Smart phone application for early detection of adverse clinical outcomes in solid malignancy.

Abstract

562 Background: The widespread application of mobile technology in healthcare, particularly in the realm of telemedicine and Patient-Reported Outcomes (PRO), is revolutionizing care. We have developed a mobile application that leverages artificial intelligence (AI) and The Internet of Medical Things (IoMT) using machine learning (ML) assisted dashboard to enable real-time documentation and communication between patients and healthcare providers. The aim of our research is to explore the potential of this innovative combination in boosting patient quality of life (QoL) and enabling prompt, effective patient management. Methods: We conducted a pilot randomized controlled trial. The trial focused on comparing the quality of life at baseline, 1 month, and 3 months of cancer patients receiving standard conventional follow-up care versus those using our intervention. Patients receive a smartwatch and download our application, while a monitoring care team was established. Our application incorporates guidelines from MacMillan Cancer providing ML-guided symptom assessment. If adverse drug reactions or treatment effects occurred, the application provided prompt self-care suggestions. The secondary outcomes evaluated included cumulative emergency visits, cancer care knowledge assessment results, and the feasibility. Results: Between December 1, 2022, and June 1, 2023, a total of 30 patients were recruited for the trial. The average age of the patients was 51 years, with a majority being women (76.6%). The cohort comprised five types of solid malignancies, with breast cancer accounting for 56.6%. Most patients were in stage 4, and the aim of treatment for them was palliative (60%). The mean FACT-G scores were similar between the two groups at all time points. However, the control group showed a significant decrease in Functional Well-Being at 3 months compared to baseline (P = .025). Additionally, while the Intervention group had zero emergency visits, the Control group experienced a total of five visits (P = .016). The literacy test scores showed no significant difference. On average, individuals spent 60 minutes per day using the application, indicating high user engagement and overall feasibility. Conclusions: Mobile application, powered by AI and IoMT, has the potential to significantly impact patient care and further research is warranted to explore its broader implementation in healthcare settings. Clinical trial information: TCTR20230331002 .[Table: see text]