorest OS (hazard ratio: 7.51; p = 0.002). This suggests that combining VI-RADS and CYFRA 21-1 improves prognostic accuracy in bladder cancer, demonstrating potential clinical utility by informing individualized treatment strategies; however, limitations include the retrospective study design and absence of external validation.

Background: We investigated the clinical and economic outcomes of robot‐assisted radical prostatectomy (RARP) using the hinotori surgical system (H‐RARP).Methods: The analysis was conducted on 76 and 68 patients who underwent RARP using the da Vinci surgical system (D‐RARP) and H‐RARP, respectively. Safety, oncological, and functional outcomes were compared between H‐RARP and D‐RARP. Risk factors influencing medical costs in RARP were identified via linear regression analysis.Results: Except for longer operative time in H‐RARP, clinical outcomes were comparable. The median medical costs per case were $12,426.8 for D‐RARP and $12,548.9 for H‐RARP. Operative time (coefficient: 0.0002, p < 0.001), pathological T stage (coefficient: 0.023, p = 0.030), and postoperative hospital stay (coefficient: 0.028, p < 0.001) were significant factors affecting medical costs; in contrast, the type of robot‐assisted surgical system was not a significant factor.Conclusions: H‐RARP offers clinical outcomes comparable to those of D‐RARP while maintaining equivalent medical costs.

BACKGROUND Falls among hospitalized patients are a critical issue that often leads to prolonged hospital stays and increased health care costs. Traditional fall risk assessments typically rely on standardized scoring systems; however, these may fail to capture the complex and multifactorial nature of fall risk factors. OBJECTIVE This retrospective observational multicenter study aimed to develop and validate a machine learning–based model to predict in-hospital falls and to evaluate its performance in terms of discrimination and calibration. METHODS We analyzed the data of 83,917 inpatients aged 65 years and older with a hospital stay of at least 3 days. Using Diagnosis Procedure Combination data and laboratory results, we extracted demographic, clinical, functional, and pharmacological variables. Following the selection of 30 key features, 4 predictive models were constructed: logistic regression, extreme gradient boosting, light gradient boosting machine (LGBM), and categorical boosting (CatBoost). The synthetic minority oversampling technique and isotonic regression calibration were applied to improve the prediction quality and address class imbalance. RESULTS Falls occurred in 2173 (2.6%) patients. CatBoost achieved the highest F1-score (0.189, 95% CI 0.162-0.215) and area under the precision-recall curve (0.112, 95% CI 0.091-0.136), whereas LGBM had the best calibration slope (0.964, 95% CI 0.858-1.070) with good discrimination (F1-score 0.182, 95% CI 0.156-0.209; area under the precision-recall curve 0.094, 95% CI 0.078-0.113). Logistic regression had the lowest discrimination (F1-score 0.120, 95% CI 0.100-0.143). Shapley Additive Explanations analysis consistently identified low albumin, impaired transfer ability, and the use of sedative-hypnotics or diabetes medications as major contributors to fall risk. In incident report analysis (n=435), 49.2% of falls were toileting-related, peaking between 4 and 6 AM, with bedside falls predominating in high or very high risk groups. CONCLUSIONS CatBoost and LGBM offer clinically valuable prediction performance, with CatBoost favored for high-risk patient identification and LGBM for probability-based intervention thresholds. Integrating such models into electronic health records could enable real-time risk scoring and trigger targeted interventions (eg, toileting assistance and mobility support). Future work should incorporate dynamic, time-varying patient data to improve real-time risk prediction.