Connecting the dots in Fertility

We believe that the opportunity to be a parent should become even more available. Sometimes, additional help is needed. People undergoing in vitro fertilization (IVF) are more than patients; they are active participants in their own treatment, day in, day out. Fertility treatment demands a lot of time and energy. The daily medication, changing hormone levels and lifestyle choices made by patients can have a huge impact on their fertility journey.¹ Yet IVF physicians are disconnected from the many important patient developments, like changes in hormone levels, that happen at home.
 

These days, health tech empowers the growing number of people who want to learn more about their well-being to manage their personal health. What if we could offer new health tech solutions that allow people undergoing IVF to collect data and share it in real-time with their physician? Can we connect the dots, establishing precise medication tracking, and home monitoring devices to better bond clinics and patients? With this new approach, we would enable physicians to react in real-time and give patients more insight into their own treatment.

In order to successfully realize these opportunities, we need to consider the difference in design between personal health solutions and more precise offerings for healthcare providers. Digital health solutions for consumers are often designed to be light, accessible and easy to use. Meanwhile, technologies for clinicians and clinics often seem more complex and less intuitive. This is because they need to provide experts with precise data that can seamlessly fit into the fertility treatment process. These technical solutions are strictly regulated because they directly support treatment decisions.

Despite the different needs of these audiences, there are some highly promising digital health solutions emerging that seek to connect healthcare providers and patients. It is a huge opportunity. Patients can keep clinicians updated on specific biomarkers in real-time and from home, for example, we could provide more transparency on treatment progression and see greater personalization of treatment and decision making across the fertility industry. The collection of those data points could then be analyzed using Artificial Intelligence (AI) to provide new treatment options for IVF physicians. These exciting new digital health solutions could also allow greater connectivity with patients and thereby enable new standards of care centered on remote treatment and consultation. During the current pandemic, we are seeing an acceleration towards remote treatment across healthcare systems and we need to harness the potential of new technologies to ensure we are providing the best care to our patients.

Digital health solutions for clinical use could also help to free up time for clinic staff to dedicate to the cases that need their support and attention. Patient satisfaction is of the upmost importance in fertility, and additional insight into how health care professionals can better meet the needs of the patient can only benefit all parties.² This would offer reassurance to patients, allowing them to feel supported throughout their fertility journey.

Today, we are on the cusp of realizing the potential of digital health solutions to improve our fertility. Contemporary efforts to develop digital health solutions have broadly followed two different strategies; devices generating data and supporting fertility treatment; and intelligent algorithms, based on artificial intelligence, which analyze large, complex datasets. These two different types of technologies need to work hand-in-hand to be effective and fulfill their potential, or else the increasing volume of data cannot be understood as quickly or in as much detail.

AI is by far the fastest growing and broadest area of digital health solutions across all therapeutic areas. According to a survey organized by LinkedIn, AI Specialist is one of the fastest emerging jobs in the US this year.³ To get AI widely accepted by IVF physicians and patients we need to tackle questions about how we set the standards for AI tools and their development and align on what ‘good’ and ‘high quality’ mean.

More research is needed to promote the value of AI in reproductive medicine,⁴ to allow it to be used more broadly. Currently, the only information clinicians have are very individual datasets across various patients and centers,⁵ which are hard to unify and analyze. If we are to better integrate patients into the decision-making process and deliver personalized treatment, we need enable the broad use of AI solutions throughout the fertility
treatment journey.

To do this we need to jointly establish a data and interface standard. In addition, we need to ensure accepted quality standards are put in place and maintained for AI products and their development. This is a fantastic opportunity for all stakeholders in fertility to improve reproductive treatment in its entirety.

If we are to make a success of digital health solutions, we must all work together across companies, academia and associations to join the dots between the clinic and the patient, because there’s no such thing as a passive patient where fertility treatment is concerned.

References

¹ Pilot National Fertility Patient Survey 2018. Human Fertilisation and Embryology Authority. Available at: https://www.hfea.gov.uk/media/2702/pilot-national-fertility-patient-survey-2018.pdf Last accessed: April 2020
² Gonen, L.D. Satisfaction with in vitro fertilization treatment: patients’ experiences and professionals’ perceptions. Fertil Res and Pract 2, 6 (2016). https://doi.org/10.1186/s40738-016-0019-4
³ 2020 Emerging Jobs Report. LinkedIn. Available at: https://business.linkedin.com/content/dam/me/business/en-us/talent-solutions/emerging-jobs-report/EmergingJobsReportU.S.FINAL.pdf Last accessed: April 2020
⁴ Wang, R., Pan, W., Jin, L., Li, Y., Geng, Y., Gao, C., Chen, G., Wang, H., Ma, D., & Liao, S. (2019). Artificial intelligence in reproductive medicine, Reproduction, 158(4), R139-R154. Retrieved Apr 6, 2020, from https://rep.bioscientifica.com/view/journals/rep/158/4/REP-18-0523.xml
⁵  Curchoe, C.L., Bormann, C.L. Artificial intelligence and machine learning for human reproduction and embryology presented at ASRM and ESHRE 2018. J Assist Reprod Genet 36, 591–600 (2019). https://doi.org/10.1007/s10815-019-01408-x

• GL-NONF-00619