IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0231166.html
   My bibliography  Save this article

Opening the black box of artificial intelligence for clinical decision support: A study predicting stroke outcome

Author

Listed:
  • Esra Zihni
  • Vince Istvan Madai
  • Michelle Livne
  • Ivana Galinovic
  • Ahmed A Khalil
  • Jochen B Fiebach
  • Dietmar Frey

Abstract

State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide clinical decision support systems to physicians. Modern ML approaches such as artificial neural networks (ANNs) and tree boosting often perform better than more traditional methods like logistic regression. On the other hand, these modern methods yield a limited understanding of the resulting predictions. However, in the medical domain, understanding of applied models is essential, in particular, when informing clinical decision support. Thus, in recent years, interpretability methods for modern ML methods have emerged to potentially allow explainable predictions paired with high performance. To our knowledge, we present in this work the first explainability comparison of two modern ML methods, tree boosting and multilayer perceptrons (MLPs), to traditional logistic regression methods using a stroke outcome prediction paradigm. Here, we used clinical features to predict a dichotomized 90 days post-stroke modified Rankin Scale (mRS) score. For interpretability, we evaluated clinical features’ importance with regard to predictions using deep Taylor decomposition for MLP, Shapley values for tree boosting and model coefficients for logistic regression. With regard to performance as measured by Area under the Curve (AUC) values on the test dataset, all models performed comparably: Logistic regression AUCs were 0.83, 0.83, 0.81 for three different regularization schemes; tree boosting AUC was 0.81; MLP AUC was 0.83. Importantly, the interpretability analysis demonstrated consistent results across models by rating age and stroke severity consecutively amongst the most important predictive features. For less important features, some differences were observed between the methods. Our analysis suggests that modern machine learning methods can provide explainability which is compatible with domain knowledge interpretation and traditional method rankings. Future work should focus on replication of these findings in other datasets and further testing of different explainability methods.

