discussion

Tell me something interesting: : Clinical utility of machine learning prediction models in the ICU

Authors:

Bar Eini-Porat,

Uri ShalitAuthors Info & Claims

Volume 132, Issue C

https://doi.org/10.1016/j.jbi.2022.104107

Published: 01 August 2022 Publication History

Graphical abstract

Display Omitted

Highlights

•

Characterize ICU clinicians’ needs from machine learning-based prediction systems.

•

We identify multiple aspects in which these needs deviate from most current practice.

•

Desired prediction targets include patient trajectory and care prioritization.

•

Important aspects of trajectory prediction are clinical norm, trend and trend deviation .We obtained quantitative estimates of clinical utility of vital signs prediction. Derived utilities can be used to derive model evaluation metrics and loss functions.

•

We obtained quantitative estimates of clinical utility of vital signs prediction.

•

Derived utilities can be used to derive model evaluation metrics and loss functions.

Abstract

In recent years, extensive resources are dedicated to the development of machine learning (ML) based clinical prediction models for intensive care unit (ICU) patients. These models are transforming patient care into a collaborative human-AI task, yet prediction of patient-related events is mostly treated as a standalone goal, without considering clinicians’ roles, tasks or workflow in depth. We conducted a mixed methods study aimed at understanding clinicians’ needs and expectations from such systems, informing the design of machine learning based prediction models. Our findings identify several areas of focus where clinicians’ needs deviate from current practice, including desired prediction targets, timescales stemming from actionability requirements, and concerns regarding the evaluation and trust in these algorithms. Based on our findings, we suggest several design implications for ML-based prediction tools in the ICU.

References

[1]

S. Blecker, D. Sontag, L.I. Horwitz, G. Kuperman, H. Park, A. Reyentovich, S.D. Katz, Early Identification of Patients With Acute Decompensated Heart Failure, J. Cardiac Fail. 24 (2018) 357–362.

[2]

A.E.W. Johnson, M.M. Ghassemi, S. Nemati, K.E. Niehaus, D. Clifton, G.D. Clifford, Machine Learning and Decision Support in Critical Care, Proc. IEEE 104 (2016) 444–466.

[3]

K.E. Henry, D.N. Hager, P.J. Pronovost, S. Saria, A targeted real-time early warning score (TREWScore) for septic shock, Sci. Translat. Med. 7 (2015) 122–299.

[4]

M. Schvetz, L. Fuchs, V. Novack, R. Moskovitch, Outcomes prediction in longitudinal data: Study designs evaluation, use case in ICU acquired sepsis, J. Biomed. Inform. 117 (2021) 103734.

[5]

Y. Si, J. Du, Z. Li, X. Jiang, T. Miller, F. Wang, W.J. Zheng, K. Roberts, Deep representation learning of patient data from electronic health records (EHR): A systematic review, J. Biomed. Inform. 115 (2021) 103671.

Digital Library

[6]

M. Moor, B. Rieck, M. Horn, C.R. Jutzeler, K. Borgwardt, Early prediction of sepsis in the ICU using machine learning: a systematic review, Front. Med. 8 (2021) 348.

[7]

T. Desautels, J. Calvert, J. Hoffman, M. Jay, Y. Kerem, L. Shieh, D. Shimabukuro, U. Chettipally, M.D. Feldman, C. Barton, D.J. Wales, R. Das, Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach, JMIR Med. Informat. 4 (2016) e28.

[8]

S. Ghosh, J. Li, L. Cao, K. Ramamohanarao, Septic shock prediction for ICU patients via coupled hmm walking on sequential contrast patterns, J. Biomed. Inform. 66 (2017) 19–31.

Digital Library

[9]

A.-S. Poncette, C. Spies, L. Mosch, M. Schieler, S. Weber-Carstens, H. Krampe, F. Balzer, Clinical requirements of future patient monitoring in the intensive care unit: qualitative study, JMIR Med. Informat. 7 (2019) e13064.

[10]

O. Faust, Y. Hagiwara, T.J. Hong, O.S. Lih, U.R. Acharya, Deep learning for healthcare applications based on physiological signals: A review, Comput. Methods Programs Biomed. 161 (2018) 1–13.

