"The human body is a black box": supporting clinical decision-making with deep learning
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
Machine learning technologies are increasingly developed for use in healthcare. While research communities have focused on creating state-of-the-art models, there has been less focus on real world implementation and the associated challenges to fairness, transparency, and accountability that come from actual, situated use. Serious questions remain underexamined regarding how to ethically build models, interpret and explain model output, recognize and account for biases, and minimize disruptions to professional expertise and work cultures. We address this gap in the literature and provide a detailed case study covering the development, implementation, and evaluation of Sepsis Watch, a machine learning-driven tool that assists hospital clinicians in the early diagnosis and treatment of sepsis. Sepsis is a severe infection that can lead to organ failure or death if not treated in time and is the leading cause of inpatient deaths in US hospitals. We, the team that developed and evaluated the tool, discuss our conceptualization of the tool not as a model deployed in the world but instead as a socio-technical system requiring integration into existing social and professional contexts. Rather than focusing solely on model interpretability to ensure fair and accountable machine learning, we point toward four key values and practices that should be considered when developing machine learning to support clinical decision-making: rigorously define the problem in context, build relationships with stakeholders, respect professional discretion, and create ongoing feedback loops with stakeholders. Our work has significant implications for future research regarding mechanisms of institutional accountability and considerations for responsibly designing machine learning systems. Our work underscores the limits of model interpretability as a solution to ensure transparency, accuracy, and accountability in practice. Instead, our work demonstrates other means and goals to achieve FATML values in design and in practice.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“there has been increasing recent research efforts [8, 15, 22, 41, 58, 65] that highlight the importance of involving stakeholders to understand their practices and needs [15, 41, 65] and socio-environmental factors [8] for the design and evaluation of a system.”
From Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making (2023) · cites this paper as [58]
In the citing paper
“Despite a growing body of literature on both physician perspectives of sepsis CDS implementation [26-28] and sepsis machine learning algorithms, more research is needed to understand clinician views on black box machine learning models that do not explain their predictions in a way that humans can understand [29,30].”
From Integrating a Machine Learning System Into Clinical Workflows: Qualitative Study (2020) · cites this paper as [30]
In the citing paper
“although the field of explainable AI can contribute to trustworthy AI, it has its limits [83].”
Citations
Cites
Rogers, E. M., Singhal, A., & Quinlan, M. M. (2019) · An Integrated Approach to Communication Theory and Research · doi:10.4324/9780203710753-35 · Cited by 37,322
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450 · cited 2×
“challenges in healthcare [45, 59].”
BackgroundTo Err is Human: Building a Safer Health System
Hendee, W. R. (2001) · Journal of Vascular and Interventional Radiology · doi:10.1016/s1051-0443(01)70072-3 · Cited by 10,103
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“At the same time, concerns have been raised about the role machine learning technologies might play in exacerbating systemic inequities in healthcare, undercutting patient privacy, increasing surveillance of vulnerable populations, and “dehumanizing” medicine [17, 38, 41, 60].”
Backgroundboyd, D., & Crawford, K. (2012) · Information, Communication & Society · doi:10.1080/1369118x.2012.678878 · Cited by 5,479
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 1×
“Although there are emerging methods to improve explainability of RNNs, end users cannot contemplate the entire model and cannot reliably understand the relationships between model inputs and outputs [13, 32].”
MethodExplanation in Artificial Intelligence: Insights from the Social Sciences
Miller, T. (2017) · arXiv · doi:10.48550/arxiv.1706.07269 · Cited by 5,338
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Moons, K. G. M., Altman, D. G., Reitsma, J. B., Ioannidis, J. P. A., Macaskill, P., Steyerberg, E. W., Vickers, A. J., Ransohoff, D. F., & Collins, G. S. (2015) · Annals of Internal Medicine · doi:10.7326/m14-0698 · Cited by 5,147
Research works printed but not linked: 14
- Futoma , J. , Hariharan , S. and Heller , K . 2017. Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier . International Conference on Machine Learning. (Jun. 2017 ), 1--9. Futoma, J., Hariharan, S. and Heller, K. 2017. Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier. International Conference on Machine Learning. (Jun. 2017), 1--9.
- Gawande , A. 2010. The Velluvial Matrix. The New Yorker. (Jan . 2010 ). Gawande, A. 2010. The Velluvial Matrix. The New Yorker. (Jan. 2010).
- Green , B. and Chen , Y . 2019 . Disparate Interactions. ( New York, New York, USA , 2019 ), 90--99. Green, B. and Chen, Y. 2019. Disparate Interactions. (New York, New York, USA, 2019), 90--99.