Suggested Citation

  • Esra Zihni & Vince Istvan Madai & Michelle Livne & Ivana Galinovic & Ahmed A Khalil & Jochen B Fiebach & Dietmar Frey, 2020. "Opening the black box of artificial intelligence for clinical decision support: A study predicting stroke outcome," PLOS ONE, Public Library of Science, vol. 15(4), pages 1-15, April.
  • Handle: RePEc:plo:pone00:0231166
    DOI: 10.1371/journal.pone.0231166
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0231166
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0231166&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0231166?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Li Luo & Jialing Li & Chuang Liu & Wenwu Shen, 2019. "Using machine‐learning methods to support health‐care professionals in making admission decisions," International Journal of Health Planning and Management, Wiley Blackwell, vol. 34(2), pages 1236-1246, April.
    2. Jong Hyun Jhee & SungHee Lee & Yejin Park & Sang Eun Lee & Young Ah Kim & Shin-Wook Kang & Ja-Young Kwon & Jung Tak Park, 2019. "Prediction model development of late-onset preeclampsia using machine learning-based methods," PLOS ONE, Public Library of Science, vol. 14(8), pages 1-12, August.
    3. Effy Vayena & Alessandro Blasimme & I Glenn Cohen, 2018. "Machine learning in medicine: Addressing ethical challenges," PLOS Medicine, Public Library of Science, vol. 15(11), pages 1-4, November.
    4. Hamed Asadi & Richard Dowling & Bernard Yan & Peter Mitchell, 2014. "Machine Learning for Outcome Prediction of Acute Ischemic Stroke Post Intra-Arterial Therapy," PLOS ONE, Public Library of Science, vol. 9(2), pages 1-11, February.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Khishigsuren Davagdorj & Van Huy Pham & Nipon Theera-Umpon & Keun Ho Ryu, 2020. "XGBoost-Based Framework for Smoking-Induced Noncommunicable Disease Prediction," IJERPH, MDPI, vol. 17(18), pages 1-22, September.
    2. Indy Man Kit Ho & Kai Yuen Cheong & Anthony Weldon, 2021. "Predicting student satisfaction of emergency remote learning in higher education during COVID-19 using machine learning techniques," PLOS ONE, Public Library of Science, vol. 16(4), pages 1-27, April.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Isabel Marques & Zélia Serrasqueiro & Fernanda Nogueira, 2021. "Managers’ Competences in Private Hospitals for Investment Decisions during the COVID-19 Pandemic," Sustainability, MDPI, vol. 13(4), pages 1-14, February.
    2. Mashael Alsobhi & Harpreet Singh Sachdev & Mohamed Faisal Chevidikunnan & Reem Basuodan & Dhanesh Kumar K U & Fayaz Khan, 2022. "Facilitators and Barriers of Artificial Intelligence Applications in Rehabilitation: A Mixed-Method Approach," IJERPH, MDPI, vol. 19(23), pages 1-21, November.
    3. Charlotte Blease & Anna Kharko & Cosima Locher & Catherine M DesRoches & Kenneth D Mandl, 2020. "US primary care in 2029: A Delphi survey on the impact of machine learning," PLOS ONE, Public Library of Science, vol. 15(10), pages 1-18, October.
    4. Lepore, Dominique & Dolui, Koustabh & Tomashchuk, Oleksandr & Shim, Heereen & Puri, Chetanya & Li, Yuan & Chen, Nuoya & Spigarelli, Francesca, 2023. "Interdisciplinary research unlocking innovative solutions in healthcare," Technovation, Elsevier, vol. 120(C).
    5. Wenjuan Wang & Martin Kiik & Niels Peek & Vasa Curcin & Iain J Marshall & Anthony G Rudd & Yanzhong Wang & Abdel Douiri & Charles D Wolfe & Benjamin Bray, 2020. "A systematic review of machine learning models for predicting outcomes of stroke with structured data," PLOS ONE, Public Library of Science, vol. 15(6), pages 1-16, June.
    6. Yizhao Ni & Kathleen Alwell & Charles J Moomaw & Daniel Woo & Opeolu Adeoye & Matthew L Flaherty & Simona Ferioli & Jason Mackey & Felipe De Los Rios La Rosa & Sharyl Martini & Pooja Khatri & Dawn Kle, 2018. "Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis," PLOS ONE, Public Library of Science, vol. 13(2), pages 1-20, February.
    7. Lily Popova Zhuhadar & Miltiadis D. Lytras, 2023. "The Application of AutoML Techniques in Diabetes Diagnosis: Current Approaches, Performance, and Future Directions," Sustainability, MDPI, vol. 15(18), pages 1-24, September.
    8. Delahunty, Fionn & Arcan, Mihael & Johansson, Robert, 2019. "Passive Diagnosis of Mental Health Disorders Incorporating an Empathic Dialogue System," Thesis Commons 98c3q, Center for Open Science.
    9. Carl B. Roth & Andreas Papassotiropoulos & Annette B. Brühl & Undine E. Lang & Christian G. Huber, 2021. "Psychiatry in the Digital Age: A Blessing or a Curse?," IJERPH, MDPI, vol. 18(16), pages 1-32, August.
    10. Dessislava Pachamanova & Vera Tilson & Keely Dwyer-Matzky, 2022. "Case Article—Machine Learning, Ethics, and Change Management: A Data-Driven Approach to Improving Hospital Observation Unit Operations," INFORMS Transactions on Education, INFORMS, vol. 22(3), pages 178-187, May.
    11. Michael Gerlich, 2024. "Brace for Impact: Facing the AI Revolution and Geopolitical Shifts in a Future Societal Scenario for 2025–2040," Societies, MDPI, vol. 14(9), pages 1-17, September.
    12. Yao Tong & Beilei Lin & Gang Chen & Zhenxiang Zhang, 2022. "Predicting Continuity of Asthma Care Using a Machine Learning Model: Retrospective Cohort Study," IJERPH, MDPI, vol. 19(3), pages 1-18, January.
    13. Ignat Drozdov & Daniel Forbes & Benjamin Szubert & Mark Hall & Chris Carlin & David J Lowe, 2020. "Supervised and unsupervised language modelling in Chest X-Ray radiological reports," PLOS ONE, Public Library of Science, vol. 15(3), pages 1-16, March.
    14. Morley, Jessica & Machado, Caio C.V. & Burr, Christopher & Cowls, Josh & Joshi, Indra & Taddeo, Mariarosaria & Floridi, Luciano, 2020. "The ethics of AI in health care: A mapping review," Social Science & Medicine, Elsevier, vol. 260(C).
    15. Wieslaw L Nowinski & Varsha Gupta & Guoyu Qian & Wojciech Ambrosius & Radoslaw Kazmierski, 2014. "Population-Based Stroke Atlas for Outcome Prediction: Method and Preliminary Results for Ischemic Stroke from CT," PLOS ONE, Public Library of Science, vol. 9(8), pages 1-11, August.
    16. Thomas Molala & Jabulani Makhubele, 2021. "A conceptual framework for the ethical deployment of Artificial Intelligence in addressing mental health challenges: Guidelines for Social Workers," Technium Social Sciences Journal, Technium Science, vol. 24(1), pages 696-706, October.
    17. Siala, Haytham & Wang, Yichuan, 2022. "SHIFTing artificial intelligence to be responsible in healthcare: A systematic review," Social Science & Medicine, Elsevier, vol. 296(C).
    18. Zahlan, Ahmed & Ranjan, Ravi Prakash & Hayes, David, 2023. "Artificial intelligence innovation in healthcare: Literature review, exploratory analysis, and future research," Technology in Society, Elsevier, vol. 74(C).
    19. Mohammad I. Merhi, 2023. "An Assessment of the Barriers Impacting Responsible Artificial Intelligence," Information Systems Frontiers, Springer, vol. 25(3), pages 1147-1160, June.
    20. Jens Kjølseth Møller & Martin Sørensen & Christian Hardahl, 2021. "Prediction of risk of acquiring urinary tract infection during hospital stay based on machine-learning: A retrospective cohort study," PLOS ONE, Public Library of Science, vol. 16(3), pages 1-16, March.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0231166. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.