Fuzzy logic for preanesthetic risk assessment in cataract surgery patients


Yilmaz G., Küçüksaraç G., Esen O., Akdaş N., BALKAN B., SANDAL B., ...Daha Fazla

Medicine (United States), cilt.105, sa.12, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 105 Sayı: 12
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1097/md.0000000000047977
  • Dergi Adı: Medicine (United States)
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, BIOSIS, CINAHL, EMBASE, MEDLINE, Directory of Open Access Journals
  • Anahtar Kelimeler: cataract, comorbidity, fuzzy logic, postoperative complications, risk assessment
  • Sağlık Bilimleri Üniversitesi Adresli: Evet

Özet

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.