Fuzzy logic for preanesthetic risk assessment in cataract surgery patients

We aimed to build a fuzzy logic preanaesthetic risk score tailored to cataract surgery. By fusing systemic comorbidities with key patient attributes in an adaptive rule base, our goal was to generate patient-specific risk estimates that move beyond the coarse granularity of traditional categorical tools. A prospective observational cohort study was conducted at Kanuni Sultan Suleyman Hospital, University of Health Sciences, Istanbul, Turkey. Two hundred fifty-one adults who were scheduled for cataract surgery under either local or general anesthesia were included in the study. Demographic information and comorbidities were gathered prior to surgery. A fuzzy inference system incorporating 5 major (pulmonary, cardiac, renal, liver disease, and diabetes) and 3 minor (age, BMI, and smoking) criteria was developed. Risk levels were generated using 270 expert-defined fuzzy rules. Postoperative transient intraocular pressure (IOP) elevations and other complications were monitored. Among the 251 patients, 70 (27.9%) developed postoperative transient IOP elevations. Fuzzy risk scores correlated strongly with the number of major comorbidities (r = 0.954), confirming internal consistency. However, the model did not significantly differentiate between patients with and without postoperative transient intraocular pressure (IOP) elevations (AUC = 0.439; P > .05). There were no other complications found, but transient IOP elevations was significantly linked to advanced age and long-term smoking. The fuzzy logic model reliably quantified systemic risk burden but lacked predictive power for ophthalmic-specific outcomes driven by ocular factors such as transient IOP elevations. Incorporating domain-specific variables like intraocular pressure and detailed ophthalmologic assessments may improve future performance. The model remains valuable for general preanesthetic risk stratification in surgical populations.