From data to optimal decision making: a data-driven, probabilistic machine learning approach to decision support for patients with sepsis
Open accessAbstract
BACKGROUND: A tantalizing question in medical informatics is how to construct knowledge from heterogeneous datasets, and as an extension, inform clinical decisions. The emergence of large-scale data integration in electronic health records (EHR) presents tremendous opportunities. However, our ability to efficiently extract informed decision support is limited due to the complexity of the clinical states and decision process, missing data and lack of analytical tools to advice based on statistical relationships. OBJECTIVE: Development and assessment of a data-driven method that infers the probability distribution of the current state of patients with sepsis, likely trajectories, optimal actions related to antibiotic administration, prediction of mortality and length-of-stay. METHODS: We present a data-driven, probabilistic framework for clinical decision support in sepsis-related cases. We first define states, actions, observations and rewards based on clinical practice, expert knowledge and data representations in an EHR dataset of 1492 patients. We then use Partially Observable Markov Decision Process (POMDP) model to derive the optimal policy based on individual patient trajectories and we evaluate the performance of the model-derived policies in a separate test set. Policy decisions were focused on the type of antibiotic combinations to administer. Multi-class and discriminative classifiers were used to predict mortality and length of stay. RESULTS: Data-derived antibiotic administration policies led to a favorable patient outcome in 49% of the cases, versus 37% when the alternative policies were followed (P=1.3e-13). Sensitivity analysis on the model parameters and missing data argue for a highly robust decision support tool that withstands parameter variation and data uncertainty. When the optimal policy was followed, 387 patients (25.9%) have 90% of their transitions to better states and 503 patients (33.7%) patients had 90% of their transitions to worse states (P=4.0e-06), while in the non-policy cases, these numbers are 192 (12.9%) and 764 (51.2%) patients (P=4.6e-117), respectively. Furthermore, the percentage of transitions within a trajectory that lead to a better or better/same state are significantly higher by following the policy than for non-policy cases (605 vs 344 patients, P=8.6e-25). Mortality was predicted with an AUC of 0.7 and 0.82 accuracy in the general case and similar performance was obtained for the inference of the length-of-stay (AUC of 0.69 to 0.73 with accuracies from 0.69 to 0.82). CONCLUSIONS: A data-driven model was able to suggest favorable actions, predict mortality and length of stay with high accuracy. This work provides a solid basis for a scalable probabilistic clinical decision support framework for sepsis treatment that can be expanded to other clinically relevant states and actions, as well as a data-driven model that can be adopted in other clinical areas with sufficient training data.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
ML tools for optimizing care outcomes have been used in critical care for optimizing sepsis management, management of chronic conditions, and optimizing surgical outcomes.
“ML tools for optimizing care outcomes have been used in various settings, including critical care for optimizing sepsis management (27), management of chronic conditions (28), and optimizing surgical outcomes (29).”
From Accessing Artificial Intelligence for Clinical Decision-Making (2021) · cites this paper as [27]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Wu, Y., & Vapnik, V. N. (1999) · Technometrics · doi:10.2307/1271368 · Cited by 27,236 · see citing works
Watkins, C., & Dayan, P. (1992) · Machine-mediated learning · doi:10.1023/a:1022676722315 · Cited by 14,277 · see citing works
Bone, R. C., BALK, R. A., Cerra, F. B., Dellinger, R. P., Fein, A. M., Knaus, W. A., Schein, R. M. H., & Sibbald, W. J. (1992) · CHEST Journal · doi:10.1378/chest.101.6.1644 · Cited by 13,192 · see citing works
Vincent, J. L., Moreno, R., Takala, J., Willatts, S., De Mendonça, A., Bruining, H., Reinhart, C. K., Suter, P. M., & Thijs, L. G. (1996) · Intensive Care Medicine · doi:10.1007/bf01709751 · Cited by 11,674 · see citing works
Watkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083 · see citing works
A comparison of methods for multiclass support vector machines
Hsu, C., & Lin, C. (2002) · IEEE Transactions on Neural Networks · doi:10.1109/72.991427 · Cited by 6,861 · cited 1× · see citing works
“For the latter, we consider both combinatorial pairwise and one-versus-all schemes [36], where we observed no significant difference in our results.”
