Artificial intelligence in the management and treatment of burns: a systematic review

Abstract

Background: Artificial intelligence (AI) is an innovative field with potential for improving burn care. This article provides an updated review on machine learning in burn care and discusses future challenges and the role of healthcare professionals in the successful implementation of AI technologies. Methods: A systematic search was carried out on MEDLINE, Embase and PubMed databases for English-language articles studying machine learning in burns. Articles were reviewed quantitatively and qualitatively for clinical applications, key features, algorithms, outcomes and validation methods. Results: A total of 46 observational studies were included for review. Assessment of burn depth (n = 26), support vector machines (n = 19) and 10-fold cross-validation (n = 11) were the most common application, algorithm and validation tool used, respectively. Conclusion: AI should be incorporated into clinical practice as an adjunct to the experienced burns provider once direct comparative analysis to current gold standards outlining its benefits and risks have been studied. Future considerations must include the development of a burn-specific common framework. Authors should use common validation tools to allow for effective comparisons. Level I/II evidence is required to produce robust proof about clinical and economic impacts.

Keywords

Artificial intelligence / Machine learning / Computer vision / Burn / Neural networks

References

[1] WHO. The global burden of disease: 2004 update. Geneva, Switzerland: World Health Organisation, 2008.

[2] Bodenheimer T, Sinsky C. From triple to quadruple aim: care of the patient requires care of the provider. Ann Fam Med. 2014; 12: 573-6. doi: 10.1370/afm.1713.

[3] Carson E. IBM Watson Health computes a pair of new solutions to improve healthcare data and security. TechRepublic, 2015.

[4] Kanevsky J, Corban J, Gaster R, Kanevsky A, Lin S, Gilardino M. Big data and machine learning in plastic surgery: a new frontier in surgical innovation. Plast Reconstr Surg. 2016; 137: 890e-7. doi: 10.1097/PRS.0000000000002088.

[5] Bellman R.An introduction to artificial intelligence: Can computers think? Boston, USA: Thomson Course Technology, 1978.

[6] Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017; 69: S36-40. doi: 10.1016/j.metabol.2017.01.011.

[7] Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019; 25: 44-56. doi: 10.1038/s41591-018-0300-7.

[8] Sevakula RK, Au-Yeung WTM, Singh JP, Heist EK, Isselbacher EM, Armoundas AA. State-of-the-art machine learning techniques aiming to improve patient outcomes pertaining to the cardiovascular system. J Am Heart Assoc. 2020; 9: e013924. doi: 10.1161/JAHA.119.013924.

[9] da Silva IN, Hernane Spatti D, Andrade Flauzino R, Liboni LHB, dos Reis Alves SF, da Silva IN, et al. Artificial Neural Network Architectures and Training Processes. Artif. Neural Networks, Springer International Publishing; 2017, p. 21-8. doi: 10.1007/978-3-319-43162-8_2.

[10] Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nat Med. 2019; 25: 24-9. doi: 10.1038/s41591-018-0316-z.

[11] Egmont-Petersen M, De Ridder D, Handels H. Image processing with neural networks-a review. Pattern Recognit. 2002; 35: 2279-301. doi: 10.1016/S0031-3203(01)00178-9.

[12] Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial intelligence in surgery: promises and perils. Ann Surg. 2018; 268: 70-6. doi: 10.1097/SLA.0000000000002693.

[13] Szegedy C, Liu W, Sermanet P, Reed S, Anguelov D, Erhan D, et al. Going deeper with convolutions. In: , 2014.

[14] Szegedy C, Liu W, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. The IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA: IEEE.

[15] Zeng X, Ouyang W, Yan J, Li H, Xiao T, Wang K, et al. Crafting GBD-net for object detection. IEEE Trans Pattern Anal Mach Intell. 2016; 40: 2109-23.

[16] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-December, IEEE Computer Society; 2016, p. 770-8. doi: 10.1109/CVPR.2016.90.

[17] Nadkarni PM, Ohno-Machado L, Chapman WW. Natural language processing: an introduction. J Am Med Inform Assoc. 2011; 18: 544-51. doi: 10.1136/amiajnl-2011-000464.

