An intelligent decision support system for acute postoperative endophthalmitis: design, development and evaluation of a smartphone application.

BACKGROUND: Today, clinical decision support systems based on artificial intelligence can significantly help physicians in the correct diagnosis and quick rapid treatment of endophthalmitis as the most important cause of blindness in emergency diseases. This study aimed to design, develop, and evaluate an intelligent decision support system for acute postoperative endophthalmitis. METHODS: This study was conducted in 2020-2021 in three phases: analysis, design and development, and evaluation. The user needs and the features of the system were identified through interviews with end users. Data were analyzed using thematic analysis. The list of clinical signs of acute postoperative endophthalmitis was provided to ophthalmologists for prioritization. 4 algorithms support vector machine, decision tree classifier, k-nearest neighbors, and random forest were used in the design of the computing core of the system for disease diagnosis. The acute postoperative endophthalmitis diagnosis application was developed for using by physicians and patients. Based on the data of 60 acute postoperative endophthalmitis patients, 143 acute postoperative endophthalmitis records and 12 non-acute postoperative endophthalmitis records were identified. The learning process of the algorithm was performed on 70% of the data and 30% of the data was used for evaluation. RESULTS: The most important features of the application for physicians were selecting clinical signs and symptoms, predicting diagnosis based on artificial intelligence, physician-patient communication, selecting the appropriate treatment, and easy access to scientific resources. The results of the usability evaluation showed that the application was good with a mean (± SD) score of 7.73 ± 0.53 out of 10. CONCLUSION: A decision support system with accuracy, precision, sensitivity and specificity, negative predictive values, F-measure and area under precision-recall curve 100% was created thanks to widespread participation, the use of clinical specialists' experiences and their awareness of patients' needs, as well as the availability of a comprehensive acute postoperative endophthalmitis clinical dataset.

Incidence and related factors of surface eye disorders in traumatic intensive care unit patients in Iran.

BACKGROUND: Intensive care unit (ICU) patients are exposed to several surface eye disorders ranged from minor complications like corneal dryness to more serious ones such as corneal perforation and blindness. This study is then to assess the incidence of the ocular complications and related factors. MATERIALS AND METHODS: During a prospective cross sectional study in a general adult ICU, ocular complications of the patients were assessed by an ophthalmologist. Data were analyzed using descriptive analysis. A P-value of ≤0.05 was considered significant. RESULTS: Out of 155 patients, 130 cases (260 eyes) were covered during the study period, 2016-2017. The most common complications among the patients included dry eye and corneal abrasion (25.8%) followed by conjunctivitis (25%). The mean time of occurrence for dryness and corneal abrasion was 4±2.93 days after admission to the ICU. Lower Glasgow coma scale (GCS) and longer hospital stay were significantly associated with ocular complications in the ICU (P<0.05). CONCLUSION: Eye surface complications are commonplace in critically ill patients admitted in the ICU. Dry eye, corneal abrasion, and conjunctivitis have been revealed as the most prevalent complications in this study. Lower GCS and longer stay in the ICU predisposed the cases to these complications. Efficient eye care protocol and training the ICU staff are both recommended to reduce complication rates as such.

Bacterial Etiology and Antibiotic Susceptibility of Conjunctivitis Patients' Isolates in Kashan, Iran.

BACKGROUND: Conjunctivitis is a very common ocular disease, which can be caused by a wide variety of microorganisms. This study was aimed to assess the bacterial etiology and antibiotic susceptibility of conjunctivitis patients' isolates from Central Iran. MATERIALS AND METHODS: This study was performed in 180 patients referred to the Department of Ophthalmology in Kashan University with symptoms of conjunctivitis from July 2017 to December 2017. To detect of different bacteria, Gram staining, morphological characterization, pigment production, biochemical characteristics, coagulase test, optochin and PYR tests, oxidase test, and culture on specific media were used. Antibiotic susceptibility of the bacteria isolated was done using the Kirby-Bauer method. Methicillin resistance in staphylococci isolated from the patients was identified using polymerase chain reaction technique. RESULTS: Of the 195 bacteria isolated, about 81.5% were Staphylococcus epidermidis and Staphylococcus aureus and the remaining 19.5% included other species. In the present study, Pseudomonas aeruginosa was most resistant to ampicillin. In the case of S. epidermidis and S. aureus, the highest resistance was observed against erythromycin and the least resistance was against rifampicin and linezolid. CONCLUSION: In this study, S. aureus and S. epidermidis are the most common causes of conjunctivitis in all age groups, however, this condition decreases with age and is also influenced by other factors such as season and weather conditions. The results of this study can be helpful in planning more prudent treatment strategies for patients with conjunctivitis in Kashan.