- Kluttz , D.N. , Kohli , N. and Mulligan , D.K . 2020 . Shaping Our Tools: Contestability as a Means to Promote Responsible Algorithmic Decision Making in the Professions, in After the Dihital Tornado: Networks, Algorithms, Humanity . Combridge University Press . (2020). Kluttz, D.N., Kohli, N. and Mulligan, D.K. 2020. Shaping Our Tools: Contestability as a Means to Promote Responsible Algorithmic Decision Making in the Professions, in After the Dihital Tornado: Networks, Algorithms, Humanity. Combridge University Press. (2020).
- Lin , A.L. , Sendak , M.P. , Bedoya , A.D. , Clement , M.E. , Futoma , J. , Nichols , M. , Gao , M. , Heller , K. and O Brien , C. 2018. What Is Sepsis: Investigating the Heterogeneity of Patient Populations Captured by Different Sepsis Definitions. American Journal of Respiratory and Critical Care Medicine. (May 2018 ). Lin, A.L., Sendak, M.P., Bedoya, A.D., Clement, M.E., Futoma, J., Nichols, M., Gao, M., Heller, K. and OBrien, C. 2018. What Is Sepsis: Investigating the Heterogeneity of Patient Populations Captured by Different Sepsis Definitions. American Journal of Respiratory and Critical Care Medicine. (May 2018).
- Lipton , Z.C. 2017 . The Doctor Just Won't Accept That . Interpretable ML Symposium NeurIPS 2017 . (Nov. 2017). Lipton, Z.C. 2017. The Doctor Just Won't Accept That. Interpretable ML Symposium NeurIPS 2017. (Nov. 2017).
- Lipton , Z.C. 2016 . The Mythos of Model Interpretability. ICML Workshop on Human Interpretability. (2016). Lipton, Z.C. 2016. The Mythos of Model Interpretability. ICML Workshop on Human Interpretability. (2016).
- Nestor , B. , McDermott , M.B. , Chauhau , G. , Naumann , T. , Hughes , M.C. , Goldenberg , A. and Ghassemi , M . 2018. Rethinking Clinical Prediction: Why Machine learning Must Consider Year of Care and Feature Aggregation . Machine Learning for Health MLH Workshop at NeurIPS. (Nov. 2018 ). Nestor, B., McDermott, M.B., Chauhau, G., Naumann, T., Hughes, M.C., Goldenberg, A. and Ghassemi, M. 2018. Rethinking Clinical Prediction: Why Machine learning Must Consider Year of Care and Feature Aggregation. Machine Learning for Health MLH Workshop at NeurIPS. (Nov. 2018).
- Rhee , C. 2018 . Compliance With the National SEP-1 Quality Measure and Association With Sepsis Outcomes . Journal of the American Medical Association. 46 , 10 (Oct. 2018), 1585--1591. Rhee, C. et al. 2018. Compliance With the National SEP-1 Quality Measure and Association With Sepsis Outcomes. Journal of the American Medical Association. 46, 10 (Oct. 2018), 1585--1591.
- Saria , S. and Subbaswamy , A . 2019 . Tutorial: Safe and Reliable Machine Learning. ACM Conference on Fairness, Accountability, and Transparency. (Apr. 2019 ), 1--4. Saria, S. and Subbaswamy, A. 2019. Tutorial: Safe and Reliable Machine Learning. ACM Conference on Fairness, Accountability, and Transparency. (Apr. 2019), 1--4.
- Select Committee on Artificial Intelligence 2019. The National Artificial Intelligence Research and Development Strategic Plan: 2019 Update . National Science Technology Council . ( Jun. 2019 ). Select Committee on Artificial Intelligence 2019. The National Artificial Intelligence Research and Development Strategic Plan: 2019 Update. National Science Technology Council. (Jun. 2019).
- Sendak , M.P. et al . 2019 . Sepsis Watch : A Real-World Integration of Deep Learning into Routine Clinical Care. JMIR Preprints . (Jun. 2019). Sendak, M.P. et al. 2019. Sepsis Watch: A Real-World Integration of Deep Learning into Routine Clinical Care. JMIR Preprints. (Jun. 2019).
- Sendak , M.P. , Gao , M. , Nichols , M. , Lin , A. and Balu , S . 2019 . Machine Learning in Health Care: A Critical Appraisal of Challenges and Opportunities. eGEMs Generating Evidence and Methods to Improve Patient Outcomes. 7, 1 (Jan. 2019), 1--4. Sendak, M.P., Gao, M., Nichols, M., Lin, A. and Balu, S. 2019. Machine Learning in Health Care: A Critical Appraisal of Challenges and Opportunities. eGEMs Generating Evidence and Methods to Improve Patient Outcomes. 7, 1 (Jan. 2019), 1--4.
