Parkinson's Disease 10 6월, 2022 읽기 시간: 3 mins

향후 AI 성능은 임상 판단을 앞지르게 될까요?

A thought-provoking final debate closed MDS Virtual Congress 2020. The motion—Will artificial intelligence outperform clinical judgment in the near future?—was defended by Professor Roongroj Bhidayasiri, Bangkok, Thailand, and opposed by Professor Christopher Goetz, Chicago, IL.

The MDS Virtual Congress 2020 ended with a final and thought-provoking discussion. On the topic of whether AI's performance will outperform clinical judgment in the future, Professor Roongroj Bhidayasiri of Bangkok, Thailand agreed, and Professor Christopher Goetz of Chicago, Illinois, disagreed.

Professor Bhidayasiri highlighted how artificial intelligence (AI) is improving neurologic practice and patient outcomes. Professor Goetz counterargued that it has never been about AI versus human abilities, and that AI and humans are most potent when they cooperate. AI cannot mimic a physician's empathy and neurologists will always be needed to refine digital and deep phenotyping for Parkinson's disease (PD), he said.

Professor Bidayashiri emphasized that AI is advancing neurological treatment and patient outcomes. In the case of Professor Koetsu, on the other hand, he countered that AI and humans are most likely when they collaborate rather than compete. He added that AI cannot mimic the empathy of doctors, and that neurologists will always play a role in improving the digital and deep phenotype of Parkinson's.

AI and humans are most potent when they cooperate

AI and humans are most likely when they work together.

The majority of voters—52% of 430 (and as it turned out, also Professor Bhidayasiri), agreed with Professor Goetz, whereas 25% voters agreed with Professor Bhidayasiri, and 24% voted for a tie.

Of the 430 voters, a majority of 52% agreed with Professor Koetsu (which turned out to have also been voted for by Professor Vidayashiri), while 25% agreed with Professor Bidayashiri and 24% tied the vote. threw the

AI can improve diagnostic accuracy

AI can increase the accuracy of diagnosis.

 

Defending the motion

in favor of the proposition

The process from first seeing a patient to validating a diagnosis of PD can be depicted as a funnel, explained Professor Bhidayasiri, with:

The process from first meeting with a patient to validating a diagnosis of Parkinson's disease can be likened to a funnel, explains Professor Vidayashiri:

  • a wide initial reasoning process, which benefits from clinical judgment rather than AI
  • Early reasoning processes that rely more on clinical judgment rather than AI are a large part of the funnel.
  • narrowing of diagnostic possibilities
  • 진단 가능성은 깔대기의 좁은 부분입니다.
  • further narrowing to validation of the diagnosis—at this point, AI has the potential to outperform the neurologist
  • 진단 결과를 검증하는 것까지 점점 깔대기는 좁아지며, 이때 AI의 잠재력은 신경학자를 능가할 수 있습니다.

AI cannot replace a neurologist’s empathy

AI는 신경학자의 공감능력을 대체할 수 없습니다.

The diagnostic accuracy of a PD diagnosis of 82.7% has not significantly improved over the past 25 years, he noted, but AI can improve diagnostic accuracy, for example:

그에 따르면 지난 25년간 82.7%라는 파킨슨병 진단 정확도는 대폭 향상되지 않았지만, 다음과 같이 AI를 통해 진단 정확도가 증가할 수 있습니다:

  • a risk algorithm can identify individuals at increased risk of a future diagnosis of PD

  • 리스크 알고리즘을 통해 향후 파킨슨병을 진단받을 가능성이 증가한 사람들을 식별할 수 있습니다.

  • a finger sensor can discriminate between the tremor of PD and essential tremor

  • 손가락 센서를 통해 파킨슨병으로 인한 떨림과 본태 떨림을 구분할 수 있습니다.

  • smartphone videos of finger tapping can quantify PD bradykinesia

  • 손가락 두드리기 검사의 스마트폰 영상을 통해 파킨슨병 운동완만증을 정량화할 수 있습니다.

  • digital phenotyping of voice can reveal early PD

  • 목소리의 디지털 표현형을 통해 초기 파킨슨병을 확인할 수 있습니다.

  • a variety of machine learning algorithms can provide critical upper and lower limb data and gait

  • 다양한 머신러닝 알고리즘을 통해 주요 상지 및 하지 데이터와 걸음걸이를 확인할 수 있습니다.

Mobile health technologies will play an increasing role in future neurologic practice for patients with PD, said Professor Bhidayasiri, and the MDS Task Force on Technology has developed a roadmap for their implementation.

비다야시리 교수에 따르면 모바일 건강 기술의 경우 향후 파킨슨병 환자의 신경 치료에 있어 점차 많은 역할을 할 수 있을 것이며, 운동 장애 학회의 기술 TF는 도입을 위한 로드맵을 만들었습니다.

 

Opposing the motion

발의안에 대한 반대

AI cannot replace the non-linear working methods used by neurologists

AI는 신경학자가 사용하는 비선형 작업 방법을 대체할 수 없습니다.

AI provides many opportunities for improving the management of patients with PD, agreed Professor Goetz. For example, machine learning approaches providing an objective assessment of freezing of gait, an objective severity score from smartphone sensor data, and automatic detection of dyskinesias.

AI는 파킨슨병 환자의 관리 향상 측면에서 많은 기회를 제공한다고 고에츠 교수는 설명합니다. 예를 들어 머신러닝의 경우 보행정지의 객관적 평가, 스마트폰 센서 데이터를 통해 객관적 중증도 점수를 제공하고, 그리고 운동이상증을 자동으로 감지합니다.

However, AI cannot replace the empathy, clinical judgement, and non-linear working methods used by neurologists to improve outcomes for their patients.

그럼에도 AI는 신경학자가 환자의 치료 결과를 발전시키기 위해 사용하는 공감능력, 임상 판단, 비선형 작업 방법을 대체할 수는 없습니다.

It has never been about AI or humans, he concluded. Competent professionals will always be needed to interpret and refine AI, and AI and humans are most potent when they cooperate.

It's never an AI vs. human battle, he concluded. Interpreting and improving AI always requires talented experts, and AI and humans are most likely when they work together.

참고문헌

  1. Vishnu VY, Vinny PW. Ann Indian Acad Neurol. 2019;22:264–6.
  2. Rizzo G, et al. Neurology. 2016;86:566–76.
  3. Semigran HL, et al. JAMA Int Med. 2016;176:1860–1.
  4. Schrag A, et al. Mov Disord. 2019;34:480–6.
  5. Thanawattano C, et al. BioMed Eng Online. 2015;14:1010. doi: 10.1186/s12938-015-0098-1.
  6. Williams S, et al. J Neurol Sci. 2020;416:117003. doi: 10.1016/j.jns.2020.117003.
  7. Tracy JM, et al. J Biomed Inform. 2020;104:103362. doi: 10.1016/j.jbi.2019.103362.
  8. Belic M, et al. Clin Neurol Neurosurg. 2019;184:105442. doi: 10.1016/j.clineuro.2019.105442.
  9. Espay AJ, et al. Mov Disord. 2019;34:657–63.
  10. Reches T, et al. Sensors 2020;20:4474.doi:10.3390/s20164474.
  11. Zhan A, et al. JAMA Neurol. 2018;75:876–80.