Artificial intelligence might be the future of practice management

While a hot topic of late, it is easy to forget that the concept of artificial intelligence (AI) is not new. Early philosophers and mathematicians theorized that mechanical reasoning could one day be taught to robots, automatons, and smart machines.  

However, AI advancements slowed over the next few decades due to competing funding priorities, moral/ethical concerns, and the limitations of computing technology and data storage. It was not until the late 1990s/early 2000s that most of these challenges and concerns were alleviated and computer and data technologies advanced, becoming more affordable.  

Related: How artificial intelligence is changing the future of optometry  

Today, significant investment can be seen in health care-related AI with well-known companies like Microsoft, Google, and IBM heavily involved in promoting AI solutions in eye care,and smaller startups even attaining FDA-approval as standalone diagnostic technology.^2-6

Most of these AI platforms for eye care are focused on diagnosing diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucoma from retinal photos and “eye scans.” 

Outside of eye care, AI is already used to better diagnose, genotype, and match cancer patients with treatment protocols and trials that maximize outcomes.³

With technologies such as these, fears abound within healthcare provider communities that AI will one day replace the doctor in the doctor-patient relationship.

However, in light of recent revelations-that AI still has far to go in clinical settings to match its performance in controlled studies⁹ and that AI in conjunction with a doctor is superior to diagnosing and grading diabetic retinopathy (DR)¹⁰-those concerns may be misguided, or at least highly premature. 

Related: Is optometry ready for the age of smartphone imaging? 

Applications
Just like an autorefractor or the normative database in ocular coherence tomography (OCT), AI can enhance clinical care and improve patient outcomes when applied correctly. 

But what about AI for practice management?   

AI applications could offer opportunities to enhance clinic flow, simplify billing, expedite electronic health record (EHR) input, streamline claims, and enhance cash flow. And with today’s high-deductible health plans (HDHPs) becoming more popular with employers-and therefore more common with patients-revenue cycle management is a natural fit for AI as more patients are defaulting on their portion of medical bills. 

How close is any of this to becoming reality?

Recent launches 
Last summer, EHR vendor CompuLink launched a new AI-integrated practice management system called Advantage SMART Practice that aims to reduce staff time required to work claims by 90 percent, improve patient throughput by 15 percent or more, and achieve net collections of up to 98 percent.¹¹

Additionally, in April, Advanced Data Systems Corporation began offering an AI-based revenue cycle management platform called MedicsRCM to help practices and healthcare networks better manage and maximize cash flow.¹²

Related: What OCTA shows us 

Specifically, efficiencies are targeted in the preparation of clean claims to avoid insurance denials upfront, with the AI platform spontaneously adjusting claims errors prior to filing and automatically preparing supporting claims documents in advance.

Further, the integrated AI claims to fast-track patient eligibility verification as well as speed up the determination of co-pay and deductible amounts. 

It then offers this information to patients prior to their visits to help them understand their insurance coverage and financial responsibility, thereby reducing unpaid balances.

On the EHR side, Nuance recently announced successful beta testing of a new AI platform to reduce time documenting exam details in the EHR with launch planned for next year. 

This new offering-called Ambient Clinical Intelligence-utilizes voice recognition AI technology with 16 microphones strategically placed within the exam room to “listen” to conversations with patients, then document the interaction in the EHR without the doctor diverting attention from the patient. 

Related: Use technology advancements to modernize your practice 

Medication orders can also be completed using an embedded virtual assistant. It automatically captures patient responses to clinical questions, and can be used to sign the exam on the spot.^13,14

Conclusion  
Change can be difficult, but ignoring or disparaging AI as a whole would be a costly mistake. 

More AI advances are in the works for eye care, so for patients’ health-as well as the health of practices-ODs need to stay abreast of developments in AI, oppose any that threaten patient safety, and adopt those which are appropriate. 

As these platforms continue to advance and become more affordable, seek ways to make AI work for the good of patients and practices. By doing so, ODs may achieve “super intelligence.”

