Background/Objectives: Febrile neutropenia (FN) in hematologic malignancies carries a high risk of sepsis. We developed a regression model and a simplified nurse-led sepsis risk score using artificial intelligence (AI)-enabled remote patient monitoring (RPM) measurements and routine clinical and laboratory variables. Methods: A nested case–control study included 120 adult FN episodes (40 Sepsis-3-defined cases within 14 days of FN onset; 80 matched controls) in a hematology/bone marrow transplantation unit (BMT) in India (December 2021–December 2024). Heart rate and respiratory rate were obtained by ballistocardiography; blood pressure (BP), peripheral oxygen saturation (SpO₂), and temperature were obtained using connected probes. Only a single set of FN-onset measurements was analyzed; longitudinal RPM trends and platform-generated alerts were excluded. Conditional logistic regression identified independent predictors and supplied coefficients for an integer-weighted score. Regression-model validation used two 1000-resample bootstrap analyses: one holding cut-offs and predictors fixed, the other repeating cut-off determination and backward selection. Integer-score discrimination was assessed separately. Results: Six predictors—tachycardia, hypotension, ≥2 comorbidities, absolute neutrophil count <99.5 cells/μL, chills, and elevated procalcitonin—formed an 8-point score. The regression model area under the receiver operating characteristic curve (AUC) was 0.847, with fixed-specification optimism of 0.028 and a corrected AUC of 0.819. Repeating cut-off determination and predictor selection yielded an apparent AUC of 0.855, optimism of 0.036, and corrected AUC of 0.819. The integer-score apparent AUC was 0.654 (95% CI 0.567–0.740), without optimism correction. Conclusions: Regression-model discrimination remained similar after accounting for cut-off determination and predictor selection. Integer-score performance remains uncorrected for optimism and requires independent temporal validation before clinical use. RPM’s AI functions and continuous-monitoring benefits were not evaluated. Temporal validation is planned in Phase II. Trial registration: Clinical Trials Registry of India (CTRI/2025/06/088290).

Background: Thirty-day unplanned readmission following coronary artery bypass grafting (CABG) affects 10%-20% of patients and is a key quality indicator, particularly in low- and middle-income countries (LMICs) where access to cardiac rehabilitation is limited. Existing risk models are static, lack real-time engagement, and no validated large language model (LLM)–based clinical decision support (CDS) system exists for post-CABG readmission prevention. Objective: This protocol describes the development, validation, and evaluation of Smart CABGuard, a nurse-led, LLM-based CDS chatbot with continuous remote electrocardiographic (ECG) monitoring, to predict and prevent postoperative complications, and 30-day unplanned readmission after isolated CABG. Methods: This multiphase translational study is conducted at Amrita Institute of Medical Sciences, Kochi, India, following TRIPOD-LLM (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis–Large Language Model) and CONSORT (Consolidated Standards of Reporting Trials) AI reporting guidelines. Phase I uses an ambispective design (retrospective: January 2020 to December 2024; prospective needs survey: June 2025 to January 2026) to develop a logistic regression-based Complication Risk Index (CRI), assessed via receiver operating characteristic area under the curve, Brier score, and decision curve analysis. Phase II refines Smart CABGuard by integrating a frozen Mistral-7B LLM (low-rank adaptation fine-tuned), the CRI engine, explainable AI, and single-lead ECG telemetry (Amrita Spandanam device), with a usability threshold of ≥80%. Phase III is a prospective, parallel-group, open-label randomized controlled trial (RCT). Adults aged ≥18 years undergoing isolated CABG with smartphone access are randomized 1:1 via permuted block randomization, with allocation concealment. The intervention arm receives Smart CABGuard–assisted care (daily chatbot check-ins, CRI-based risk stratification, ECG monitoring, and nurse-led triage) for approximately 24 days postdischarge plus standard care; the control arm receives standard care with structured telephone follow-up for outcome ascertainment only. Outcome assessors and statisticians are blinded; analyses follow the intention-to-treat principle. The primary outcome is 30-day all-cause unplanned readmission. Based on a baseline rate of 10.71%, a 50% relative reduction, α=.10, and 80% power, the target sample size is 800 patients (400 per arm, including 10% attrition). Results: Ethics approval was granted by the Institutional Ethics Committee of Amrita Institute of Medical Sciences on April 16, 2025. Funding was awarded by Sigma Theta Tau International Honor Society of Nursing, Small Grants Program (grant 21650) in June 2025. Phase I data extraction commenced in May 2025 and is projected to be completed by April 2026; the patient needs survey (June 2025 to January 2026) is ongoing. Phase II usability evaluation is projected from May to July 2026. Phase III recruitment is anticipated from August 2026 to September 2027. Results are expected to be published in early 2028. Conclusions: Smart CABGuard is the first RCT protocol of an LLM-based nurse-led CDS system for post-CABG readmission prevention in an LMIC setting, aiming to establish the usefulness, safety, and feasibility of AI-augmented postoperative surveillance.

