Background and objectives :
After the age of 50 years, men's health may be impacted by various disorders such as
lower urinary tract symptoms (LUTS) and erectile dysfunction (ED). Due to a lack of
understanding and awareness, patients often fail to recognize early signs and are not
compliant with medical advice. As they are hesitant to discuss these issues related to
urination and erectile functions, they avoid seeking medical help, especially due to the
restrictions and concerns brought by the COVID-19 pandemic. Consequently, worsening
symptoms can adversely affect their quality of life and dignity. Studies have found that
providing men with self-management health programs results in better symptom management
and medical decisions. Therefore, work is underway to develop artificial intelligence
(AI) platforms to allow men to manage their health before consulting a doctor. Chatbots
are used for various medical decisions and healthcare management, and can now provide
men with various healthcare information to help improve the effectiveness of self-care
and medical treatments in the post COVID-19 period.
The purpose of this study is to explore the impact of AI chatbot aid intervention on
enhancing self-management, and decision self-efficacy among men with lower urinary tract
symptoms (LUTS) due to an enlarged prostate, with or without erectile dysfunction (ED)
in the post COVID-19 era.
Materials and Methods:
2.1. Trial design and ethical approval
This was a 1:1 two groups randomized controlled trial (RCT) with pre- and post-test
experimental design. This study was approved by the Institutional Review Board (IRB) of Cheng
Hsin General Hospital in Taipei, Taiwan (approval number CHGH-IRB (988)111A-66-2) and
participants were provided with informed consent. Both groups had similar demographics. One
hundred male patients will be recruited from the Urology outpatient clinic, with 50 patients
randomly assigned to the experimental group and 50 patients to the control group.
2.2 Participants
Patients diagnosed with health-related diseases by urologists were included in this study.
The conditions were as follows:(1) male, (2) age between 45-80 years old, (3) prostate
enlargement with lower urinary tract symptoms, (4) need a mobile phone and willing to
download the line chatbot. The exclusion criterion was a history of psychosis.
2.3 Intervention
The study uses a chatbot in collaboration with the Taiwan Urological Association (TUA) and
the Taiwan Continence Society (TCS), which is deployed on the line app for mobile devices.
The chatbot uses an AI model integrated with the line developer platform to predict risks for
men's health conditions such as urinary symptoms and erectile dysfunction. Patients can
access the chatbot for free by scanning a QR code. It provides self-management advice on
issues such as prostate enlargement, urinary symptoms, and erectile dysfunction. It also
provides patient-centered decision-making aids that support and encourage patients,
especially in improving urination and erectile dysfunction.
2.4 Research instruments
The patients in both groups were asked to complete a basic personal information form, as well
as several questionnaires including the International Prostate Symptom Score (IPSS),
International Index of Erectile Function-5 (IIEF-5), Men's Health knowledge score, Partners
in Health (PIH), and Decision Self-Efficacy Scale (DSES) before and 2-4 weeks after receiving
the intervention measures. Additional examination data, such as prostate-specific antigen
(PSA), uroflowmetry, and prostate sonography, were collected from medical records. A
satisfaction questionnaire was also administered to the patients.
2.5 Statistical methods
SPSS was used for statistical analysis, including McNemar's test and independent sample
t-test were used to compare and analyze the difference in the knowledge score,
self-management, and decision-making self-efficacy between the experimental group and control
group before and after the intervention; paired t-test was used to compare individuals before
and after receiving intervention measures; Pearson's correlation was used to analyze the
relationship among LUTS, knowledge score, self-management, and decision self-efficacy;
Finally, multiple regression analysis to analyze the impact of using the chatbot on
satisfaction.