Abstract
Simple SummaryStructured survey on the predictive analysis of postoperative complications in oncology, bridging classic risk scores with machine learning advances, and further establishing principles to guide the design of cohort studies and the predictive modeling of postsurgical risks.Postoperative complications can impose a significant burden, increasing morbidity, mortality, and the in-hospital length of stay. Today, the number of studies available on the prognostication of postsurgical complications in cancer patients is growing and has already created a considerable set of dispersed contributions. This work provides a comprehensive survey on postoperative risk analysis, integrating principles from classic risk scores and machine-learning approaches within a coherent frame. A qualitative comparison is offered, taking into consideration the available cohort data and the targeted postsurgical outcomes of morbidity (such as the occurrence, nature or severity of postsurgical complications and hospitalization needs) and mortality. This work further establishes a taxonomy to assess the adequacy of cohort studies and guide the development and assessment of new learning approaches for the study and prediction of postoperative complications.
Highlights
Cancer is among the leading causes of death of the 21st century
We first establish a taxonomy to guide the design of cohort studies and the development and assessment of new learning approaches for predicting postoperative complications. Contextualized by this taxonomy, this paper provides a comprehensive survey of classical approaches and machine learning (ML) advances for postsurgical risk analysis
Danjuma [48] used Decision trees (DT) to predict mortality within 1 year from surgery. The results shown their efficacy for the targeted ends, with the efficacy only slightly surpassed by artificial neural networks
Summary
Cancer is among the leading causes of death of the 21st century. In the United States, as of 2020, the number of new cases of cancer was estimated to surpass 1,800,000 and deaths due to cancer were close to 600,000. With advances on the technology and health data analysis, an increasing amount of studies identify the main factors propelling postoperative complications and, considering these factors, propose new risk tools, or recalibrate existing ones [5] In this context, medical professionals are assisted when deciding whether a surgery is viable for a patient, while patients can more manage expectations associated with potentially high-risk surgeries. ASAPS is a point system with various parameters whose evaluation is not standardized, is associated with high variability among similar users Despite these criticisms, ASA-PS is Cancers 2021, 13, 3217 still used today since studies suggest that its result roughly transduce the risk of morbidity and mortality [11]. It has laid the foundation for other classification systems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