[18] Liu NT, Salinas J. Machine learning in burn care and research: a systematic review of the literature. Burns. 2015; 41: 1636-41. doi: 10.1016/j.burns.2015.07.001.

[19] Jones AD, Graff JP, Darrow M, Borowsky A, Olson KA, Gandour-Edwards R, et al. Impact of pre-analytical variables on deep learning accuracy in histopathology. Histopathology. 2019; 75: 39-53. doi: 10.1111/his.13844.

[20] Frye KE, Izenberg SD, Williams MD, Luterman A. Simulated biologic intelligence used to predict length of stay and survival of burns. J Burn Care Rehabil. 1996; 17: 540-6. doi: 10.1097/00004630-199611000-00011.

[21] Estahbanati HK, Bouduhi N. Role of artificial neural networks in prediction of survival of burn patients-a new approach. Burns. 2002; 28: 579-86. doi: 10.1016/S0305-4179(02)00045-1.

[22] Patil BM, Joshi RC, Toshniwal D, Biradar S. A new approach: role of data mining in prediction of survival of burn patients. J Med Syst. 2011; 35: 1531-42. doi: 10.1007/s10916-010-9430-2.

[23] Izamis ML, Uygun K, Sharma NS, Uygun B, Yarmush ML, Berthiaume F. Development of metabolic indicators of burn injury: very low density lipoprotein (VLDL) and acetoacetate are highly correlated to severity of burn injury in rats. Metabolites. 2012; 2: 458-78. doi: 10.3390/metabo2030458.

[24] Jiménez F, Sánchez G, Juárez JM.Multi-objective evolutionary algorithms for fuzzy classification in survival prediction. Artif Intell Med. 2014; 60: 197-219. doi: 10.1016/j.artmed.2013.12.006.

[25] Stylianou N, Akbarov A, Kontopantelis E, Buchan I, Dunn KW. Mortality risk prediction in burn injury: comparison of logistic regression with machine learning approaches. Burns. 2015; 41: 925-34. doi: 10.1016/j.burns.2015.03.016.

[26] Huang Y, Zhang L, Lian G, Zhan R, Xu R, Huang Y, et al. A novel mathematical model to predict prognosis of burnt patients based on logistic regression and support vector machine. Burns. 2016; 42: 291-9. doi: 10.1016/j.burns.2015.08.009.

[27] Cobb AN, Daungjaiboon W, Brownlee SA, Baldea AJ, Sanford AP, Mosier MM, et al. Seeing the forest beyond the trees: predicting survival in burn patients with machine learning. Am J Surg. 2018; 215: 411-6. doi: 10.1016/j.amjsurg.2017.10.027.

[28] Acha B, Serrano C, Acha JI, Roa LM. CAD tool for burn diagnosis. Information Processing in Medical Imaging. 2003; 2732: 294-305. doi: 10.1007/978-3-540-45087-0_25.

[29] Acha B, Serrano C, Acha JI, Roa LM. Segmentation and classification of burn images by color and texture information. J Biomed Opt. 2005; 10: 034014. doi: 10.1117/1.1921227.

[30] Heredia-Juesas J, Thatcher JE, Lu Y, Squiers JJ, King D, Fan W, et al. Non-invasive optical imaging techniques for burn-injured tissue detection for debridement surgery. Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, vol. 2016-October, Institute of Electrical and Electronics Engineers Inc.; 2016, p. 2893-6. doi: 10.1109/EMBC.2016.7591334.

[31] Wang P, Cao Y, Yin M, Li Y, Wu J. A burn depth detection system based on near infrared spectroscopy and ensemble learning. Rev Sci Instrum. 2017; 88. doi: 10.1063/1.4997121.

[32] Kuan PN, Chua S, Safawi EB, Wang HH, Tiong W. A comparative study of the classification of skin burn depth in human. JournalUtemEduMy, 2017; 9: 15.

[33] Heredia-Juesas J, Graham K, Thatcher JE, Fan W, Dimaio JM, Martinez-Lorenzo JA. Merging of Classifiers for Enhancing Viable vs Non-Viable Tissue Discrimination on Human Injuries. Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, 2018-July, Honolulu, HI, USA: IEEE; 2018; 9: 726. doi: 10.1109/EMBC.2018.8512378.

