Many Australians will experience a headache bad enough to require a visit to the Emergency Department (ED) at least once in their life. It is the fourth-most common reason people present at ED – in 2018 more than 4.9 million Australians visited ED for a headache.1
Although the vast majority of headaches are not serious, a small percentage will be a symptom of a life-threatening condition – such as a brain tumor or an intracranial hemorrhage.2 These patients require urgent treatment and it is critical for physicians to screen patients for these life-threatening conditions as soon as they present.
However, due to the limited time and resources in EDs, managing for all these potential conditions can be a challenging and time-consuming endeavor.3
This is the problem we’re working to solve.
Artificial intelligence (AI) systems have huge potential to help healthcare practitioners make more informed decisions and improve the treatment they provide to patients. The eye can be quickly and easily imaged, making it a good target for AI systems that could be used in busy environments like EDs.
The retina is also a window to the central nervous system, and changes in it can be signs of issues throughout the rest of the body.4
Papilledema – a swelling of optic disc – is a consequence of intracranial hypertension.5 It is one of the most important red flags for a potentially life-threatening headache.6 Although many emergency departments have the tools needed to examine the fundus, it can be difficult for physicians to use this equipment in a busy setting.7
Because of this, examination of the optic disc is not always well-performed in ED.8 To solve this, my team at CERA and I have developed a Smart Camera powered by AI to screen for these red flags.
Our AI system has shown great potential to accurately detect papilledema from retinal images, but it has not yet been tested in real-world settings.
We collaborated with Monash Medical AI Group and an industry partner to integrate the AI system into a retinal camera. Our Smart Camera is designed to automatically take retinal images and detect the presence of papilledema with high accuracy.
Physicians just need to ask the patients to get into position, and the Smart Camera completes the scan and provides a diagnosis report in about two minutes.
It is designed to help physicians screen for these life-threatening headaches more smoothly. Furthermore, it is fully automatic and portable, making it easy to use in emergency settings.
Our next steps are to refine the AI algorithm with more diverse clinical data to further improve its accuracy, and also undertake clinical validation trials to assess its feasibility and performance in the real-world setting of an emergency department.
If successful, it could prove to be a reliable, rapid, and cost-effective screening solution for headache management.
We also foresee that we could potentially expand the use of the Smart Camera to other neurological and eye conditions.
Our system is one of several projects at CERA using AI to spot conditions through the eye, ranging from heart disease to Alzheimer’s.
All have a great potential to assist doctors treat their patients.
About the author
Name: Dr Lisa Zhuoting Zhu
Qualifications: MD, PhD
Organisations: Centre for Eye Research Australia
Position: Primary Investigator, Ophthalmic Epidemiology
Location: Melbourne
Years in profession: 4
More reading
Bupa Optical using AI to check patients’ heart health
AI offers ‘comparable’ advice to ophthalmologists
Go eye-to-eye with Eyetelligence AI at O=MEGA23
References
- Migraine in Australia whitepaper | Deloitte Australia | Deloitte Access Economics report, Health. Deloitte Australia n.d. https://www2.deloitte.com/au/en/pages/economics/articles/migraine-australia-whitepaper.html (accessed March 10, 2023).
- Chu KH, Howell TE, Keijzers G, Furyk JS, Eley RM, Kinnear FB, et al. Acute Headache Presentations to the Emergency Department: A Statewide Cross-sectional Study. Acad Emerg Med 2017;24:53–62. https://doi.org/10.1111/acem.13062.
- Giamberardino MA, Affaitati G, Costantini R, Guglielmetti M, Martelletti P. Acute headache management in emergency department. A narrative review. Intern Emerg Med 2020;15:109–17. https://doi.org/10.1007/s11739-019-02266-2.
- London A, Benhar I, Schwartz M. The retina as a window to the brain—from eye research to CNS disorders. Nat Rev Neurol 2013;9:44–53. https://doi.org/10.1038/nrneurol.2012.227.
- Rigi M, Almarzouqi SJ, Morgan ML, Lee AG. Papilledema: epidemiology, etiology, and clinical management. Eye Brain 2015;7:47–57. https://doi.org/10.2147/EB.S69174.
- Crum OM, Kilgore KP, Sharma R, Lee MS, Spiegel MR, McClelland CM, et al. Etiology of Papilledema in Patients in the Eye Clinic Setting. JAMA Netw Open 2020;3:e206625. https://doi.org/10.1001/jamanetworkopen.2020.6625.
- Bruce BB, Lamirel C, Biousse V, Ward A, Heilpern KL, Newman NJ, et al. Feasibility of Non-Mydriatic Ocular Fundus Photography in the Emergency Department: Phase I of the FOTO-ED Study. Acad Emerg Med 2011;18:928–33. https://doi.org/10.1111/j.1553-2712.2011.01147.x.