A review of feature selection techniques in bioinformatics
Saeys, Y., Inza, I., & Larrañaga, P. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm344 · Cited by 5,252 · see citing works
American College of Chest Physicians/Society of Critical Care Medicine Consensus Conference
(1992) · Critical Care Medicine · doi:10.1097/00003246-199206000-00025 · Cited by 5,091 · see citing works
Planning and acting in partially observable stochastic domains
Kaelbling, L. P., Littman, M. L., & Cassandra, A. R. (1998) · Artificial Intelligence · doi:10.1016/s0004-3702(98)00023-x · Cited by 4,149 · cited 2× · see citing works
“In that case, a belief regarding the current system state is formed based on the observations and their state-based likelihoods [14].”
A survey of robot learning from demonstration
Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.10.024 · Cited by 3,227 · see citing works
Perseus: Randomized point-based value iteration for POMDPs
Spaan, M. T. J., & Vlassis, N. A. (2005) · UvA-DARE (University of Amsterdam) · Cited by 526 · see citing works
Inpatient care for septicemia or sepsis: a challenge for patients and hospitals.
Hall, M. J., Williams, S. N., DeFrances, C. J., & Golosinskiy, A. (2011) · PubMed · Cited by 465 · see citing works
What It Will Take To Achieve The As-Yet-Unfulfilled Promises Of Health Information Technology
Kellermann, A. L., & Jones, S. S. (2013) · Health Affairs · doi:10.1377/hlthaff.2012.0693 · Cited by 460 · cited 1× · see citing works
“Unfortunately, despite explosive EHR adoption, and enormous associated capital expenditures, these gains have yet to be realized [5,6].”
Computer Technology and Clinical Work: Still Waiting for Godot
Wears, R. L., & Berg, M. (2005) · JAMA · doi:10.1001/jama.293.10.1261 · Cited by 448 · cited 1× · see citing works
“Although in certain systems patient cases are used for probabilistic training, these efforts focus on feature correlations and final clinical outcomes [7-10] rather than actionable policy (see [11,12] for a review).”
Gunter, T. D., & Terry, N. P. (2005) · Journal of Medical Internet Research · doi:10.2196/jmir.7.1.e3 · Cited by 440 · cited 1× · see citing works
“…transformative approach to this problem would be to exploit the vast amount of information that is hidden in the Electronic Health Records (EHR) of patients to derive a CDSS. Adoption of EHR’s by health care systems was predicted to vastly improve the efficiency and quality of patient care [4].”
Markov decision processes: a tool for sequential decision making under uncertainty
Alagoz, O., Hsu, H., Schaefer, A. J., & Roberts, M. S. (2010) · Medical Decision Making · doi:10.1177/0272989x09353194 · Cited by 266 · cited 1× · see citing works
“MDP has been used for decision support in determining liver acceptance for liver transplants [18-20], HIV therapy initiation [21], breast cancer screening [22], treatment of hepatitis C [23], statin therapy timing [24], among others [25].”
The Optimal Timing of Living-Donor Liver Transplantation
Alagöz, O., Maillart, L. M., Schaefer, A. J., & Roberts, M. S. (2004) · Management Science · doi:10.1287/mnsc.1040.0287 · Cited by 213 · cited 1× · see citing works
“MDP has been used for decision support in determining liver acceptance for liver transplants [18-20], HIV therapy initiation [21], breast cancer screening [22], treatment of hepatitis C [23], statin therapy timing [24], among others [25].”
OR Forum—A POMDP Approach to Personalize Mammography Screening Decisions
Ayer, T., Alagöz, O., & Stout, N. K. (2012) · Operations Research · doi:10.1287/opre.1110.1019 · Cited by 199 · see citing works
Planning treatment of ischemic heart disease with partially observable Markov decision processes
Hauskrecht, M., & Fraser, H. (2000) · Artificial Intelligence in Medicine · doi:10.1016/s0933-3657(99)00042-1 · Cited by 176 · cited 1× · see citing works
“A notable example of POMDP adoption in medical decision support is that of Hauskrecht and Fraser [26,27] who modeled Ischemic Heart Disease with a POMDP model that included both treatment and test actions.”
Clermont, G., Angus, D. C., DiRusso, S. M., Griffin, M. F., & Linde‐Zwirble, W. T. (2001) · Critical Care Medicine · doi:10.1097/00003246-200102000-00012 · Cited by 165 · cited 1× · see citing works
“Although in certain systems patient cases are used for probabilistic training, these efforts focus on feature correlations and final clinical outcomes [7-10] rather than actionable policy (see [11,12] for a review).”