[34] Heredia-Juesas J, Grahaml K, Thatcher JE, Fan W, Michael Dimaio J, Martinez-Lorenzo JA. Mahalanobis Outier Removal for Improving the Non-Viable Detection on Human Injuries. IEEE Engineering in Medicine and Biology Society, 18-21 July 2018, Honolulu, HI, USA: Institute of Electrical and Electronics Engineers Inc.; 2018, p. 698-701. doi: 10.1109/EMBC.2018.8512321.

[35] Martínez-Jiménez MA, Ramirez-GarciaLuna JL, Kolosovas-Machuca ES, Drager J, Gonzalez FJ. Development and validation of an algorithm to predict the treatment modality of burn wounds using thermographic scans: prospective cohort study. PLoS One. 2018; 13: e0206477. doi: 10.1371/journal.pone.0206477.

[36] Heredia-Juesas J, Thatcher JE, Lu Y, Squiers JJ, King D, Fan W, et al. Burn-injured tissue detection for debridement surgery through the combination of non-invasive optical imaging techniques. Biomed Opt Express. 2018; 9: 1809. doi: 10.1364/boe.9.001809.

[37] Rangaraju LP, Kunapuli G, Every D, Ayala OD, Ganapathy P, Mahadevan-Jansen A. Classification of burn injury using Raman spectroscopy and optical coherence tomography: an ex-vivo study on porcine skin. Burns. 2019; 45: 659-70. doi: 10.1016/j.burns.2018.10.007.

[38] Wang P, Cao Y, Yin M, Li Y, Lv S, Huang L, et al. Full-field burn depth detection based on near-infrared hyperspectral imaging and ensemble regression. Rev Sci Instrum. 2019; 90: 064103. doi: 10.1063/1.5034503.

[39] Yadav DP, Sharma A, Singh M, Goyal A. Feature extraction based machine learning for human burn diagnosis from burn images. IEEE J Transl Eng Heal Med. 2019; 7: 1800507. doi: 10.1109/JTEHM.2019.2923628.

[40] Serrano C, Acha B, Gómez-Cía T, Acha JI, Roa LM. A computer assisted diagnosis tool for the classification of burns by depth of injury. Burns. 2005; 31: 275-81. doi: 10.1016/j.burns.2004.11.019.

[41] Cirillo MD, Mirdell R, Sjöberg F, Pham TD. Time-independent prediction of burn depth using deep convolutional neural networks. J Burn Care Res. 2019; 40: 857-63. doi: 10.1093/jbcr/irz103.

[42] Rowland R, Ponticorvo A, Baldado M, Kennedy GT, Burmeister DM, Christy RJ, et al. Burn wound classification model using spatial frequency-domain imaging and machine learning. J Biomed Opt. 2019; 24: 1-9. doi: 10.1117/1.JBO.24.5.056007.

[43] Jiao C, Su K, Xie W, Ye Z. Burn image segmentation based on mask regions with convolutional neural network deep learning framework: more accurate and more convenient. Burn Trauma. 2019; 7: 1-14. doi: 10.1186/s41038-018-0137-9.

[44] Chauhan J, Goyal P. BPBSAM: body part-specific burn severity assessment model. Burns. 2020; 46: 1407-23. doi: 10.1016/j.burns.2020.03.007.

[45] Wang Y, Ke Z, He Z, Chen X, Zhang Y, Xie P, et al. Real-time burn depth assessment using artificial networks: a large-scale, multicentre study. Burns. 2020; 46: 1829-38. doi: 10.1016/j.burns.2020.07.010.

[46] Wantanajittikul K, Auephanwiriyakul S, Theera-Umpon N, Koanantakool T. Automatic segmentation and degree identification in burn color images. Biomedical Engineering International Conference. 29-31 Jan 2012. Chiang Mai, Thailand: IEEE; 2012, p. 169-73. doi: 10.1109/BMEiCon.2012.6172044.

[47] Acha B, Serrano C, Fondon I, Gomez-Cia T. Burn depth analysis using multidimensional scaling applied to psychophysical experiment data. IEEE Trans Med Imaging. 2013; 32: 1111-20. doi: 10.1109/TMI.2013.2254719.

