Artificial intelligence clinical trials and critical appraisal: a necessity

Self Cite

BackgroundThis study aimed to examine the performance of machine learning algorithms for the prediction of discharge within 12 and 24 h to produce a measure of readiness for discharge after general surgery.MethodsConsecutive general surgery patients at two tertiary hospitals, over a 2‐year period, were included. Observation and laboratory parameter data were stratified into training, testing and validation datasets. Random forest, XGBoost and logistic regression models were evaluated. Each ward round note time was taken as a different event. Primary outcome was classification accuracy of the algorithmic model able to predict discharge within the next 12 h on the validation data set.Results42 572 ward round note timings were included from 8826 general surgery patients. Discharge occurred within 12 h for 8800 times (20.7%), and within 24 h for 9885 (23.2%). For predicting discharge within 12 h, model classification accuracies for derivation and validation data sets were: 0.84 and 0.85 random forest, 0.84 and 0.83 XGBoost, 0.80 and 0.81 logistic regression. For predicting discharge within 24 h, model classification accuracies for derivation and validation data sets were: 0.83 and 0.84 random forest, 0.82 and 0.81 XGBoost, 0.78 and 0.79 logistic regression. Algorithms generated a continuous number between 0 and 1 (or 0 and 100), representing readiness for discharge after general surgery.ConclusionsA derived artificial intelligence measure (the Adelaide Score) successfully predicts discharge within the next 12 and 24 h in general surgery patients. This may be useful for both treating teams and allied health staff within surgical systems.

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

The Adelaide Score: An artificial intelligence measure of readiness for discharge after general surgery

Kovoor

Bacchi

Gupta

et al. 2023

Self Cite

“…34 More advanced technology is emerging, and is largely unexplored as an adjunct for prehabilitation interventions. The most notable example is artificial intelligence, which is already demonstrating potential benefits for surgical systems, 66 in particular those for general surgery. [67][68][69] For prehabilitation interventions specifically, artificial intelligence could assist with intervention personalisation according to patient characteristics and preferences, enhancement of information provision and experience for potentially improved adherence, 70 predictive metrics to allow for early modulation of interventions when required, 71 and decision aids 72 for both clinicians and patients.…”

Section: Discussionmentioning

confidence: 99%

Prehabilitation for general surgery: a systematic review of randomized controlled trials

Kovoor,

Nann,

Barot

et al. 2023

Self Cite

BackgroundPrehabilitation seeks to optimize patient health before surgery to improve outcomes. Randomized controlled trials (RCTs) have been conducted on prehabilitation, however an updated synthesis of this evidence is required across General Surgery to inform potential Supplementary discipline‐level protocols. Accordingly, this systematic review of RCTs aimed to evaluate the use of prehabilitation interventions across the discipline of General Surgery.MethodsThis study was registered with PROSPERO (CRD42023403289), and adhered to PRISMA 2020 and SWiM guidelines. PubMed/MEDLINE and Ovid Embase were searched to 4 March 2023 for RCTs evaluating prehabilitation interventions within the discipline of General Surgery. After data extraction, risk of bias was assessed using the Cochrane RoB 2 tool. Quantitative and qualitative data were synthesized and analysed. However, meta‐analysis was precluded due to heterogeneity across included studies.ResultsFrom 929 records, 36 RCTs of mostly low risk of bias were included. 17 (47.2%) were from Europe, and 14 (38.9%) North America. 30 (83.3%) investigated cancer populations. 31 (86.1%) investigated physical interventions, finding no significant difference in 16 (51.6%) and significant improvement in 14 (45.2%). Nine (25%) investigated psychological interventions: six (66.7%) found significant improvement, three (33.3%) found no significant difference. Five (13.9%) investigated nutritional interventions, finding no significant difference in three (60%), and significant improvement in two (40%).ConclusionsPrehabilitation interventions showed mixed levels of effectiveness, and there is insufficient RCT evidence to suggest system‐level delivery across General Surgery within standardized protocols. However, given potential benefits and non‐inferiority to standard care, they should be considered on a case‐by‐case basis.

“…For all patient populations, but particularly those that are disadvantaged at baseline, undergoing a formal interventional procedure, be it surgical or non‐surgical, can present a traumatic biopsychosocial disruption to the patient's life especially if the post‐procedure outcome is poor 7 . When evaluating surgical recovery, patient, surgical, system, and societal factors must be considered 8 . Although modern procedural healthcare systems provide individualized, patient‐centred care, the ability to predict and prevent suboptimal post‐procedural outcomes based on patient demographics at admission may potentially improve health equity.…”

Section: Introductionmentioning

confidence: 99%

Achieving equity: patient demographics and outcomes after surgical and non‐surgical procedures in South Australia, 2022

Kovoor,

Gupta,

Bacchi

et al. 2024

BackgroundAlthough modern Australian healthcare systems provide patient‐centred care, the ability to predict and prevent suboptimal post‐procedural outcomes based on patient demographics at admission may improve health equity. This study aimed to identify patient demographic characteristics that might predict disparities in mortality, readmission, and discharge outcomes after either an operative or non‐operative procedural hospital admission.MethodsThis retrospective cohort study included all surgical and non‐surgical procedural admissions at three of the four major metropolitan public hospitals in South Australia in 2022. Multivariable logistic regression, with backwards selection, evaluated association between patient demographic characteristics and outcomes up to 90 days post‐procedurally.Results40 882 admissions were included. Increased likelihood of all‐cause, post‐procedure mortality in‐hospital, at 30 days, and 90 days, were significantly associated with increased age (P < 0.001), increased comorbidity burden (P < 0.001), an emergency admission (P < 0.001), and male sex (P = 0.046, P = 0.03, P < 0.001, respectively). Identification as ATSI (P < 0.001) and being born in Australia (P = 0.03, P = 0.001, respectively) were associated with an increased likelihood of 30‐day hospital readmission and decreased likelihood of discharge directly home, as was increased comorbidity burden (P < 0.001) and emergency admission (P < 0.001). Being married (P < 0.001) and male sex (P = 0.003) were predictive of an increased likelihood of discharging directly home; in contrast to increased age (P < 0.001) which was predictive of decreased likelihood of this occurring.ConclusionsThis study characterized several associations between patient demographic factors present on admission and outcomes after surgical and non‐surgical procedures, that can be integrated within patient flow pathways through the Australian healthcare system to improve healthcare equity.