[11]

L. Clifton, D.A. Clifton, M.A. Pimentel, P.J. Watkinson, L. Tarassenko, Gaussian processes for personalized e-health monitoring with wearable sensors, IEEE Trans. Biomed. Eng. 60 (2012) 193–197.

[12]

P. Schulam, S. Saria, A framework for individualizing predictions of disease trajectories by exploiting multi-resolution structure, in: Advances in Neural Information Processing Systems, vol. 28.

[13]

A.M. Alaa, J. Yoon, S. Hu, M. Van der Schaar, Personalized risk scoring for critical care prognosis using mixtures of Gaussian processes, IEEE Trans. Biomed. Eng. 65 (2017) 207–218.

[14]

H. Soleimani, A. Subbaswamy, S. Saria, Treatment-response models for counterfactual reasoning with continuous-time, continuous-valued interventions, in: Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, 2017.

[15]

G.W. Colopy, S.J. Roberts, D.A. Clifton, Bayesian optimization of personalized models for patient vital-sign monitoring, IEEE J. Biomed. Health Informat. 22 (2017) 301–310.

[16]

L.-F. Cheng, B. Dumitrascu, G. Darnell, C. Chivers, M. Draugelis, K. Li, B.E. Engelhardt, Sparse multi-output Gaussian processes for online medical time series prediction, BMC Med. Informat. Decision Making 20 (2020) 1–23.

[17]

N.L. Downing, J. Rolnick, S.F. Poole, E. Hall, A.J. Wessels, P. Heidenreich, L. Shieh, Electronic health record-based clinical decision support alert for severe sepsis: a randomised evaluation, BMJ Quality Saf. 28 (2019) 762–768.

[18]

A. Wong, E. Otles, J.P. Donnelly, A. Krumm, J. McCullough, O. DeTroyer-Cooley, J. Pestrue, M. Phillips, J. Konye, C. Penoza, et al., External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients, JAMA Int. Med. 181 (2021) 1065–1070.

[19]

J.L. Guidi, K. Clark, M.T. Upton, H. Faust, C.A. Umscheid, M.B. Lane-Fall, M.E. Mikkelsen, W.D. Schweickert, C.A. Vanzandbergen, J. Betesh, et al., Clinician perception of the effectiveness of an automated early warning and response system for sepsis in an academic medical center, Ann. Am. Thoracic Soc. 12 (2015) 1514–1519.

[20]

S. Tonekaboni, S. Joshi, M. D. McCradden, A. Goldenberg, What clinicians want: Contextualizing explainable machine learning for clinical end use, in: Proceedings of the 4th Machine Learning for Healthcare Conference, Proceedings of Machine Learning Research, PMLR, vol. 106, 2019, pp. 359–380.

[21]

O. Amir, B. J. Grosz, K. Z. Gajos, S. M. Swenson, L. M. Sanders, From care plans to care coordination: Opportunities for computer support of teamwork in complex healthcare, in: Proceedings of the 33rd annual ACM conference on human factors in computing systems, Association for Computing Machinery, New York, NY, USA, 2015, pp. 1419–1428.

[22]

M. Jacobs, J. He, M. F. Pradier, B. Lam, A. C. Ahn, T. H. McCoy, R. H. Perlis, F. Doshi-Velez, K. Z. Gajos, Designing ai for trust and collaboration in time-constrained medical decisions: A sociotechnical lens, in: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Association for Computing Machinery, New York, NY, USA, 2021, pp. 1–14.

[23]

G.J. Escobar, B.J. Turk, A. Ragins, J. Ha, B. Hoberman, S.M. LeVine, M.A. Ballesca, V. Liu, P. Kipnis, Piloting electronic medical record–based early detection of inpatient deterioration in community hospitals, J. Hospital Med. 11 (2016) S18–S24.

[24]

M. C. Elish, The stakes of uncertainty: developing and integrating machine learning in clinical care, in: Ethnographic Praxis in Industry Conference Proceedings, vol. 1, Wiley Online Library, pp. 364–380.