- Topol , E.J. Deep Medicine (p. 18). Basic Books . March 2019 . Topol, E.J. Deep Medicine (p. 18). Basic Books. March 2019.
Cited by
Items 301–321 of 321
Ali, A. (2026) · Annual Methodological Archive Research Review
Facilitating Human-Machine Teaming in Machine Learning Problem Formulation
Guo, M. (2025) · Carolina Digital Repository (University of North Carolina at Chapel Hill) · doi:10.17615/f81p-1318
Atmoko, R. A., Asriningtias, S. R., & Setiawan, A. B. (2026) · Advances in wireless technologies and telecommunication book series · doi:10.4018/979-8-3373-9124-3.ch013
A Strategic Guide to AI in Healthcare: From Awareness to Implementation
Ramachandran, M. (2026) · Routledge eBooks · doi:10.4324/9781042007721
A Human-Centered Explainability Framework for Medical AI Systems
Cadena-Yanez, M., Bernardini, A., & Gómez, M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-45467-6_25
Blansit, K. (2021) · eScholarship (California Digital Library)
Hanumanthgari, R. R. (2025) · International Journal of Advanced Artificial Intelligence Research
Ai-Driven Predictive Models for Maternal Mortality Reduction in Rural Nigeria: A Systematic Review
Igbokwe, B. I. (2026) · INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN · doi:10.56201/ijcsmt.vol.12.no1.2026.pg229.242
Lu, J., Sattler, A., Wang, S., Khaki, A. R., Callahan, A., Fleming, S., Fong, R., Ehlert, B., Li, R. C., Shieh, L., et al. (2022) · doi:10.3389/fdgth.2022.943768.s002
Cost-Driven Selective Information Control for Multi-Layered Neural Networks
Kamimura, R. (2021) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai53430.2021.00058
ШТУЧНИЙ ІНТЕЛЕКТ ЯК МЕХАНІЗМ РЕФОРМУВАННЯ ЛІДЕРСЬКОГО ПОТЕНЦІАЛУ В ПУБЛІЧНОМУ УПРАВЛІННІ
Хлановський, В. С. (2026) · Investytsiyi praktyka ta dosvid · doi:10.32702/2306-6814.2026.2.409
Learning-Driven Data Fabric Governance: Standards and Regulatory Compliance
S, S. P., Usharani, R., Uma, S., Devi, M. A., & Tamilmani, G. (2026) · Springer eBooks · doi:10.1007/978-3-032-09090-4_14
Pallothu, S. C., Suchitra, D., Babu, C. A., & Sreenivas, M. (2026) · International Journal of Allied Medical Sciences and Clinical Research · doi:10.61096/ijamscr.v14.iss2.2026.812-816
Gambetti, A., Han, Q., Soares, C., & Shen, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.04613
Wu, X., Sha, T., Hu, H., Sun, M., Wu, J., & Chen, Z. (2026) · PubMed Central · doi:10.12122/j.issn.1673-4254.2026.06.14
Eight Dimensions of Human-Machine Combination
Wilson, B., Natali, C., Roach, M., Rahat, A., Scott, D., Rawlinson, D. R., & Cabitza, F. (2026) · Frontiers in artificial intelligence and applications · doi:10.3233/faia260528
From Data to Practice: The Impact of Nursing Informatics on Clinical Decision-Making
Alshammari, R. G. F. (2024) · Review of Contemporary Philosophy
Refining Preventive Measures for Surgical Site Infections: Global Standards and Options
Shah, S. S., Gupta, A., Mehsam, S. A., Raheem, M. F., Jain, N., & Khalid, S. S. (2024) · African Journal of Biomedical Research · doi:10.53555/ajbr.v27i4s.6319
Gupta, A., & Swami, P. D. (2026) · Electronics · doi:10.3390/electronics15215195
Metadata
- Authors
- Sendak, M., Elish, M. C., Gao, M., Futoma, J., Ratliff, W., Nichols, M., Bedoya, A., Balu, S., & O'Brien, C.
- Affiliations
- Duke University (US)
- Data & Society Research Institute (US)
- Harvard University (US)
- Duke School of Medicine
- ORCID
- Venue
- Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2020-01-27
- Pages
- 99-109
- OpenAlex
- W3002972902
- Cited by
- 196
- References
- 49
- Citations by year
- 2026: 37 · 2025: 22 · 2024: 33 · 2023: 26 · 2022: 30 · 2021: 32 · 2020: 16
- FWCI
- 9.92
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- clinical decision support, socio-technical systems, model interpretability, stakeholder engagement, professional discretion, institutional accountability, responsible AI design, healthcare implementation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.