METHOD: This is a 6-month, single-center, prospective, randomized, two-arm, and parallel-group controlled trial. The trial recruits patients attending the otorhinolaryngology clinics of a tertiary referral hospital. Participants are randomized into control or intervention groups in a 1:1 ratio using permuted block randomization. The total number of participants estimated is 154, with each group requiring 77 participants. The control group receives standard pharmaceutical care, while the intervention group receives pharmacist-led education according to the AR-PRISE model. Both groups are assessed for middle turbinate endoscopy findings, disease severity, knowledge level, symptom control, medication adherence, and QoL at baseline and the end-of-study follow-up (day 180 ± 7). Depending on feasibility, intermediate follow-ups are conducted on days 60 ± 7 and 120 ± 7, either virtually or face-to-face. During intermediate follow-ups, participants are assessed for symptom control, medication adherence, and QoL. The intention-to-treat analysis includes all participants assigned to each group. An independent T-test compares the mean difference in knowledge level between the two groups. A two-way repeated measures ANOVA analysis is employed to determine between-group differences for scores of symptom control, adherence rate, and QoL. A P-value
METHODS: A dataset containing medical records of 809 patients suspected to suffer from ACS was used. For each subject, 266 clinical factors were collected. At first, a feature selection was performed based on interviews with 20 cardiologists; thereby 40 seminal features for classifying ACS were selected. Next, a feature selection algorithm was also applied to detect a subset of the features with the best classification accuracy. As a result, the feature numbers considerably reduced to only seven. Lastly, based on the seven selected features, eight various common pattern recognition tools for classification of ACS were used.
RESULTS: The performance of the aforementioned classifiers was compared based on their accuracy computed from their confusion matrices. Among these methods, the multi-layer perceptron showed the best performance with the 83.2% accuracy.
CONCLUSION: The results reveal that an integrated AI-based feature selection and classification approach is an effective method for the early and accurate classification of ACS and ultimately a timely diagnosis and treatment of this disease.