Predicting Patient-Reported Outcomes Following Surgery Using Machine Learning

Hassan, Abbas M.; Biaggi-Ondina, Andrea; Rajesh, Aashish; Asaad, Malke; Nelson, Jonas A.; Coert, J. Henk; Mehrara, Babak J.; Butler, Charles E.

doi:10.1177/00031348221109478

Cited by 8 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"Prediction and risk strati cation" of disease was the second theme that was extracted from studies on AI applications in decision-making. Disease prediction and risk strati cation, forecast of disease occurrence, prediction of infectious diseases, prediction of aging-related diseases, prediction of disease risk for anomaly detection, prediction of mortality risk, prediction of future events, prediction of the spread of disease, and predictive models for diseases are some AI applications in disease prediction and their risk strati cation (29)(30)(31)(32)(33)(34)(35)(36)(37)(38)(39)(40)(41)(42). Therefore, AI has considerable capacity in disease prediction and risk strati cation that should be considered in para clinical centers.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence Applications in Decision Making for Disease Management

Abdekhoda

Ranjbaran

2023

Preprint

View full text Add to dashboard Cite

Background: Artificial intelligence (AI) has several potential applications in medicine, creating opportunities for reliable and evidence based decision making in disease management. Thus, the practical aspects of AI in decision-making should be identified. This study was conducted to identify AI applications in decision making for disease management. Method: This study was a systematic review using the PRISMA-ScR checklist. Data collection was carried out by searching the related keywords in WOS and Scopus in May 2023. Results: Regarding the AI applications in decision making for disease management, we found 80 sub-themes which were categorized into six themes, i.e. 1) Processing and managing data, 2) Characterization and analysis, 3) Prediction and risk stratification, 4) Screening, 5) Prognosis, and 6) Diagnosis. Conclusion: AI has considerable capability in disease treatment and would be an integral part of medicine in the future. This study clearly identified six main themes that addressed AI capability in decision making for disease management. The use of AI can help in making medical decisions with more trust and confidence and thus make medical interventions more accurate and effective.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence Applications in Decision Making for Disease Management

Abdekhoda

Ranjbaran

2023

Preprint

View full text Add to dashboard Cite

show abstract

Risk-Specific Training Cohorts to Address Class Imbalance in Surgical Risk Prediction

Balch,

Ruppert,

Guan

et al. 2024

JAMA Surg

View full text Add to dashboard Cite

ImportanceMachine learning tools are increasingly deployed for risk prediction and clinical decision support in surgery. Class imbalance adversely impacts predictive performance, especially for low-incidence complications.ObjectiveTo evaluate risk-prediction model performance when trained on risk-specific cohorts.Design, Setting, and ParticipantsThis cross-sectional study performed from February 2024 to July 2024 deployed a deep learning model, which generated risk scores for common postoperative complications. A total of 109 445 inpatient operations performed at 2 University of Florida Health hospitals from June 1, 2014, to May 5, 2021 were examined.ExposuresThe model was trained de novo on separate cohorts for high-risk, medium-risk, and low-risk Common Procedure Terminology codes defined empirically by incidence of 5 postoperative complications: (1) in-hospital mortality; (2) prolonged intensive care unit (ICU) stay (≥48 hours); (3) prolonged mechanical ventilation (≥48 hours); (4) sepsis; and (5) acute kidney injury (AKI). Low-risk and high-risk cutoffs for complications were defined by the lower-third and upper-third prevalence in the dataset, except for mortality, cutoffs for which were set at 1% or less and greater than 3%, respectively.Main Outcomes and MeasuresModel performance metrics were assessed for each risk-specific cohort alongside the baseline model. Metrics included area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), F1 scores, and accuracy for each model.ResultsA total of 109 445 inpatient operations were examined among patients treated at 2 University of Florida Health hospitals in Gainesville (77 921 procedures [71.2%]) and Jacksonville (31 524 procedures [28.8%]). Median (IQR) patient age was 58 (43-68) years, and median (IQR) Charlson Comorbidity Index score was 2 (0-4). Among 109 445 operations, 55 646 patients were male (50.8%), and 66 495 patients (60.8%) underwent a nonemergent, inpatient operation. Training on the high-risk cohort had variable impact on AUROC, but significantly improved AUPRC (as assessed by nonoverlapping 95% confidence intervals) for predicting mortality (0.53; 95% CI, 0.43-0.64), AKI (0.61; 95% CI, 0.58-0.65), and prolonged ICU stay (0.91; 95% CI, 0.89-0.92). It also significantly improved F1 score for mortality (0.42; 95% CI, 0.36-0.49), prolonged mechanical ventilation (0.55; 95% CI, 0.52-0.58), sepsis (0.46; 95% CI, 0.43-0.49), and AKI (0.57; 95% CI, 0.54-0.59). After controlling for baseline model performance on high-risk cohorts, AUPRC increased significantly for in-hospital mortality only (0.53; 95% CI, 0.42-0.65 vs 0.29; 95% CI, 0.21-0.40).Conclusion and RelevanceIn this cross-sectional study, by training separate models using a priori knowledge for procedure-specific risk classes, improved performance in standard evaluation metrics was observed, especially for low-prevalence complications like in-hospital mortality. Used cautiously, this approach may represent an optimal training strategy for surgical risk-prediction models.

show abstract

Artificial Intelligence, Deep Learning, and Machine Learning Applications in Total Knee Arthroplasty

Sosa

2023

Total Knee Arthroplasty

View full text Add to dashboard Cite

Predicting Patient-Reported Outcomes Following Surgery Using Machine Learning

Cited by 8 publications

References 23 publications

Artificial Intelligence Applications in Decision Making for Disease Management

Artificial Intelligence Applications in Decision Making for Disease Management

Risk-Specific Training Cohorts to Address Class Imbalance in Surgical Risk Prediction

Artificial Intelligence, Deep Learning, and Machine Learning Applications in Total Knee Arthroplasty

Contact Info

Product

Resources

About