Machine Learning-Based Risk Prediction of Critical Care Unit Admission for Advanced Stage High Grade Serous Ovarian Cancer Patients Undergoing Cytoreductive Surgery: The Leeds-Natal Score

Abstract

Achieving complete surgical cytoreduction in advanced stage high grade serous ovarian cancer (HGSOC) patients warrants an availability of Critical Care Unit (CCU) beds. Machine Learning (ML) could be helpful in monitoring CCU admissions to improve standards of care. We aimed to improve the accuracy of predicting CCU admission in HGSOC patients by ML algorithms and developed an ML-based predictive score. A cohort of 291 advanced stage HGSOC patients with fully curated data was selected. Several linear and non-linear distances, and quadratic discriminant ML methods, were employed to derive prediction information for CCU admission. When all the variables were included in the model, the prediction accuracies were higher for linear discriminant (0.90) and quadratic discriminant (0.93) methods compared with conventional logistic regression (0.84). Feature selection identified pre-treatment albumin, surgical complexity score, estimated blood loss, operative time, and bowel resection with stoma as the most significant prediction features. The real-time prediction accuracy of the Graphical User Interface CCU calculator reached 95%. Limited, potentially modifiable, mostly intra-operative factors contributing to CCU admission were identified and suggest areas for targeted interventions. The accurate quantification of CCU admission patterns is critical information when counseling patients about peri-operative risks related to their cytoreductive surgery.

Stratification of Length of Stay Prediction following Surgical Cytoreduction in Advanced High-Grade Serous Ovarian Cancer Patients Using Artificial Intelligence; the Leeds L-AI-OS Score

“…Descriptive cohort statistics are shown in Table 2 . The cohort has been previously described [ 27 ]. A total of 201 (two samples removed) samples and 84 samples (three samples were removed from the calibration and post-hoc test sets, respectively) were used for the analysis.…”

“…Our study also shows that over the four-year period, the overall median LOS has significantly reduced. This was partly due to the increased proportion of patients experiencing ideal LOS, which was promoted as a good care measure following the introduction of the ERAS pathway in our institution [ 27 ]. Implementation of ERAS pathways for advanced-stage EOC results in a shorter LOS due to earlier recovery and a lower rate of readmission, with no increase in morbidity or mortality [ 3 ].…”

“…Unlike other algorithms, BPN controls errors by resubmitting flawed solutions to the initial neurons, allowing the backpropagation method to improve in the next iteration. These ML/DL paradigms have been comprehensively described in our previous work [ 27 ]. Clinicians are mostly familiar with regressions, odds ratios, and hazard ratios.…”

Factors Predicting Surgical Effort Using Explainable Artificial Intelligence in Advanced Stage Epithelial Ovarian Cancer

“…The Society guidelines for the peri-operative care of gynaecological oncology patients have been released and recently updated [ 26 ]. Post-operative critical care unit (CCU) admission was electively booked for high-risk EOC [ 27 ], who were scheduled to undergo complex major surgery, including multi-visceral resections, or undertook pre-operative cardiopulmonary exercise (CPEX) fitness testing if they were deemed high risk at pre-assessment.…”

Beauty is in the explainable artificial intelligence (XAI) of the “agnostic” beholder

“…Understanding the EOC trajectory requires a vast amount of information, to be handled by different computational approaches, well beyond the capacity of traditional statistics. We have meticulously evaluated the clinical applications of AI models in the surgical outcomes related to EOC to determine areas of future research (8)(9)(10). The application of such AIempowered approaches in the field of EOC holds the potential of upgrading the approach to patient-oriented decision-making (11).…”