[48] Suvarna M, Niranjan UC. Classification of skin burn images. Int J Comput Sci Inf Technol. 2013; 5: 109-18. doi: 10.5121/ijcsit.2013.5109.

[49] Ganapathy P, Tamminedi T, Qin Y, Nanney L, Cardwell N, Pollins A, et al. Dual-imaging system for burn depth diagnosis. Burns. 2014; 40: 67-81. doi: 10.1016/j.burns.2013.05.004.

[50] Li W, Mo W, Zhang X, Squiers JJ, Lu Y, Sellke EW, et al. Outlier detection and removal improves accuracy of machine learning approach to multispectral burn diagnostic imaging. J Biomed Opt. 2015; 20: 121305. doi: 10.1117/1.jbo.20.12.121305.

[51] Serrano C, Boloix-Tortosa R, Gómez-Cía T, Acha B. Features identification for automatic burn classification. Burns. 2015; 41: 1883-90. doi: 10.1016/j.burns.2015.05.011.

[52] Badea MS, Vertan C, Florea C, Florea L, Bădoiu S. Severe burns assessment by joint color-thermal imagery and ensemble methods. International Conference on e-Health Networking, Applications and Services (Healthcom), Munich, Germany: Institute of Electrical and Electronics Engineers Inc.; 2016. doi: 10.1109/HealthCom.2016.7749450.

[53] Liu NT, Rizzo JA, Shields BA, Serio-Melvin ML, Christy RJ, Salinas J. Predicting the ability of wounds to heal given any burn size and fluid volume: an analytical approach. J Burn Care Res. 2018; 39: 661-9. doi: 10.1093/jbcr/iry021.

[54] Desbois A, Beguet F, Leclerc Y, González Hernández AE, Gervais S, Perreault I, et al. Predictive Modeling for personalized three-dimensional burn injury assessments. J Burn Care Res. 2020; 41: 121-30. doi: 10.1093/jbcr/irz114.

[55] Yamamura S, Kawada K, Takehira R, Nishizawa K, Katayama S, Hirano M, et al. Artificial neural network modeling to predict the plasma concentration of aminoglycosides in burn patients. Biomed Pharmacother. 2004; 58: 239-44. doi: 10.1016/j.biopha.2003.12.012.

[56] Yamamura S, Kawada K, Takehira R, Nishizawa K, Katayama S, Hirano M, et al. Prediction of aminoglycoside response against methicillin-resistant Staphylococcus aureus infection in burn patients by artificial neural network modeling. Biomed Pharmacother. 2008; 62: 53-8. doi: 10.1016/j.biopha.2007.11.004.

[57] Tran NK, Albahra S, Pham TN, Holmes JH, Greenhalgh D, Palmieri TL, et al. Novel application of an automated-machine learning development tool for predicting burn sepsis: proof of concept. Sci Rep. 2020; 10: 12354. doi: 10.1038/s41598-020-69433-w.

[58] Yang CS, Wei CP, Yuan CC, Schoung JY. Predicting the length of hospital stay of burn patients: comparisons of prediction accuracy among different clinical stages. Decis Support Syst. 2010; 50: 325-35. doi: 10.1016/j.dss.2010.09.001.

[59] Tran NK, Sen S, Palmieri TL, Lima K, Falwell S, Wajda J, et al. Artificial intelligence and machine learning for predicting acute kidney injury in severely burned patients: a proof of concept. Burns. 2019; 45: 1350-8. doi: 10.1016/j.burns.2019.03.021.

[60] Aghaei A, Soori H, Ramezankhani A, Mehrabi Y. Factors related to Pediatric unintentional Burns: the comparison of logistic regression and data mining algorithms. J Burn Care Res. 2019; 40: 606-12. doi: 10.1093/jbcr/irz066.

[61] Rashidi HH, Sen S, Palmieri TL, Blackmon T, Wajda J, Tran NK. Early recognition of burn-and trauma-related acute kidney injury: a pilot comparison of machine learning techniques. Sci Rep. 2020; 10: 1-9. doi: 10.1038/s41598-019-57083-6.

[62] Abubakar A, Ugail H, Ali Bukar M. Assessment of human skin Burns: a deep transfer learning approach. J Med Biol Eng. 2020; 40: 1-13. doi: 10.1007/s40846-020-00520-z.