Read more technology and practice mangaement content here 

References:

1. Anyoha R. The History of Artificial Intelligence. Harvard University. Available at: http://sitn.hms.harvard.edu/flash/2017/history-artificial-intelligence/. Accessed 8/28/19.

2. MMC Ventures. The State of AI 2019: Divergence: Chapter 7: Europe’s AI startups. Available at: https://www.stateofai2019.com/chapter-7-europes-ai-startups/. Accessed 8/28/19.

3. Project Hanover. Machine reading for precision medicine. Available at: https://hanover.azurewebsites.net/#overview. Accessed 8/28/19.

4. DeFauw J, Ledsam JR, Romera-Paredes B, Nikolov S, Tomasev N, Blackwell S, Askham H, Glorot X, O’Donoghue B, Visentin D, van den Driessche G, Lakshminarayanan B, Meyer C, Mackinder F, Bouton S, Ayoub K, Chopra R, King D, Karthikesalingam A, Hughes CO, Raine R, Hughes J, Sim DA, Egan C, Tufail A, Montgomery H, Hassabis D, Rees G, Back T, Khaw PT, Suleyman M, Cornebise J, Keane PA, Ronneberger O. Clinically applicable deep learning for diagnois and referral in retina disease. Nat Med. 2018 Sep;24(9):1342-1350.

5. American Academy of Ophthalmology. IBM is training Watson to detect glaucoma. Available at: https://www.aao.org/headline/ibm-is-training-watson-to-detect-glaucoma. Accessed 8/28/19.

6. Maetschke S, Antony B, Ishikawa H, Wollstein G, Schuman J, Garnavi R. A feature agnostic approach for glaucoma detection in OCT volumes. PLoS One. 2019 Jul 1;14(7):e0219126. doi: 10.1371/journal.pone.0219126.

7. Muoi D. Study results support FDA approval of diagnostic algorithm, but experts remain wary. MobiHealthNews. Available at: https://www.mobihealthnews.com/content/study-results-support-fda-approval-diagnostic-algorithm-experts-remain-wary. Accessed 8/28/19.

8. Kent C. AI & Ophthalmology: Two Approaches to Diagnosis. Review of Ophthalmology. Available at: https://www.reviewofophthalmology.com/article/ai-and-ophthalmology-two-approaches-to-diagnosis. Accessed 8/28/19.

9. Kanagasingam Y, Xiao D, Vignarajan J, Preetham A, T-K ML, Mehrotra A. Evaluation of Artificial Intelligence–Based Grading of Diabetic Retinopathy in Primary Care. JAMA Netw Open. 2018 Sep; 1(5): e182665.

10. Sayres R, Taly A, Rahimy E, Blumer K, Coz D, Hammel N, Krause J, Narayanaswamy A, Rastegar Z, Wu D, Zu S, Barb S, Joseph A, Shumski M, Smith J, Sood AB, Corrado GS, Peng L, Webster DR. Using a Deep Learning Algorithm and Integrated Gradients Explanation to Assist Grading for Diabetic Retinopathy. Ophthalmology. 2019 Apr;126(4):552-564.

11. Compulink Healthcare Solutions. Compulink launches Advantage SMART Practice Suit of Aritifical Intelligence Solutions. Available at: https://www.compulinkadvantage.com/press-release/compulink-launches-advantage-smart-practice-suite-of-artificial-intelligence-solutions/. Accessed 8/28/19.

12. Advanced Data Systems Corporation. Employ the Brilliance of AI to Maximize Your Revenue Cycle Management Process. Available at: https://www.adsc.com/blog/brilliance-ai-maximize-revenue-cycle-management-process. Accessed 8/28/19.

13. AI System that Frees Doctors to Focus on Patients in Exam Room. Review of Optometric Business. Available at: https://reviewob.com/ai-system-that-frees-doctors-to-focus-on-patients-in-exam-room/. Accessed 8/28/19.

14. Dietsche E. Nuance’s AI makeover to clinical documentation takes exam room to the future. MedCity News. Available at: https://medcitynews.com/2019/06/nuance-ai-exam-room/. Accessed 8/28/19.