Assessing Dynamic Breast Cancer Screening Policies
Maillart, L. M., Ivy, J. S., Ransom, S. B., & Diehl, K. M. (2008) · Operations Research · doi:10.1287/opre.1080.0614 · Cited by 163 · cited 1× · see citing works
“MDP has been used for decision support in determining liver acceptance for liver transplants [18-20], HIV therapy initiation [21], breast cancer screening [22], treatment of hepatitis C [23], statin therapy timing [24], among others [25].”
The Optimal Time to Initiate HIV Therapy Under Ordered Health States
Shechter, S. M., Bailey, M. D., Schaefer, A. J., & Roberts, M. S. (2008) · Operations Research · doi:10.1287/opre.1070.0480 · Cited by 148 · cited 1× · see citing works
“MDP has been used for decision support in determining liver acceptance for liver transplants [18-20], HIV therapy initiation [21], breast cancer screening [22], treatment of hepatitis C [23], statin therapy timing [24], among others [25].”
Determining the Acceptance of Cadaveric Livers Using an Implicit Model of the Waiting List
Alagöz, O., Maillart, L. M., Schaefer, A. J., & Roberts, M. S. (2007) · Operations Research · doi:10.1287/opre.1060.0329 · Cited by 145 · cited 1× · see citing works
“MDP has been used for decision support in determining liver acceptance for liver transplants [18-20], HIV therapy initiation [21], breast cancer screening [22], treatment of hepatitis C [23], statin therapy timing [24], among others [25].”
Optimizing the Start Time of Statin Therapy for Patients with Diabetes
Denton, B. T., Kurt, M., Shah, N. D., Bryant, S. C., & Smith, S. A. (2009) · Medical Decision Making · doi:10.1177/0272989x08329462 · Cited by 88 · cited 1× · see citing works
“MDP has been used for decision support in determining liver acceptance for liver transplants [18-20], HIV therapy initiation [21], breast cancer screening [22], treatment of hepatitis C [23], statin therapy timing [24], among others [25].”
Choosing Among Living-Donor and Cadaveric Livers
Alagöz, O., Maillart, L. M., Schaefer, A. J., & Roberts, M. S. (2007) · Management Science · doi:10.1287/mnsc.1070.0726 · Cited by 78 · cited 1× · see citing works
“MDP has been used for decision support in determining liver acceptance for liver transplants [18-20], HIV therapy initiation [21], breast cancer screening [22], treatment of hepatitis C [23], statin therapy timing [24], among others [25].”
Feature Selection for Maximizing the Area Under the ROC Curve
Wang, R., & Tang, K. (2009) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2009.25 · Cited by 59 · cited 1× · see citing works
“A filter method was applied using the Area-Under-the-Curve (AUC) of the Receiver Operating Characteristic (ROC) curves as a ranking criterion [39].”
Pharmacoeconomic Implications of New Therapies in Sepsis
Wood, K. A., & Angus, D. C. (2004) · PharmacoEconomics · doi:10.2165/00019053-200422140-00001 · Cited by 53 · cited 1× · see citing works
“[1] Severe sepsis is the leading cause of Intensive Care Unit (ICU) deaths (60-80% of ICU deaths in developing countries) and it kills more than 6 million children world-wide every year [2].”
Tang, C. H. H., Middleton, P. M., Savkin, A. V., Chan, G. S. H., Bishop, S. M., & Lovell, N. H. (2010) · Physiological Measurement · doi:10.1088/0967-3334/31/6/004 · Cited by 47 · cited 1× · see citing works
“Then we used Support Vector Machines (SVM) with different kernel functions [33,34].”
Prediction of Severe Sepsis Using SVM Model
Wang, S., Wu, F., & Wang, B.-H. (2010) · Advances in experimental medicine and biology · doi:10.1007/978-1-4419-5913-3_9 · Cited by 43 · cited 1× · see citing works
“Then we used Support Vector Machines (SVM) with different kernel functions [33,34].”
Modeling treatment of ischemic heart disease with partially observable Markov decision processes.
Hauskrecht, M., & Fraser, H. (1998) · PubMed · Cited by 23 · see citing works
Modeling hospital discharge policies for patients with pneumonia-related sepsis
Kreke, J. E., Bailey, M. D., Schaefer, A. J., Angus, D. C., & Roberts, M. S. (2008) · IIE Transactions · doi:10.1080/07408170802165872 · Cited by 19 · cited 1× · see citing works
“Kreke et al created a 2-state POMDP model for pneumonia-related sepsis patients that included only a Cytokine test as an investigative action and incorporated the Sequential Organ Failure Assessment (SOFA) score for the MDP state space definition [29,30].”
