Introduction: Noninvasive assessment of esophageal varices (EV) decreases the medical and financial burden related to screening and helps in the management of patients with chronic liver diseases (CLDs). In this study, our aim was to assess the utility of the platelet count/spleen diameter index for the noninvasive evaluation of EV. Materials and methods: In this cross-sectional observational study, a total of 100 CLD patients underwent screening endoscopy for EV in Medicine and Gastroenterology Department, Sylhet MAG Osmani Medical College Hospital, Sylhet, Bangladesh. Platelet count/spleen diameter ratio was assessed in all patients and its diagnostic implication was calculated. Results: Upper gastrointestinal endoscopy revealed that 45 (45.0%) patients had medium EV followed by 27 (27.0%) that had small EV and 19 (19.0%) patients had large EV. Receiver operator characteristic (ROC) curve was constructed using platelet count/spleen index, which gave a cut-off value of ≥905. The validity of platelet count/spleen index evaluation of CLD was: Sensitivity 92.3%, specificity 66.7%, accuracy 90.0%, positive predictive value (PPV) and negative predictive value (NPV) were 96.6 and 46.2% respectively. True positive was 84 cases, false positive 3 cases, false negative 7 cases, and true negative 6 cases. If we consider cut-off value as 909 in the evaluation of EV in CLD, then true positive was 85 cases, false positive 3 cases, false negative 6 cases, and true negative 6 cases. From this, by calculation, sensitivity was 93.4%, specificity 66.7%, accuracy 91%, PPV 96.6%, and NPV 50%. Conclusion: The platelet count/spleen index may be proposed to be a safe and reliable mean of screening of EV in CLD patients; however, case–control study would be required to validate this.