[63] Hadley TD, Pettit RW, Malik T, Khoei AA, Salihu HM. Artificial intelligence in Global Health-a framework and strategy for adoption and sustainability. Int J Matern Child Heal AIDS. 2020; 9: 121-7. doi: 10.21106/ijma.296.

[64] Burns PB, Rohrich RJ, Chung KC. The levels of evidence and their role in evidence-based medicine. Plast Reconstr Surg. 2011; 128: 305-10. doi: 10.1097/PRS.0b013e318219c171.

[65] World Health Organisation (WHO).A WHO plan for burn prevention and care. Geneva, Switzerland: World Health Organization, 2008.

[66] Yeong EK, Hsiao TC, Huihua KC, Lin CW. Prediction of burn healing time using artificial neural networks and reflectance spectrometer. Burns. 2005; 31: 415-20. doi: 10.1016/j.burns.2004.12.003.

[67] Tran H, Le T, Le T, Nguyen T. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series. Lect. Notes Inst. Comput. Sci. Soc. Telecommun. Eng. LNICST, vol. 165, Germany: Springer Verlag; 2016, p. 233-42. doi: 10.1007/978-3-319-29236-6_23.

[68] Tran H, Hoang Le T, Nguyen TT. The degree of skin Burns images recognition using convolutional neural network. Indian J Sci Technol. 2016; 9: 1. doi: 10.17485/ijst/2016/v9i45/106772.

[69] Cirillo MD, Mirdell R, Sjöberg F, Pham TD. Tensor decomposition for colour image segmentation of burn wounds. Sci Rep. 2019; 9: 1-13. doi: 10.1038/s41598-019-39782-2.

[70] King DR, Li W, Squiers JJ, Mohan R, Sellke E, Mo W, et al. Surgical wound debridement sequentially characterized in a porcine burn model with multispectral imaging. Burns. 2015; 41: 1478-87. doi: 10.1016/j.burns.2015.05.009.

[71] Horner GN, Agboola S, Jethwani K, Tan-McGrory A, Lopez L. Designing patient-Centered text messaging interventions for increasing physical activity among participants with type 2 diabetes: qualitative results from the text to move intervention. JMIR Mhealth Uhealth. 2017; 5: e54. doi: 10.2196/mhealth.6666.

[72] Ryu B, Kim N, Heo E, Yoo S, Lee K, Hwang H, et al. Impact of an electronic health record-integrated personal health record on patient participation in health care: development and randomized controlled trial of myhealthkeeper. J Med Internet Res. 2017; 19: e401. doi: 10.2196/jmir.8867.

[73] Harvey C, Koubek R, Bégat V, Jacob S. Usability evaluation of a blood glucose monitoring system with a spill-resistant vial, easier strip handling, and connectivity to a mobile app: improvement of patient convenience and satisfaction. J Diabetes Sci Technol. 2016; 10: 1136-41. doi: 10.1177/1932296816658058.

[74] Desbois A, Matei S, Perreault I, Beguet F, Gervais S, De Guise JA. The importance of a three-dimensional-based approach with personalized models for accurately assessing TBSA. J Burn Care Res. 2018; 39: 235-44. doi: 10.1097/BCR.0000000000000580.

[75] Tran NK, Sen S, Palmieri TL, Lima K, Falwell S, Wajda J, et al. Artificial intelligence and machine learning for predicting acute kidney injury in severely burned patients: a proof of concept. Burns. 2019; 45: 1350-8. doi: 10.1016/j.burns.2019.03.021.

[76] Soguero-Ruiz C, Fei WME, Jenssen R, Augestad KM, Álvarez JLR, Jiménez IM, et al. Data-driven temporal prediction of surgical site infection. AMIA Annu Symp Proceedings AMIA Symp. 2015; 2015: 1164-73.

[77] Maani CV, Hoffman HG, Morrow M, Maiers A, Gaylord K, McGhee LL, et al. Virtual reality pain control during burn wound debridement of combat-related burn injuries using robot-like arm mounted VR goggles. J Trauma-Inj Infect Crit Care. 2011; 71: S125-30. doi: 10.1097/TA.0b013e31822192e2.