A knowledge-driven agent-centred framework for data mining in EMG
Balter, J., Labarre‐Vila, A., Ziébelin, D., & Catherine Garbay, B. (2002) · Comptes Rendus Biologies · doi:10.1016/s1631-0691(02)01434-8 · Cited by 12 · cited 1× · see citing works
“Although in certain systems patient cases are used for probabilistic training, these efforts focus on feature correlations and final clinical outcomes [7-10] rather than actionable policy (see [11,12] for a review).”
Modeling disease management decisions for patients with pneumonia-related sepsis
Kreke, J. E. (2007) · D-Scholarship@Pitt (University of Pittsburgh) · Cited by 9 · see citing works
Zhang, D. D., Jing, X., & Yang, J. (2006) · Computational intelligence and its applications (COMIA) book series/Computational intelligence and its applications series · doi:10.4018/978-1-59140-830-7.ch002 · Cited by 6 · cited 1× · see citing works
“Principal Component Analysis (PCA) was also used to assess whether linear transformation of the feature space and dimensionality reduction can be achieved in this case [38].”
Flagged first, then by citations
Research works printed but not linked: 5
- [7]Ouali A Ramdane-Cherif Z Ramdane-Cherif A Levy N Krebs M Agent paradigm in clinical large-scale data mining environment 2003 2nd IEEE International Conference on Cognitive Informatics (ICCI) August 18-20, 2003 London, UK 143 150
- [8]Catley C Frize M A prototype XML-based implementation of an integrated intelligent neonatal intensive care unit 2003 8 18 4th International IEEE Conference on Information Technology Applications in Biomedicine 2003 London, UK 322 325
- [11]Foster D McGregor C El-Masri S A survey of agent-based intelligent decision support systems to support clinical management and research 2005 7 25 Fourth International Joint Conference on Autonomous Agents and Multiagent Systems 2005 Ultrecht, Netherlands 16 34
- [16]Howard RA Dynamic programming and markov processes Technology Press 1960 Boston, MA Massachusetts Institute of Technology
- [23]Faissol DM Griffin PM Timing of testing and treatment of hepatitis C and other diseases Proceedings 2007 INFORMS international meeting July 2007 Puerto Rico 11
Cited by
Sorted by citations
Peiffer-Smadja, N., Rawson, T. M., Ahmad, R., Buchard, A., Georgiou, P., Lescure, F.-X., Birgand, G., & Holmes, A. H. (2020) · Clinical Microbiology and Infection · doi:10.1016/j.cmi.2019.09.009 · Cited by 561 · see citing works
Accessing Artificial Intelligence for Clinical Decision-Making
Giordano, C., Brennan, M., Mohamed, B., Rashidi, P., Modave, F., & Tighe, P. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.645232 · Cited by 326 · see citing works
“ML tools for optimizing care outcomes have been used in various settings, including critical care for optimizing sepsis management (27), management of chronic conditions (28), and optimizing surgical outcomes (29).”
MethodHorng, S., Sontag, D. A., Halpern, Y., Jernite, Y., Shapiro, N. I., & Nathanson, L. A. (2017) · PLOS ONE · doi:10.1371/journal.pone.0174708 · Cited by 310 · see citing works
“Several previous authors have considered the use of machine learning for identifying [20] or better managing sepsis [21].”
BackgroundAnahtar, M. N., Yang, J. H., & Kanjilal, S. (2021) · Journal of Clinical Microbiology · doi:10.1128/jcm.01260-20 · Cited by 214 · see citing works
“Applications to the practice of infectious diseases have encompassed the diagnosis of infection (7, 8), the early identi fi cation of sepsis (9 – 11), and targeting preex-posure prophylaxis for people living with human immunode fi ciency virus (12, 13).”
BackgroundAli, T., Ahmed, S., & Aslam, M. (2023) · Antibiotics · doi:10.3390/antibiotics12030523 · Cited by 181 · see citing works
“An efficient An efficient way of genome data management using artificial intelligence is given in [92]. way of genome data management The establishment of optimal antibiotic use strategies in sepsis treatment using AI-based data-driven techniques is presented in [93].”
MethodHoriguchi, H., Loftus, T. J., Hawkins, R. B., Raymond, S. L., Stortz, J. A., Hollen, M. K., Weiss, B. P., Miller, E. S., Bihorac, A., Larson, S. D., et al. (2018) · Frontiers in Immunology · doi:10.3389/fimmu.2018.00595 · Cited by 164 · see citing works
“This study and similar studies using regression-based prediction models may be further improved by the use of machinelearning algorithms and deep-learning technologies (271, 272).”
MethodA review of artificial intelligence applications for antimicrobial resistance
Lv, J. Z., Deng, S., & Zhang, L. (2020) · Biosafety and Health · doi:10.1016/j.bsheal.2020.08.003 · Cited by 163 · see citing works
Belard, A., Buchman, T. G., Forsberg, J. A., Potter, B. K., Dente, C. J., Kirk, A. D., & Elster, E. A. (2016) · Journal of Clinical Monitoring and Computing · doi:10.1007/s10877-016-9849-1 · Cited by 160 · see citing works
“), remains a challenge, one which is of particular import for machine learning applications [72, 73].”
BackgroundMulti-disease prediction using LSTM recurrent neural networks
Men, L., Ilk, N., Tang, X., & Liu, Y. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114905 · Cited by 140 · see citing works
Data integration and predictive modeling methods for multi-omics datasets
Kim, M., & Tagkopoulos, I. (2017) · Molecular Omics · doi:10.1039/c7mo00051k · Cited by 99 · see citing works
Self-citationThe Quantified Patient in the Doctor's Office
West, P. A., Giordano, R., Kleek, M. G. V., & Shadbolt, N. (2016) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858445 · Cited by 81 · see citing works
“[8] [3] [5] [35] [1] [28] [36] [24] [4] [2] [17] [43] [6] [29] [33] [42] [21] [12] [39] [18] [23] [13]”
Schwartz, J., Moy, A. J., Rossetti, S. C., Elhadad, N., & Cato, K. (2020) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa296 · Cited by 79 · see citing works
“These studies either described or presented a predictive CDSS prototype or interface; none of them described involving clinical experts in this stage.(29,33,34,84,93)”
BackgroundMachine learning in the prediction of medical inpatient length of stay
Bacchi, S., Tan, Y., Oakden‐Rayner, L., Jannes, J., Kleinig, T. J., & Koblar, S. A. (2020) · Internal Medicine Journal · doi:10.1111/imj.14962 · Cited by 80 · see citing works
Sharing Patient-Generated Data in Clinical Practices: An Interview Study.
Zhu, H., Colgan, J. C., Reddy, M. C., & Choe, E. K. (2016) · PubMed Central · Cited by 80 · see citing works
Wellner, B., Grand, J., Canzone, E., Coarr, M., Brady, P. W., Simmons, J. M., Kirkendall, E. S., Dean, N., Kleinman, M. E., & Sylvester, P. (2017) · JMIR Medical Informatics · doi:10.2196/medinform.8680 · Cited by 78 · see citing works
“Most machine learning methods for predicting deterioration have focused on logistic regression models preceded by careful variable selection [12,13].”
MethodThe intensive care medicine research agenda on septic shock
Perner, A., Gordon, A. C., Angus, D. C., Lamontagne, F., Machado, F. R., Russell, J. A., Timsit, J., Marshall, J. C., Myburgh, J., Shankar‐Hari, M., et al. (2017) · Intensive Care Medicine · doi:10.1007/s00134-017-4821-1 · Cited by 75 · see citing works
“Machine learning techniques embedded in clinical decision support systems should be developed and tested to select “optimal” treatments in sepsis using data-driven models [95].”
MethodClinical Decision Support Systems and Their Role in Antibiotic Stewardship: a Systematic Review
Rittmann, B., & Stevens, M. (2019) · Current Infectious Disease Reports · doi:10.1007/s11908-019-0683-8 · Cited by 76 · see citing works
Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis
Taneja, I., Reddy, B., Damhorst, G. L., Zhao, S. D., Hassan, U., Price, Z., Jensen, T., Ghonge, T., Patel, M. J., Wachspress, S., et al. (2017) · Scientific Reports · doi:10.1038/s41598-017-09766-1 · Cited by 76 · see citing works
Cocker, D., Birgand, G., Zhu, N., Rodríguez-Manzano, J., Ahmad, R., Jambo, K., Levin, A. S., & Holmes, A. H. (2024) · Nature Reviews Microbiology · doi:10.1038/s41579-024-01076-4 · Cited by 72 · see citing works
“MLClinical Decision Support Systems (MLCDSS) have been tri alled to improve choices of antimicrobials in sepsis 189 , primary care pre scriptions 190 and antimicrobial stewardship programmes in hospitals 191 .”
