Artificial Intelligence-Enabled Evaluation of Pain Sketches to Predict Outcomes in Headache Surgery.
Journal
Plastic and reconstructive surgery
ISSN: 1529-4242
Titre abrégé: Plast Reconstr Surg
Pays: United States
ID NLM: 1306050
Informations de publication
Date de publication:
01 02 2023
01 02 2023
Historique:
entrez:
25
1
2023
pubmed:
26
1
2023
medline:
28
1
2023
Statut:
ppublish
Résumé
Recent evidence has shown that patient drawings of pain can predict poor outcomes in headache surgery. Given that interpretation of pain drawings requires some clinical experience, the authors developed a machine learning framework capable of automatically interpreting pain drawings to predict surgical outcomes. This platform will allow surgeons with less clinical experience, neurologists, primary care practitioners, and even patients to better understand candidacy for headache surgery. A random forest machine learning algorithm was trained on 131 pain drawings provided prospectively by headache surgery patients before undergoing trigger-site deactivation surgery. Twenty-four features were used to describe the anatomical distribution of pain on each drawing for interpretation by the machine learning algorithm. Surgical outcome was measured by calculating percentage improvement in Migraine Headache Index at least 3 months after surgery. Artificial intelligence predictions were compared with clinician predictions of surgical outcome to determine artificial intelligence performance. Evaluation of the data test set demonstrated that the algorithm was consistently more accurate (94%) than trained clinical evaluators. Artificial intelligence weighted diffuse pain, facial pain, and pain at the vertex as strong predictors of poor surgical outcome. This study indicates that structured algorithmic analysis is able to correlate pain patterns drawn by patients to Migraine Headache Index percentage improvement with good accuracy (94%). Further studies on larger data sets and inclusion of other significant clinical screening variables are required to improve outcome predictions in headache surgery and apply this tool to clinical practice.
Sections du résumé
BACKGROUND
Recent evidence has shown that patient drawings of pain can predict poor outcomes in headache surgery. Given that interpretation of pain drawings requires some clinical experience, the authors developed a machine learning framework capable of automatically interpreting pain drawings to predict surgical outcomes. This platform will allow surgeons with less clinical experience, neurologists, primary care practitioners, and even patients to better understand candidacy for headache surgery.
METHODS
A random forest machine learning algorithm was trained on 131 pain drawings provided prospectively by headache surgery patients before undergoing trigger-site deactivation surgery. Twenty-four features were used to describe the anatomical distribution of pain on each drawing for interpretation by the machine learning algorithm. Surgical outcome was measured by calculating percentage improvement in Migraine Headache Index at least 3 months after surgery. Artificial intelligence predictions were compared with clinician predictions of surgical outcome to determine artificial intelligence performance.
RESULTS
Evaluation of the data test set demonstrated that the algorithm was consistently more accurate (94%) than trained clinical evaluators. Artificial intelligence weighted diffuse pain, facial pain, and pain at the vertex as strong predictors of poor surgical outcome.
CONCLUSIONS
This study indicates that structured algorithmic analysis is able to correlate pain patterns drawn by patients to Migraine Headache Index percentage improvement with good accuracy (94%). Further studies on larger data sets and inclusion of other significant clinical screening variables are required to improve outcome predictions in headache surgery and apply this tool to clinical practice.
Identifiants
pubmed: 36696328
doi: 10.1097/PRS.0000000000009855
pii: 00006534-202302000-00034
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
405-411Informations de copyright
Copyright © 2022 by the American Society of Plastic Surgeons.
Déclaration de conflit d'intérêts
Disclosure:The authors have no conflicts of interest to disclose. None of the authors has a financial interest in any of the products, devices, or drugs mentioned in this article.
Références
Gfrerer L, Austen WG Jr, Janis JE. Migraine surgery. Plast Reconstr Surg Glob Open. 2019;7:e2291.
Janis JE, Barker JC, Javadi C, Ducic I, Hagan R, Guyuron B. A review of current evidence in the surgical treatment of migraine headaches. Plast Reconstr Surg. 2014;134(Suppl 2):131S–141S.
Gfrerer L, Hansdorfer MA, Ortiz R, et al. Patient pain sketches can predict surgical outcomes in trigger-site deactivation surgery for headaches. Plast Reconstr Surg. 2020;146:863–871.
Ortiz R, Gfrerer L, Hansdorfer MA, Nealon KP, Lans J, Austen WG Jr. Migraine surgery at the frontal trigger site: an analysis of intraoperative anatomy. Plast Reconstr Surg. 2020;145:523–530.
Ortiz R, Gfrerer L, Hansdorfer MA, Tsui J, Nealon KP, Austen WG Jr. A pain in the neck? Migraine surgery in patients with prior head or neck injury. Plast Reconstr Surg Glob Open. 2019;7(S-1):59–60.
Gfrerer L, Guyuron B. Surgical treatment of migraine headaches. Acta Neurol Belg. 2017;117:27–32.
Guyuron B. Migraine Surgery. New York: Thieme2018.
Guyuron B, Tucker T, Davis J. Surgical treatment of migraine headaches. Plast Reconstr Surg. 2002;109:2183–2189.