[25]

S. Malhotra, D. Jordan, E. Shortliffe, V.L. Patel, Workflow modeling in critical care: piecing together your own puzzle, J. Biomed. Inform. 40 (2007) 81–92.

Digital Library

[26]

V.L. Patel, J. Zhang, N.A. Yoskowitz, R. Green, O.R. Sayan, Translational cognition for decision support in critical care environments: a review, J. Biomed. Inform. 41 (2008) 413–431.

[27]

A.-S. Poncette, L. Mosch, C. Spies, M. Schmieding, F. Schiefenhövel, H. Krampe, F. Balzer, et al., Improvements in patient monitoring in the intensive care unit: survey study, J. Med. Internet Res. 22 (2020) e19091.

[28]

T. Foster-Hunt, A. Parush, J. Ellis, M. Thomas, J. Rashotte, Information structure and organisation in change of shift reports: An observational study of nursing hand-offs in a paediatric intensive care unit, Intensive Crit. Care Nurs. 31 (2015) 155–164.

[29]

R. Jääskeläinen, Think-aloud protocol, Handbook Translat. Stud. 1 (2010) 371–374.

[30]

A.E. Johnson, T.J. Pollard, L. Shen, H.L. Li-Wei, M. Feng, M. Ghassemi, B. Moody, P. Szolovits, L.A. Celi, R.G. Mark, Mimic-iii, a freely accessible critical care database, Sci. Data 3 (2016) 1–9.

[31]

A. Strauss, J. Corbin, Basics of qualitative research, Sage Publications (1990).

[32]

K. Holtzblatt, Contextual design, in: The human-computer interaction handbook, CRC Press, 2007, pp. 975–990.

[33]

K. Jung, S. Kashyap, A. Avati, S. Harman, H. Shaw, R. Li, M. Smith, K. Shum, J. Javitz, Y. Vetteth, et al., A framework for making predictive models useful in practice, J. Am. Med. Inform. Assoc. 28 (2021) 1149–1158.

[34]

H. Suresh, N. Hunt, A. Johnson, L. A. Celi, P. Szolovits, M. Ghassemi, Clinical intervention prediction and understanding with deep neural networks, in: F. Doshi-Velez, J. Fackler, D. Kale, R. Ranganath, B. Wallace, J. Wiens (Eds.), Proceedings of the 2nd Machine Learning for Healthcare Conference, Proceedings of Machine Learning Research, PMLR, vol. 68, 2017, pp. 322–337.

[35]

A.M. Alaa, M. van der Schaar, Bayesian inference of individualized treatment effects using multi-task Gaussian processes, Adv. Neural Inform. Process. Syst. 30 (2017).

[36]

A. Faiola, C. Newlon, Advancing critical care in the ICU: a human-centered biomedical data visualization systems, in: International Conference on Ergonomics and Health Aspects of Work with Computers, Springer, Berlin, Heidelberg, pp. 119–128.

[37]

A. Faiola, P. Srinivas, J. Duke, Supporting clinical cognition: a human-centered approach to a novel ICU information visualization dashboard, in: AMIA Annual Symposium Proceedings, vol. 2015, American Medical Informatics Association, p. 560.

[38]

J.R. Busemeyer, J.T. Townsend, Decision field theory: a dynamic-cognitive approach to decision making in an uncertain environment, Psychol. Rev. 100 (1993) 432.

[39]

S. Yang, K. Kalpakis, C. F. Mackenzie, L. G. Stansbury, D. M. Stein, T. M. Scalea, P. F. Hu, Online recovery of missing values in vital signs data streams using low-rank matrix completion, in: 2012 11th International Conference on Machine Learning and Applications, vol. 1, IEEE, pp. 281–287.

[40]

O. Linial, N. Ravid, D. Eytan, U. Shalit, Generative ODE modeling with known unknowns, in: Proceedings of the Conference on Health, Inference, and Learning, pp. 79–94.

[41]

Pragasan Dean Gopalan, Santosh Pershad, Decision-making in ICU – A systematic review of factors considered important by ICU clinician decision makers with regard to ICU triage decisions, Journal of Critical Care (2019) In press.