Bradley, R., Tagkopoulos, I., Kim, M., Kokkinos, Y., Panagiotakos, T., Kennedy, J., Meyer, G. D., Watson, P., & Elliott, J. (2019) · Journal of Veterinary Internal Medicine · doi:10.1111/jvim.15623 · Cited by 70 · see citing works
Self-citationBeeksma, M., Verberne, S., van den Bosch, A. P. J., Das, E., Hendrickx, I., & Groenewoud, S. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-0775-2 · Cited by 62 · see citing works
“…and language processing techniques have been applied to a broad range of tasks, including medical decision support and decision making [18 – 20], automatic disease detection [21 – 23], automatic diagnostication [24 – 28], identifying the role of genes in the onset of diseases [29], adverse…”
Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis
Zhang, Y., Xu, W., Yang, P. C., & Zhang, A. (2023) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-023-02383-1 · Cited by 65 · see citing works
“…predicting death within 3 months [32, 71], other two studies built two machine learning models for predicting death within 1 year [62, 70], and 4 studies built 6 machine learning models that did not specifically describe the time of sepsis death [40, 42, 64, 67], these models are depicted in Fig.”
Prescribing 10,000 Steps Like Aspirin
Kim, Y., Heo, E., Lee, H., Ji, S., Choi, J., Kim, J., Lee, J., & Yoo, S. (2017) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025570 · Cited by 55 · see citing works
“To understand patients, clinicians collect evidence by reviewing various kinds of lab data, such as vital signs and specific test results [18, 51].”
BackgroundRuminski, C., Clark, M., Lake, D. E., Kitzmiller, R. R., Keim‐Malpass, J., Robertson, M. P., Simons, T. R., Moorman, J. R., & Calland, J. F. (2018) · Journal of Clinical Monitoring and Computing · doi:10.1007/s10877-018-0194-4 · Cited by 54 · see citing works
Immunological Endotyping of Chronic Critical Illness After Severe Sepsis
Fenner, B. P., Darden, D. B., Kelly, L. S., Rincon, J. C., Brakenridge, S. C., Larson, S. D., Moore, F. A., Efron, P. A., & Moldawer, L. L. (2021) · Frontiers in Medicine · doi:10.3389/fmed.2020.616694 · Cited by 38 · see citing works
“This technique, using regression-based prediction models, may be further improved by the use of machine-learning algorithms and deep-learning technologies (167, 168).”
MethodDrug–drug interaction extraction‐based system: An natural language processing approach
Machado, J. M., Rodrigues, C., Sousa, R., & Gomes, L. M. (2023) · Expert Systems · doi:10.1111/exsy.13303 · Cited by 36 · see citing works
“However, a large amount of the valuable information on DDIs is unstructured, written in natu-ral language, and hidden in biomedical literature (Tsoukalas et al., 2015; Zheng et al., 2017).”
Estimating treatment effects for time-to-treatment antibiotic stewardship in sepsis
Liu, R., Hunold, K. M., Caterino, J. M., & Zhang, P. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00638-0 · Cited by 36 · see citing works
Prediction of Intensive Care Unit Length of Stay in the MIMIC-IV Dataset
Hempel, L., Sadeghi, S., & Kirsten, T. (2023) · Applied Sciences · doi:10.3390/app13126930 · Cited by 35 · see citing works
Disrupting Electronic Health Records Systems: The Next Generation
Celi, L. A., Marshall, J. D., Lai, Y., & Stone, D. J. (2015) · JMIR Medical Informatics · doi:10.2196/medinform.4192 · Cited by 35 · see citing works
“Optimally, a fully functional EHR would be able to provide useful predictive data analytics including the identification of patterns that characterize a patient’s normal physiologic state (thereby enabling detection of significant change from that state), as well as mapping of the predicted clinical trajectory, such a…”
Tuli, F. A., Varghese, A., & Ande, J. R. P. K. (2018) · Global Disclosure of Economics and Business · doi:10.18034/gdeb.v7i2.724 · Cited by 34 · see citing works
“We prioritize empirical facts, theoretical frameworks, case studies, best practices, and practical insights on HRM data-driven decision-making (Tsoukalas et al., 2015).”
