Developing a mobile health application for wound telemonitoring: a pilot study on abdominal surgeries post-discharge care.

BACKGROUND: Many early signs of Surgical Site Infection (SSI) developed during the first thirty days after discharge remain inadequately recognized by patients. Hence, it is important to use interactive technologies for patient support in these times. It helps to diminish unnecessary exposure and in-person outpatient visits. Therefore, this study aims to develop a follow-up system for remote monitoring of SSIs in abdominal surgeries. MATERIAL AND METHODS: This pilot study was carried out in two phases including development and pilot test of the system. First, the main requirements of the system were extracted through a literature review and exploration of the specific needs of abdominal surgery patients in the post-discharge period. Next extracted data was validated according to the agreement level of 30 clinical experts by the Delphi method. After confirming the conceptual model and the primary prototype, the system was designed. In the pilot test phase, the usability of the system was qualitatively and quantitatively evaluated by the participation of patients and clinicians. RESULTS: The general architecture of the system consists of a mobile application as a patient portal and a web-based platform for patient remote monitoring and 30-day follow-up by the healthcare provider. Application has a wide range of functionalities including collecting surgery-related documents, and regular assessment of self-reported symptoms via systematic tele-visits based on predetermined indexes and wound images. The risk-based models embedded in the database included a minimum set with 13 rules derived from the incidence, frequency, and severity of SSI-related symptoms. Accordingly, alerts were generated and displayed via notifications and flagged items on clinicians' dashboards. In the pilot test phase, out of five scheduled tele-visits, 11 (of 13) patients (85%), completed at least two visits. The nurse-centered support was very helpful in the recovery stage. Finally, the result of a pilot usability evaluation showed users' satisfaction and willingness to use the system. CONCLUSION: Implementing a telemonitoring system is potentially feasible and acceptable. Applying this system as part of routine postoperative care management can provide positive effects and outcomes, especially in the era of coronavirus disease when more willingness to telecare service is considered.

Prognosis of COVID-19 patients using lab tests: A data mining approach.

Background: The rapid prevalence of coronavirus disease 2019 (COVID-19) has caused a pandemic worldwide and affected the lives of millions. The potential fatality of the disease has led to global public health concerns. Apart from clinical practice, artificial intelligence (AI) has provided a new model for the early diagnosis and prediction of disease based on machine learning (ML) algorithms. In this study, we aimed to make a prediction model for the prognosis of COVID-19 patients using data mining techniques. Methods: In this study, a data set was obtained from the intelligent management system repository of 19 hospitals at Shahid Beheshti University of Medical Sciences in Iran. All patients admitted had shown positive polymerase chain reaction (PCR) test results. They were hospitalized between February 19 and May 12 in 2020, which were investigated in this study. The extracted data set has 8621 data instances. The data include demographic information and results of 16 laboratory tests. In the first stage, preprocessing was performed on the data. Then, among 15 laboratory tests, four of them were selected. The models were created based on seven data mining algorithms, and finally, the performances of the models were compared with each other. Results: Based on our results, the Random Forest (RF) and Gradient Boosted Trees models were known as the most efficient methods, with the highest accuracy percentage of 86.45% and 84.80%, respectively. In contrast, the Decision Tree exhibited the least accuracy (75.43%) among the seven models. Conclusion: Data mining methods have the potential to be used for predicting outcomes of COVID-19 patients with the use of lab tests and demographic features. After validating these methods, they could be implemented in clinical decision support systems for better management and providing care to severe COVID-19 patients.