[42]

Q. Yang, A. Steinfeld, J. Zimmerman, Unremarkable ai: Fitting intelli-650gent decision support into critical, clinical decision-making processes, in:Proceedings of the 2019 CHI Conference on Human Factors in ComputingSystems, CHI ’19, Association for Computing Machinery, New York, NY,USA, 2019, p. 1–11.

[43]

A. Wassenaar, L. Schoonhoven, J.W. Devlin, van Haren, A.J. Slooter, P.G. Jorens, M. & van den Boogaard, Delirium prediction in the intensive care unit: comparison of two delirium prediction models, Critical Care 22 (1) (2018) 1–9.

Cited By

Yildirim NZlotnikov SVenkat AChawla GKim JBukowski LKahn JMccann JZimmerman J(2024)Investigating Why Clinicians Deviate from Standards of Care: Liberating Patients from Mechanical Ventilation in the ICUProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641982(1-15)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613904.3641982
Yildirim NZlotnikov SSayar DKahn JBukowski LAmin SRiman KDavis BMinturn JKing ARicketts DTang LSivaraman VPerer APreum SMcCann JZimmerman J(2024)Sketching AI Concepts with Capabilities and Examples: AI Innovation in the Intensive Care UnitProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641896(1-18)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613904.3641896
Liu JCapurro DNguyen AVerspoor K(2023)Attention-based multimodal fusion with contrast for robust clinical prediction in the face of missing modalitiesJournal of Biomedical Informatics10.1016/j.jbi.2023.104466145:COnline publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1016/j.jbi.2023.104466

Recommendations

Mortality Risk Evaluation: A Proposal for Intensive Care Units Patients Exploring Machine Learning Methods
Intelligent Systems
Abstract
The high availability of clinical data and a heterogeneous and complex patient population makes Intensive Care Units (ICUs) environments opportune for developing a system that analyzes large amounts of raw data, which human specialists can ...
ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU
Graphical abstract

Display Omitted
Highlights
- Directly interpret a model trained to predict ICU mortality, no surrogate prediction model needed.
- Convolutional Neural Nets offer performance comparable to Recurrent Neural Nets.
- A convolutional architecture can handle both static ...
Abstract
To improve the performance of Intensive Care Units (ICUs), the field of bio-statistics has developed scores which try to predict the likelihood of negative outcomes. These help evaluate the effectiveness of treatments and clinical practice, and ...
Mortality Prediction of ICU patients using Machine Leaning: A survey
ICCDA '17: Proceedings of the International Conference on Compute and Data Analysis

Recently health care researchers are working a lot on outcome prediction on Intensive Care Unit (ICU) and trauma. Outcome prediction in intensive care is a difficult process. Accurate synthesis of quality data and application of prior experience to the ...

Comments

Information & Contributors

Information

Published In

cover image Journal of Biomedical Informatics

Journal of Biomedical Informatics Volume 132, Issue C

Aug 2022

199 pages

ISSN:1532-0464

Issue’s Table of Contents

Elsevier Inc.

Publisher

Elsevier Science

San Diego, CA, United States

Publication History

Published: 01 August 2022

Author Tags

Author Tags

Qualifiers

Discussion

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 16 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Yildirim NZlotnikov SVenkat AChawla GKim JBukowski LKahn JMccann JZimmerman J(2024)Investigating Why Clinicians Deviate from Standards of Care: Liberating Patients from Mechanical Ventilation in the ICUProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641982(1-15)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613904.3641982
Yildirim NZlotnikov SSayar DKahn JBukowski LAmin SRiman KDavis BMinturn JKing ARicketts DTang LSivaraman VPerer APreum SMcCann JZimmerman J(2024)Sketching AI Concepts with Capabilities and Examples: AI Innovation in the Intensive Care UnitProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641896(1-18)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613904.3641896
Liu JCapurro DNguyen AVerspoor K(2023)Attention-based multimodal fusion with contrast for robust clinical prediction in the face of missing modalitiesJournal of Biomedical Informatics10.1016/j.jbi.2023.104466145:COnline publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1016/j.jbi.2023.104466

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents