Opal: an implementation science tool for machine learning clinical decision support in anesthesia

Journal of Clinical Monitoring and Computing - Tập 36 Số 5 - Trang 1367-1377 - 2022
Andrew Bishara1, Andrew Wong2, Linshanshan Wang3, Manu Chopra3, Wudi Fan3, Alan J. Lin3, Nicholas Fong4, Aditya Palacharla3, Jon Spinner1, Rachelle Armstrong1, Mark J. Pletcher5, Dmytro Lituiev6, Dexter Hadley6, Atul J. Butte6
1Department of Anesthesia and Perioperative Care, University of California San Francisco, San Francisco, 550 16th St., San Francisco, CA, 94158, USA
2School of Medicine, University of California San Francisco, San Francisco, CA, USA
3Undergraduate Studies, University of California Berkeley, Berkeley, CA, USA
4Department of Cellular and Molecular Pharmacology, University of California, San Francisco, San Francisco, CA, USA
5Department of Epidemiology and Biostatistics , University of California, San Francisco, San Francisco, CA, USA
6Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA

Tóm tắt

AbstractOpal is the first published example of a full-stack platform infrastructure for an implementation science designed for ML in anesthesia that solves the problem of leveraging ML for clinical decision support. Users interact with a secure online Opal web application to select a desired operating room (OR) case cohort for data extraction, visualize datasets with built-in graphing techniques, and run in-client ML or extract data for external use. Opal was used to obtain data from 29,004 unique OR cases from a single academic institution for pre-operative prediction of post-operative acute kidney injury (AKI) based on creatinine KDIGO criteria using predictors which included pre-operative demographic, past medical history, medications, and flowsheet information. To demonstrate utility with unsupervised learning, Opal was also used to extract intra-operative flowsheet data from 2995 unique OR cases and patients were clustered using PCA analysis and k-means clustering. A gradient boosting machine model was developed using an 80/20 train to test ratio and yielded an area under the receiver operating curve (ROC-AUC) of 0.85 with 95% CI [0.80–0.90]. At the default probability decision threshold of 0.5, the model sensitivity was 0.9 and the specificity was 0.8. K-means clustering was performed to partition the cases into two clusters and for hypothesis generation of potential groups of outcomes related to intraoperative vitals. Opal’s design has created streamlined ML functionality for researchers and clinicians in the perioperative setting and opens the door for many future clinical applications, including data mining, clinical simulation, high-frequency prediction, and quality improvement.

Từ khóa


Tài liệu tham khảo

Obermeyer Z, Emanuel EJ. Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med. 2016;13:1216–9.

Rajkomar A, Oren E, Chen K, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018;1(1):18.

Hatib F, Jian Z, Buddi S, et al. Machine-learning algorithm to predict hypotension based on high-fidelity arterial pressure waveform analysis. Anesthesiology. 2018;129(4):663–74.

Safavi KC, Khaniyev T, Copenhaver M, et al. Development and validation of a machine learning model to aid discharge processes for inpatient surgical care. JAMA Netw Open. 2019;2(12):e1917221.

Lee CK, Hofer I, Gabel E, Baldi P, Cannesson M. Development and validation of a deep neural network model for prediction of postoperative in-hospital mortality. Anesthesiology. 2018;129(4):649–62.

Hill BL, Brown R, Gabel E, et al. An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data. Br J Anaesth. 2019;123(6):877–86.

Park KW, Smaltz D, McFadden D, Souba W. The operating room dashboard. J Surg Res. 2010;164(2):294–300.

Franklin A, Gantela S, Shifarraw S, et al. Dashboard visualizations: Supporting real-time throughput decision-making. J Biomed Inform. 2017;71:211–21.

Stonemetz J. Anesthesia information management systems marketplace and current vendors. Anesthesiol Clin. 2011;29(3):367–75.

Shah NJ, Tremper KK, Kheterpal S. Anatomy of an anesthesia information management system. Anesthesiol Clin. 2011;29(3):355–65.

Simpao AF, Rehman MA. Anesthesia information management systems. Anesth Analg. 2018;127(1):90–4.

O’Sullivan CT, Dexter F, Lubarsky DA, Vigoda MM. Evidence-based management assessment of return on investment from anesthesia information management systems. AANA J. 2007;75(1):43–8.