MethodData-driven decision making in patient management: a systematic review
Lyu, G. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03072-x · Cited by 32 · see citing works
Predicting Sepsis Mortality in a Population-Based National Database: Machine Learning Approach
Park, J. Y., Hsu, T., Hu, J., Chen, C., Hsu, W., Lee, M., Ho, J., & Lee, C. (2022) · Journal of Medical Internet Research · doi:10.2196/29982 · Cited by 31 · see citing works
Basile, L. J., Carbonara, N., Panniello, U., & Pellegrino, R. (2024) · Technovation · doi:10.1016/j.technovation.2024.103010 · Cited by 36 · see citing works
Artificial intelligence in clinical nutrition and dietetics: A brief overview of current evidence
Atwal, K. (2024) · Nutrition in Clinical Practice · doi:10.1002/ncp.11150 · Cited by 26 · see citing works
“…in devices 10 ), dosage error prevention (eg, self ‐ administering medications [insulin pens] 11 ), clinical monitoring (eg, vital sign trajectories and outcome prediction 12 ), and robotic surgery (eg., the da Vinci surgical system approved by the United States Food and Drug Administration [FDA]).”
Kokkinos, Y., Morrison, J., Bradley, R., Panagiotakos, T., Ogeer, J., Chew, D. J., O’Flynn, C., Meyer, G. D., Watson, P., & Tagkopoulos, I. (2022) · Scientific Reports · doi:10.1038/s41598-022-18793-6 · Cited by 23 · see citing works
Self-citationSimultaneous electrical detection of IL-6 and PCT using a microfluidic biochip platform
Berger, J., Valera, E., Jankelow, A. M., Garcia, C., Akhand, M., Heredia, J., Ghonge, T., Liu, C., Font-Bartumeus, V., Oshana, G., et al. (2020) · Biomedical Microdevices · doi:10.1007/s10544-020-00492-6 · Cited by 22 · see citing works
Enhancing sepsis management through machine learning techniques: A review
Ocampo-Quintero, N., Vidal-Cortés, P., del Río Carbajo, L., Fdez-Riverola, F., Reboiro-Jato, M., & Glez-Peña, D. (2022) · Medicina Intensiva · doi:10.1016/j.medin.2020.04.003 · Cited by 20 · see citing works
Data analytics and clinical feature ranking of medical records of patients with sepsis
Chicco, D., & Oneto, L. (2021) · BioData Mining · doi:10.1186/s13040-021-00235-0 · Cited by 20 · see citing works
Informatics Solutions for Application of Decision-Making Skills
Nibbelink, C. W., Young, J. R., Carrington, J. M., & Brewer, B. B. (2018) · Critical Care Nursing Clinics of North America · doi:10.1016/j.cnc.2018.02.006 · Cited by 19 · see citing works
“35 Using data from the EHR and database and the logic from CDSS, models can be created that provide “predictions” of patient outcomes based on patient characteristics.”
MethodIntegrating Artificial Intelligence into Causal Research in Epidemiology
Matthay, E. C., Neill, D. B., Titus, A. R., Desai, S. M., Troxel, A. B., Cerdá, M., Diaz, I. M., Santacatterina, M., & Thorpe, L. E. (2025) · Current Epidemiology Reports · doi:10.1007/s40471-025-00359-5 · Cited by 18 · see citing works
Bishop, J. A., Javed, H., El-Bouri, R., Zhu, T., Taylor, T., Peto, T., Watkinson, P., Eyre, D. W., & Clifton, D. A. (2021) · PLoS ONE · doi:10.1371/journal.pone.0260476 · Cited by 15 · see citing works
Otten, M., Jagesar, A. R., Dam, T. A., Biesheuvel, L. A., den Hengst, F., Ziesemer, K. A., Thoral, P. J., de Grooth, H., Girbes, A. R. J., François-Lavet, V., et al. (2023) · Critical Care Medicine · doi:10.1097/ccm.0000000000006100 · Cited by 15 · see citing works
“…sepsis treatment with vasopressors and IV fluids (21, 24, 26, 36, 37, 39, 41, 43), heparin dosing (23, 40), dosing of propofol and fentanyl (19), blood glucose control (35), ventilator setting optimization (22, 25, 42), all medication dosing (20), insulin dosing (38), and antibiotic treatment (34).”
BackgroundMethodAutomated Sepsis Detection, Alert, and Clinical Decision Support
Harrison, A. M., Herasevich, V., & Gajic, O. (2015) · Critical Care Medicine · doi:10.1097/ccm.0000000000001099 · Cited by 15 · see citing works
“Although it is not known if complex mathematical modeling and/or machine learning techniques will help with more accurate early detection of severe sepsis (12, 13), modified SIRS criteria alone are clearly not sufficient.”