Background: Febrile neutropenia (FN) is a common and potentially life-threatening complication in immunocompromised patients, particularly those undergoing hematopoietic stem cell transplantation (HSCT). Timely identification and intervention are essential to prevent progression to sepsis or multi-organ dysfunction. While conventional monitoring relies on intermittent vital sign assessment, artificial intelligence (AI)-driven remote patient monitoring (RPM) offers a promising adjunct to enhance early detection and clinical decision-making. Case Insight: We present a case involving a young adult female post-HSCT who was monitored using an AI-enabled RPM system. Over a 29-day post-transplant period, the system generated real-time alerts indicating clinical deterioration, including febrile episodes, hypotension, tachycardia, and respiratory distress. These alerts were substantiated by clinical and diagnostic evaluations, leading to prompt escalation of antibiotics and supportive care. The AI system’s continuous surveillance and predictive capability enabled earlier recognition of complications, even when standard bedside monitoring showed minimal change. Conclusion: This paper highlights the potential use of AI-integrated RPM systems to transform the management of FN by enabling earlier intervention especially in high-risk immunocompromised patients. Although the preliminary observations are promising, further prospective studies are certainly required to evaluate and assess the accuracy, clinical outcomes, and resource implications of integration of AI into routine critical care monitoring protocols.

Background This comprehensive review consolidates existing research about postoperative outcomes after coronary artery bypass grafting (CABG), a prevalent yet high-risk cardiac procedure. Notwithstanding improvements in surgical methods and perioperative management, CABG patients often encounter multisystem problems, including cardiac arrhythmias, pulmonary dysfunction, renal impairment, neurological impairments, and infections. These problems correlate with extended hospitalizations, elevated readmission rates, and increased healthcare expenditures. Materials and Methods A thorough literature search was performed in the Cochrane Library, MEDLINE, EMBASE, and CINAHL databases in accordance with PRISMA-ScR criteria and the Arksey and O’Malley methodological approach. Studies comprising adult CABG patients with follow-up durations of up to six months were incorporated. Data extraction concentrated on complication profiles, detection timeframes, hospital stay duration, and recovery metrics. Results Narrative synthesis indicated a significant correlation between the early identification of problems and decreased hospital durations. The review highlighted significant deficiencies in the current literature, including inconsistencies in monitoring techniques, insufficient focus on long-term outcomes, and inadequate representation of older and female patients. Conclusion Recent evidence indicates that artificial intelligence-based monitoring systems could improve early intervention and recovery. This analysis highlights the necessity for standardized postoperative care protocols and additional research into long-term recovery, quality of life, and cost-effective surveillance measures to enhance CABG results.

Background: Adults with hematological malignancies who develop febrile neutropenia (FN) face elevated risks of sepsis, intensive care admission, and treatment interruptions. Early sepsis detection is challenging, as classical clinical signs are often attenuated or delayed in this population. Current risk stratification tools demonstrate limitations when applied to adults with FN. A tailored, nurse-led scoring system integrating clinical, laboratory, and physiological predictors may enhance early sepsis identification. Objective: This 2-phase study aims to develop and internally validate a nurse-led sepsis risk score for adults with FN in phase I and to temporally validate its performance in phase II. The new score will be compared to the MASCC risk index, CISNE, NEWS2_ and qSOFA at FN onset . The secondary objectives include evaluating associations between risk groups and remote patient monitoring alerts within 24 hours of FN onset, interrater agreement, and bedside feasibility. Methods: The study is being conducted in the hematology and bone marrow transplantation department of a tertiary care hospital in Bengaluru, India. Phase I uses a nested matched case-control design within a retrospective cohort of approximately 140 patients with FN. We will analyze clinical, laboratory, and physiological predictors measured at FN onset using multivariable conditional logistic regression, with internal validation via bootstrapping. In Phase II, which utilizes a prospective temporal validation cohort, bedside nurses will calculate the proposed score at FN onset alongside the MASCC, CISNE, NEWS2, and qSOFA scores A substudy will include additional nurses scoring independently to assess interrater agreement and feasibility. Two blinded reviewers will adjudicate phase I outcomes within 14 days of FN onset, while assessors blinded to all scores will adjudicate phase II outcomes within the same time frame. The primary outcome is sepsis within 14 days of FN onset. Phase II evaluates discrimination, calibration, and comparative diagnostic performance. Results: We obtained ethics approval in April 2025, and the study was registered in June 2025 (CTRI/2025/06/088290). The initial phase I derivation was completed in November 2025, using sepsis within 14 days of FN onset as the primary outcome. A protocol amendment in September 2026 harmonized the outcome window to 14 days, prompting rederivation of the model and superseding the initial analysis. Phase II commenced in December 2025. As of September 2026, enrollment and data collection were ongoing, with study completion anticipated in December 2026. Main results are expected in 2027. Conclusions: This protocol evaluates an FN-specific, nurse-led sepsis score integrating clinical and laboratory predictors with contactless physiological measurements. We will examine remote patient monitoring alerts as secondary markers of clinical instability. Validation findings will establish the score’s predictive performance and inform future implementation studies.