Find out more about our Academic Medical Centre and efforts in Academic Medicine
Find out more about what JOAM do to support AM initiatives
Academic Medicine Executive Committee (AM EXCO)
Our appointed ACP leaders within the respective 15 ACPs
Guidelines, forms, and templates for Academic Medicine.
• Health economic analysis of emerging digital health strategies and technologies, including assessing the disease burden, intended use of environment, diagnostic performance, should be done to determine the efficiency of specific technologies
Singapore, 1 June 2022 – Digital technology and virtual health solutions have sparked tremendous interest in healthcare, especially during the COVID-19 pandemic which expedited the rate of adoption for these solutions and accelerated the digital transformation of healthcare systems globally. Anticipating this continuing upward trend, a team of clinician innovators from SingHealth sought to determine if digital interventions are truly more cost-efficient and bring greater value and benefits to patients – and found that it may not always be so for certain eye conditions.
In an editorial piece recently published in the Lancet Regional Health Western Pacific, the team analysed the economic health impact of digital technologies in screening for two common eye diseases – Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD). DR is a diabetes complication affecting the eyes that impacts approximately 103 million adults worldwide1, and AMD is an eye disease that affects one’s central vision which impacts approximately 196 million people globally2. Technology such as tele-screening of patients and use of artificial intelligence in diagnostic tests has been advancing and used in various settings for both conditions.
In Singapore, for example, the Singapore National Eye Centre, Singapore Eye Research Institute (SERI) and the National University of Singapore’s School of Computing developed a deep learning system called Selena+ to analyse patients’ retinal photos for signs of DR and to prevent irreversible blindness among diabetes patients. Using close to half a million retinal images, Selena+ is trained to quickly analyse retinal photographs at the speed of 10 seconds per photograph, facilitating faster turnaround time for diagnostic tests and reducing the workload of human graders by more than 50 per cent3,4. The system is currently being deployed nationwide, and has obtained regulatory approval for use in Singapore by the Health Sciences Authority and regional countries such as European CE mark, Malaysia, Brazil, Indonesia.
While a system like Selena+ works well for Singapore and its partner countries, the team found that the efficiency of digital technologies in medicine could differ from setting to setting and from condition to condition. Specifically, for DR and AMD, factors such as diagnostic performance including comparing the sensitivity and accuracy of results by human graders and artificial intelligence, grading fees, as well as digital infrastructure supporting the technology have a direct bearing on healthcare costs and must be taken into consideration. It is also important to take into account patient preferences that may differ from decision makers’ opinions.
The team referenced a recent paper5, also published in the Lancet Regional Health Western Pacific, on the cost-effectiveness and cost-utility analysis on DR and AMD tele-screening, as compared to traditional screening, in China. While the paper demonstrated that tele-screening was the most cost-effective option for combined DR and AMD screening, the team noted the importance of evaluating the incremental benefit of having AMD screening in addition to DR screening. The team also noted that tele-screening required trained graders and ophthalmologists which may not be available in less resource-rich settings, and the effectiveness of automated screening for DR and AMD in such settings would require further evaluation.
“Innovations and digital technologies are key drivers to transform healthcare for the future, and we must constantly advance and leverage them to deliver better care for our patients. That said, we must also consider their health economic implications which could be vary for different disease areas, environmental settings. These factors could impact the scope of clinical services that will utilise technological solutions and digital infrastructure required. We must view such technological solutions from a multi-faceted perspective, so as to better and more holistically benefit patients and the healthcare system,” said Dr Ann Kwee, the primary author of the paper and Consultant, Department of Endocrinology, Singapore General Hospital.
Assoc Prof Daniel Ting, Director, SingHealth Artificial Intelligence Programme and Health, AI and Digital Innovation, SERI, and senior author of the paper added – “It is important consider the following when evaluating the health economic analysis of emerging digital technologies or strategies – define the intended use environment and disease burden or prevalence; choose an appropriate health economic model based on the intended use; evaluate the diagnostic performance of the mode of screening with reference to the standard of care; as well as evaluate direct and indirect costs for screening technologies, clinical services, hospital systems and digital infrastructure”.
1Teo ZL, Tham YC, Yu M, et al. Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045: Systematic Review and Meta-analysis. Ophthalmology 2021; 128(11): 1580-91.
2Suanier V, Merle B, Delyfer ML, et al. Incidence of and Risk Factors Associated With Age-Related Macular Degeneration. JAMA Ophthalmology 2018.
3Ting DSW, Cheung CY, Lim G, et al. Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes. JAMA. 2017 Dec 12;318(22):2211-2223.
4Xie Y, Nguyen QD, Hamzah H, Lim G, Bellemo V, Gunasekeran DV, Yip MYT, Qi Lee X, Hsu W, Li Lee M, Tan CS, Tym Wong H, Lamoureux EL, Tan GSW, Wong TY, Finkelstein EA, Ting DSW. Artificial intelligence for teleophthalmology-based diabetic retinopathy screening in a national programme: an economic analysis modelling study. Lancet Digit Health. 2020 May;2(5):e240-e249.
5Li R, Yang Z, Zhang Y, et al. Cost-effectiveness and cost-utility of traditional and telemedicine combined population-based age-related macular degeneration and diabetic retinopathy screening in rural and urban China. Lancet Reg Health West Pac 2022; 23: 100435