Ehrenfeld JM, Rehman MA. Anesthesia information management systems: a review of functionality and installation considerations. J Clin Monit Comput. 2011;25(1):71–9.

Stol IS, Ehrenfeld JM, Epstein RH. Technology diffusion of anesthesia information management systems into Academic Anesthesia Departments in the United States. Anesth Analg. 2014;118(3):644–50.

Nair BG, Gabel E, Hofer I, Schwid HA, Cannesson M. Intraoperative clinical decision support for anesthesia. Anesth Analg. 2017;124(2):603–17.

Simpao AF, Tan JM, Lingappan AM, Gálvez JA, Morgan SE, Krall MA. A systematic review of near real-time and point-of-care clinical decision support in anesthesia information management systems. J Clin Monit Comput. 2017;31(5):885–94.

Chau A, Ehrenfeld JM. Using real-time clinical decision support to improve performance on perioperative quality and process measures. Anesthesiol Clin. 2011;29(1):57–69.

Kooij FO, Klok T, Hollmann MW, Kal JE. Decision support increases guideline adherence for prescribing postoperative nausea and vomiting prophylaxis. Anesth Analg. 2008;106(3):893–8.

Ehrenfeld JM, Epstein RH, Bader S, Kheterpal S, Sandberg WS. Automatic notifications mediated by anesthesia information management systems reduce the frequency of prolonged gaps in blood pressure documentation. Anesth Analg. 2011;113(2):356–63.

Nair BG, Horibe M, Newman S-F, Wu W-Y, Peterson GN, Schwid HA. Anesthesia information management system-based near real-time decision support to manage intraoperative hypotension and hypertension. Anesth Analg. 2014;118(1):206–14.

Kheterpal S, Gupta R, Blum JM, Tremper KK, O’Reilly M, Kazanjian PE. Electronic reminders improve procedure documentation compliance and professional fee reimbursement. Anesth Analg. 2007;104(3):592–7.

Blum JM, Stentz MJ, Maile MD, et al. Automated alerting and recommendations for the management of patients with preexisting hypoxia and potential acute lung injury: a pilot study. Anesthesiology. 2013;119(2):295–302.

Spring SF, Sandberg WS, Anupama S, Walsh JL, Driscoll WD, Raines DE. Automated documentation error detection and notification improves anesthesia billing performance. Anesthesiology. 2007;106(1):157–63.

Freundlich RE, Barnet CS, Mathis MR, Shanks AM, Tremper KK, Kheterpal S. A randomized trial of automated electronic alerts demonstrating improved reimbursable anesthesia time documentation. J Clin Anesth. 2013;25(2):110–4.

Nair BG, Newman S-F, Peterson GN, Schwid HA. Smart anesthesia manager (SAM)—a real-time decision support system for anesthesia care during surgery. IEEE Trans Biomed Eng. 2013;60(1):207–10.

Wijnberge M, Geerts BF, Hol L, et al. Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery. JAMA. 2020;323(11):1052.

Kellum JA, Lameire N, Aspelin P, et al. Kidney disease: Improving global outcomes (KDIGO) acute kidney injury work group. KDIGO clinical practice guideline for acute kidney injury. Kidney Int Suppl. 2012;2:1–138.

Luo X, Jiang L, Du B, et al. A comparison of different diagnostic criteria of acute kidney injury in critically ill patients. 2014;1–8.

Coquet, Adrien. "Sick.” From the Noun Project. Retrieved March 27, 2020.

Lareo, Sebastian Belalcazar. "Monitor.” From the Noun Project. Retrieved March 27, 2020.

Nociconist. "PHP.” From the Noun Project. Retrieved March 27, 2020.

Nociconist. "Database.” From the Noun Project. Retrieved March 27, 2020.

Aiden Icons. "Database.” From the Noun Project. Retrieved March 27, 2020.

Mbarki, Mohamed. "Machine Learning.” From the Noun Project. Retrieved March 27, 2020.

Product Pencil. "Deep Learning.” From the Noun Project. Retrieved March 27, 2020.

Thông tin
Thông tin xuất bản

Journal of Clinical Monitoring and Computing

Tập 36 Số 5

1367-1377

Thông tin tác giả