[78] Bini SA, Shah RF, Bendich I, Patterson JT, Hwang KM, Zaid MB. Machine learning algorithms can use wearable sensor data to accurately predict six-week patient-reported outcome scores following joint replacement in a prospective trial. J Arthroplasty. 2019; 34: 2242-7. doi: 10.1016/j.arth.2019.07.024.

[79] Abernethy AP, Ahmad A, Zafar SY, Wheeler JL, Reese JB, Lyerly HK. Electronic patient-reported data capture as a foundation of rapid learning cancer care. Med Care. 2010; 48: S32-8. doi: 10.1097/MLR.0b013e3181db53a4.

[80] Friedman C, Shagina L, Lussier Y, Hripcsak G. Automated encoding of clinical documents based on natural language processing. J Am Med Inform Assoc. 2004; 11: 392-402. doi: 10.1197/jamia.M1552.

[81] Sadideen H, Goutos I, Kneebone R. Burns education: the emerging role of simulation for training healthcare professionals. Burns. 2017; 43: 34-40. doi: 10.1016/j.burns.2016.07.012.

[82] Greenfield MJ, Luck J, Billingsley ML, Heyes R, Smith OJ, Mosahebi A, et al. Demonstration of the effectiveness of augmented reality telesurgery in complex hand reconstruction in Gaza. Plast Reconstr Surg Glob Open. 2018; 6:e1708. doi: 10.1097/GOX.0000000000001708.

[83] Ribeiro MT, Singh S, Guestrin C. “Why should i trust you?” Explaining the predictions of any classifier. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-August- 2016, San Francisco, California, USA: Association for Computing Machinery, New York, United States; 2016, p. 1135-44. doi: 10.1145/2939672.2939778.

[84] Cabitza F, Rasoini R, Gensini GF. Unintended consequences of machine learning in medicine. JAMA. 2017; 318: 517-8. doi: 10.1001/jama.2017.7797.

[85] Jüni P, Altman DG, Egger M. Systematic reviews in health care: assessing the quality of controlled clinical trials. Br Med J. 2001; 323: 42-6. doi: 10.1136/bmj.323.7303.42.

[86] Zhou XH.Challenges and strategies in analysis of missing data. Biostat Epidemiol. 2020; 4: 15-23. doi: 10.1080/24709360.2018.1469810.

[87] Cismondi F, Fialho AS, Vieira SM, Reti SR, Sousa JMC, Finkelstein SN. Missing data in medical databases: impute, delete or classify? Artif Intell Med. 2013; 58: 63-72. doi: 10.1016/j.artmed.2013.01.003.

[88] Jerez JM, Molina I, García-Laencina PJ, Alba E, Ribelles N, Martín M, et al. Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artif Intell Med. 2010; 50: 105-15. doi: 10.1016/j.artmed.2010.05.002.

[89] Dunn K, Belson P, Collings J, Cussons P, Dickson B, Fowler A, et al. National Burn Care Review. 2001.

[90] Pearl J.Causality: models, reasoning, and inference. Cambridge, UK: Cambridge University Press, 2000.

[91] Shah NR. Health care in 2030: will artificial intelligence replace physicians? Ann Intern Med. 2019; 170: 407-8. doi: 10.7326/M19-0344.

[92] Price WN, Gerke S, Cohen IG.Potential liability for physicians using artificial intelligence. JAMA. 2019; 322: 1765-6. doi: 10.1001/jama.2019.15064.

[93] Wolff J, Pauling J, Keck A, Baumbach J. The economic impact of artificial intelligence in health care: systematic review. J Med Internet Res. 2020; 22:e16866. doi: 10.2196/16866.

[94] Mikk KA, Sleeper HA, Topol EJ. The pathway to patient data ownership and better health. JAMA. 2017; 318: 1433-4. doi: 10.1001/jama.2017.12145.

[95] Vollmer S, Mateen BA, Bohner G, Király FJ, Ghani R, Jonsson P, et al. Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness. BMJ. 2020; 368: l6927. doi: 10.1136/bmj.l6927.

[96] Wilson FP.Machine learning to predict acute kidney injury. Am J Kidney Dis. 2019; 0: 965. doi: 10.1053/j.ajkd.2019.08.010.