Abstract
BACKGROUND: Infertility is the inability to conceive after a year of trying, resulting in unintentional childlessness. A clinical decision-support system can enhance diagnosis, reduce costs, improve access, and increase treatment accuracy. OBJECTIVE: This study aimed to present a conceptual model for decision support systems in infertility. MATERIALS AND METHODS: This developmental study, conducted from April-November 2024 in 3 steps. First, PubMed, Scopus, and Web of Science databases were investigated to identify data for decision support systems in infertility. Next, search engines like Google, Yahoo, and Bing, along with artificial intelligence tools such as ChatGPT, Gemini, and Perplexity, helped identify similar systems. Lastly, opinions from 32 infertility experts were collected via a researcher-made questionnaire, with reliability confirmed by Cronbach's alpha of 0.78 and validity confirmed by content validity ratio of 0.60. RESULTS: In the first step, 16,310 articles were identified; 10 were selected after removing duplicates and applying inclusion and exclusion criteria. In the second step, 71 relevant systems were identified in search engines; 58 were excluded, leaving 13 for further analysis. In the third step, a researcher-designed questionnaire was distributed to 32 experts, yielding key agreement rates of 94% for monitoring and follow-up, 94% for sperm analysis data, 90% for abortion data, and 82.5% for infertility information from health magazines. Requirements grouped into 4 categories: main features (10 elements), patient info management (19 elements), fertility prediction data (16 elements), and secondary features (3 elements). The model's overall agreement was 85%. CONCLUSION: Developing a decision-support system for infertility could enhance clinical care and outcomes; however, challenges include standardizing validation methods and considering ethnic diversity.