RESEARCH-BASED DATA COLLECTION AND DECISION SUPPORT SYSTEM FOR COS

Problem statement

According to a survey of 966 clinicians and healthcare staff in the UK, clinic personnel spend 16.8h per week on average for documentation during initial patient intake recording patients` information and loading it into the clinic`s electronic medical record (EMR) system. At the same time, patients are asked the same questions several times throughout their clinical journey and may feel disconnected and isolated within their clinic. Further, the presence of multiple data entry points increases the chances of errors and inconsistencies in clinical data, with possible effects on treatment outcomes and risk detection. Finally, a more connected and accurate data collection and evaluation system allows for the provision of more precise and safer care, where medical risks can be identified earlier, and outcome prediction can be shared with clinicians and patients alike, lowering the clinic`s operational costs, and improving the patient experience through the clinic journey. Leeaf tackles these issues with a unified, automated data collection and interpretation platform based on published clinical guidelines, artificial intelligence (AI) algorithms, and evidence-based medicine.

Methods

Leeaf collects data directly from patients through a proprietary application (Leeaf app) which is connected to an EMR (Leeaf Physician Portal) deployed in partner clinics. The patient fills out user-friendly questionnaires related to clinical history and other clinically relevant aspects before visiting the clinic, including external reports such as blood hormonal tests and serological analysis, as directed by the clinic in a customizable and flexible fashion. Drawing from Leeaf`s extensive database of more than 400.000 real-life patient data points and using a combination of published literature, society’s best practices and guidelines, and in-house medical consensus, clinicians are recommended the most effective clinical actions, and potential risks are flagged in a personalized way for each patient.

Results

We present a series of modules, each consisting of a set of rules with regard to controlled ovarian stimulation (COS). So far, we have implemented four modules: Facts to Consider, Health Risks, ESHRE Guidelines, and Lifestyle Rules. Some of the personalized recommendations provided to clinicians and patients are flagging patients for OHSS risk before the beginning of treatment and suggesting methods to mitigate this risk through appropriate stimulation protocols, doses, and trigger recommendations. Further, the risk of OHSS, risk of thrombosis, and risk of PCOS are also presented (Table 1). All of the rules go through a rigorous approval process by the medical board before they are released on the platform. Moreover, the implementation allows for custom modifications by the clinician should the need arise.

Conclusion

Leeaf offers clinicians the option to meet digitally and acquaint themselves quickly with the patient before their visit to the clinic, allowing more time to be spent on establishing a bond and exploring deeper concerns for the patients. Furthermore, the patients’ information is smartly processed, and the clinician is notified in advance of relevant risks throughout the treatment process, with evidence-based suggestions on alternative courses of action.