A scoping review of artificial intelligence applications in thoracic surgery

被引:13
作者
Seastedt, Kenneth P. [1 ]
Moukheiber, Dana [2 ]
Mahindre, Saurabh A. [3 ]
Thammineni, Chaitanya [4 ]
Rosen, Darin T. [5 ]
Watkins, Ammara A. [1 ]
Hashimoto, Daniel A. [6 ]
Hoang, Chuong D. [7 ]
Kpodonu, Jacques [8 ]
Celi, Leo A. [9 ]
机构
[1] Harvard Med Sch, Beth Israel Deaconess Med Ctr, Dept Surg, Boston, MA 02115 USA
[2] MIT, Lab Computat Physiol, 77 Massachusetts Ave, Cambridge, MA 02139 USA
[3] Univ Buffalo State Univ New York, Inst Computat & Data Sci, Buffalo, NY USA
[4] Univ Buffalo State Univ New York, HILS Lab, Buffalo, NY USA
[5] Harvard Med Sch, Beth Israel Deaconess Med Ctr, Dept Med, Boston, MA 02115 USA
[6] Harvard Med Sch, Massachusetts Gen Hosp, Dept Surg, Surg AI & Innovat Lab, Boston, MA 02115 USA
[7] NCI, Thorac Surg Branch, NIH, Bethesda, MD 20892 USA
[8] Harvard Med Sch, Beth Israel Deaconess Med Ctr, Dept Surg, Div Cardiac Surg, Boston, MA 02115 USA
[9] Harvard Med Sch, Beth Israel Deaconess Med Ctr, Div Pulm Crit Care & Sleep Med, Boston, MA 02115 USA
关键词
Artificial intelligence; Machine learning; Prediction; Survival; Complications; Algorithm; ESOPHAGEAL; PREDICTS; RISK;
D O I
10.1093/ejcts/ezab422
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
OBJECTIVES Machine learning (ML) has great potential, but there are few examples of its implementation improving outcomes. The thoracic surgeon must be aware of pertinent ML literature and how to evaluate this field for the safe translation to patient care. This scoping review provides an introduction to ML applications specific to the thoracic surgeon. We review current applications, limitations and future directions. METHODS A search of the PubMed database was conducted with inclusion requirements being the use of an ML algorithm to analyse patient information relevant to a thoracic surgeon and contain sufficient details on the data used, ML methods and results. Twenty-two papers met the criteria and were reviewed using a methodological quality rubric. RESULTS ML demonstrated enhanced preoperative test accuracy, earlier pathological diagnosis, therapies to maximize survival and predictions of adverse events and survival after surgery. However, only 4 performed external validation. One demonstrated improved patient outcomes, nearly all failed to perform model calibration and one addressed fairness and bias with most not generalizable to different populations. There was a considerable variation to allow for reproducibility. CONCLUSIONS There is promise but also challenges for ML in thoracic surgery. The transparency of data and algorithm design and the systemic bias on which models are dependent remain issues to be addressed. Although there has yet to be widespread use in thoracic surgery, it is essential thoracic surgeons be at the forefront of the eventual safe introduction of ML to the clinic and operating room.
引用
收藏
页码:239 / 248
页数:10
相关论文
共 44 条
[1]   A "datathon" model to support cross-disciplinary collaboration [J].
Aboab, Jerome ;
Celi, Leo Anthony ;
Charlton, Peter ;
Feng, Mengling ;
Ghassemi, Mohammad ;
Marshall, Dominic C. ;
Mayaud, Louis ;
Naumann, Tristan ;
McCague, Ned ;
Paik, Kenneth E. ;
Pollard, Tom J. ;
Resche-Rigon, Matthieu ;
Salciccioli, Justin D. ;
Stone, David J. .
SCIENCE TRANSLATIONAL MEDICINE, 2016, 8 (333)
[2]   Analysis of survival for lung cancer resections cases with fuzzy and soft set theory in surgical decision making [J].
Alcantud, Jose Carlos R. ;
Varela, Gonzalo ;
Santos-Buitrago, Beatriz ;
Santos-Garcia, Gustavo ;
Jimenez, Marcelo F. .
PLOS ONE, 2019, 14 (06)
[3]  
[Anonymous], 2021, J THORAC CARDIOV SUR, V161, P341
[4]   End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography [J].
Ardila, Diego ;
Kiraly, Atilla P. ;
Bharadwaj, Sujeeth ;
Choi, Bokyung ;
Reicher, Joshua J. ;
Peng, Lily ;
Tse, Daniel ;
Etemadi, Mozziyar ;
Ye, Wenxing ;
Corrado, Greg ;
Naidich, David P. ;
Shetty, Shravya .
NATURE MEDICINE, 2019, 25 (06) :954-+
[5]   Sizing up big data [J].
Banks, Marcus A. .
NATURE MEDICINE, 2020, 26 (01) :5-6
[6]   Digital Health Primer for Cardiothoracic Surgeons [J].
Baxter, Ronald D. ;
Fann, James I. ;
Lobdell, Kevin .
ANNALS OF THORACIC SURGERY, 2020, 110 (02) :364-372
[7]   Using machine learning to predict early readmission following esophagectomy (Publication with Expression of Concern) [J].
Bolourani, Siavash ;
Tayebi, Mohammad A. ;
Diao, Li ;
Wang, Ping ;
Patel, Vihas ;
Manetta, Frank ;
Lee, Paul C. .
JOURNAL OF THORACIC AND CARDIOVASCULAR SURGERY, 2021, 161 (06) :1926-+
[8]   Predicting respiratory failure after pulmonary lobectomy using machine learning techniques (vol 168, pg P743, 2020) [J].
Bolourani, Siavash ;
Wang, Ping ;
Patel, Vihas M. ;
Manetta, Frank ;
Lee, Paul C. .
SURGERY, 2021, 169 (04) :1001-1001
[9]   Predicting respiratory failure after pulmonary lobectomy using machine learning techniques [J].
Bolourani, Siavash ;
Wang, Ping ;
Patel, Vihas M. ;
Manetta, Frank ;
Lee, Paul C. .
SURGERY, 2020, 168 (04) :743-752
[10]  
Celi LA, 2019, LANCET DIGIT HEALTH, V1, pE255, DOI 10.1016/s2589-7500(19)30127-x