Chandawarkar A, Chartier C, Kanevsky J, Cress PE. A practical approach to artificial intelligence in plastic surgery. Aesthet Surg J Open Forum. 2020;2:ojaa001.
Johnson AEW, Aboab J, Raffa JD, et al. A comparative analysis of sepsis identification methods in an electronic database. Crit Care Med. 2018;46:494–499.
Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316:2402–2410.
Haenssle HA, Fink C, Schneiderbauer R, et al. Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol. 2018;29:1836–1842.
Bouletreau P, Makaremi M, Ibrahim B, Louvrier A, Sigaux N. Artificial intelligence: applications in orthognathic surgery. J Stomatol Oral Maxillofac Surg. 2019;120:347–354.
Hashimoto DA, Rosman G, Witkowski ER, et al. Computer vision analysis of intraoperative video: automated recognition of operative steps in laparoscopic sleeve gastrectomy. Ann Surg. 2019;270:414–421.
Nahar J, Imam T, Tickle KS, Chen YPP. Association rule mining to detect factors which contribute to heart disease in males and females. Expert Syst Appl. 2013;40:1086–1093.
Shaballout N, Aloumar A, Neubert TA, Dusch M, Beissner F. Digital pain drawings can improve doctors’ understanding of acute pain patients: survey and pain drawing analysis. JMIR Mhealth Uhealth. 2019;7:e11412.
Hüllemann P, Keller T, Kabelitz M, Freynhagen R, Tölle T, Baron R. Pain drawings improve subgrouping of low back pain patients. Pain Pract. 2017;17:293–304.
Voorhies RM, Jiang X, Thomas N. Predicting outcome in the surgical treatment of lumbar radiculopathy using the Pain Drawing Score, McGill Short Form Pain Questionnaire, and risk factors including psychosocial issues and axial joint pain. Spine J. 2007;7:516–524.
MacDowall A, Robinson Y, Skeppholm M, Olerud C. Pain drawings predict outcome of surgical treatment for degenerative disc disease in the cervical spine. Ups J Med Sci. 2017;122:194–200.
Guyuron B, Nahabet E, Khansa I, Reed D, Janis JE. The current means for detection of migraine headache trigger sites. Plast Reconstr Surg. 2015;136:860–867.
Chartier C, Gfrerer L, Austen WG. Ultrasonographic evidence of trapezius fascia thickening in patients undergoing trigger site deactivation surgery compared to healthy control. Paper presented at: 65th Annual Meeting of the Plastic Surgery Research Council Meeting; May 28–31, 2020; Toronto, Ontario, Canada.
Harris PA, Taylor R, Thielke R, Payne J, Gonzalez N, Conde JG. Research electronic data capture (REDCap): a metadata-driven methodology and workflow process for providing translational research informatics support. J Biomed Inform. 2009;42:377–381.
Janis JE, Hatef DA, Ducic I, et al. The anatomy of the greater occipital nerve: Part II. Compression point topography. Plast Reconstr Surg. 2010;126:1563–1572.
Janis JE, Hatef DA, Hagan R, et al. Anatomy of the supratrochlear nerve: implications for the surgical treatment of migraine headaches. Plast Reconstr Surg. 2013;131:743–750.
Mosser SW, Guyuron B, Janis JE, Rohrich RJ. The anatomy of the greater occipital nerve: implications for the etiology of migraine headaches. Plast Reconstr Surg. 2004;113:693–697; discussion 698–700.
Janis JE, Hatef DA, Ducic I, et al. Anatomy of the auriculotemporal nerve: variations in its relationship to the superficial temporal artery and implications for the treatment of migraine headaches. Plast Reconstr Surg. 2010;125:1422–1428.
Janis JE, Ghavami A, Lemmon JA, Leedy JE, Guyuron B. The anatomy of the corrugator supercilii muscle: Part II. Supraorbital nerve branching patterns. Plast Reconstr Surg. 2008;121:233–240.
Lee M, Brown M, Chepla K, et al. An anatomical study of the lesser occipital nerve and its potential compression points: implications for surgical treatment of migraine headaches. Plast Reconstr Surg. 2013;132:1551–1556.
Gfrerer L, Hulsen JH, McLeod MD, Wright EJ, Austen WG Jr. Migraine surgery: an all or nothing phenomenon? Prospective evaluation of surgical outcomes. Ann Surg. 2019;269:994–999.
Liu MT, Armijo BS, Guyuron B. A comparison of outcome of surgical treatment of migraine headaches using a constellation of symptoms versus botulinum toxin type A to identify the trigger sites. Plast Reconstr Surg. 2012;129:413–419.
Chung PW, Lee MJ, Park JW, et al. Differences of cluster headache on the basis of sex in the Korean cluster headache registry. Headache. 2019;59:1722–1730.
Guyuron B, Gatherwright J, Reed D, Ansari H, Knackstedt R. Treatment of dopplerable nummular headache with minimally invasive arterectomy under local anesthesia. J Plast Reconstr Aesthet Surg. 2018;71:1010–1014.
Rangwani S, Hehr J, Janis J. Clinical effectiveness of peripheral nerve blocks for diagnosis of migraine trigger points. Plast Reconstr Surg Glob Open. 2020;8(Suppl):107–108.