BackgroundThe treatment of sepsis: an episodic memory-assisted deep reinforcement learning approach
Liang, D., Deng, H., & Liu, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04099-7 · Cited by 14 · see citing works
“In [20], an approach using probabilistic machine learning was proposed to model physiology and dosing behavior, but it suffered from the accuracy problem.”
MethodReal-Time and Retrospective Health-Analytics-as-a-Service: A Novel Framework
Khazaei, H., McGregor, C., Eklund, J., & El‐Khatib, K. (2015) · JMIR Medical Informatics · doi:10.2196/medinform.4640 · Cited by 15 · see citing works
“This data-rich, knowledge-poor oxymoron is particularly true in computationally driven clinical decision support systems (CDSSs), where advances in automated high-throughput data acquisition and electronic health records (EHRs) have yet to be translated into knowledge extraction [1].”
Nikravangolsefid, N., Reddy, S., Truong, H. H., Charkviani, M., Ninan, J., Prokop, L. J., Suppadungsuk, S., Singh, W., KASHANI, K. B., & Garces, J. P. D. (2024) · Journal of Critical Care · doi:10.1016/j.jcrc.2024.154889 · Cited by 12 · see citing works
Mudenda, S., Hakayuwa, C. M., Lubanga, A. F., Kasanga, M., Daka, V., Salachi, K. I., Mwaba, M., Chileshe, C., Champo, M., Kamayani, M., et al. (2025) · Pharmacology & Pharmacy · doi:10.4236/pp.2025.167014 · Cited by 14 · see citing works
Utilization of Data Mining for Generalizable, All-Admission Prediction of Inpatient Mortality
Hillsgrove, T., & Steele, R. J. (2019) · International Conference on Information and Computer Technologies (ICICT) · doi:10.1109/infoct.2019.8711434 · Cited by 10 · see citing works
“These models show comparable performance to models developed in such works as described in [6-9], while these previous works are more restricted in terms of the patent conditions that they are applicable to or the health facility locales.”
MethodResultPersonalised Medicine in Critical Care Using Bayesian Reinforcement Learning
Utomo, C. P., Kurniawati, H., Li, X., & Pokharel, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-35231-8_47 · Cited by 10 · see citing works
Kehinde, O., Abdul, R., Afolabi, B., Vir, P., Namblard, C., Mukhopadhyay, A., & Adereni, A. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i20.30223 · Cited by 9 · see citing works
Belard, A., Buchman, T. G., Dente, C. J., Potter, B. K., Kirk, A. D., & Elster, E. A. (2018) · Military Medicine · doi:10.1093/milmed/usx164 · Cited by 9 · see citing works
“) remains a challenge.(46,47) This concept of interoperability is critical if components are to be optimally inserted into a symbiotic system where data can be imported and exported seamlessly between components, that is, pulling data from the EHR to run CDSSs and subsequently pushing outcome data back to EHR to infor…”
BackgroundMachine Learning and Visualization in Clinical Decision Support: Current State and Future DirectionsPreprint
Levy-Fix, G., Kuperman, G., & Elhadad, N. (2019) · arXiv.org · doi:10.48550/arxiv.1906.02664 · Cited by 12 · see citing works
“[ 124,126,177,227,238] The need for interpretable and transparent learning methods has also been recognized outside of the health domain.”
BackgroundAntibiotic Decision-Making in the ICU
Parra-Rodriguez, L., & Guillamet, C. V. (2022) · Seminars in Respiratory and Critical Care Medicine · doi:10.1055/s-0041-1741014 · Cited by 8 · see citing works
Rosenstrom, E., Meshkinfam, S., Ivy, J. S., Goodarzi, S. H., Capan, M., Huddleston, J. M., & Brufau, S. R. (2022) · Decision Analysis · doi:10.1287/deca.2022.0455 · Cited by 8 · see citing works
Optimizing Sequential Medical Treatments with Auto-Encoding Heuristic Search in POMDPsPreprint
Li, L., Komorowski, M., & Faisal, A. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.07465 · Cited by 8 · see citing works
“Hauskrecht and Fraser (2000); Tsoukalas et al. (2015); Nemati et al. (2016) build POMDP frameworks in medical context but nevertheless assume discrete observation and/or action spaces and impute trivial structures on environment dynamics.”
BackgroundRing-Topology Echo State Networks for ICU Sepsis Classification
Alfaras, M., Varandas, R. S. P., & Gamboa, H. F. S. (2019) · Computing in cardiology · doi:10.22489/cinc.2019.327 · Cited by 7 · see citing works
Barrett, C. D., Suzuki, Y., Hussein, S., Garg, L., Tumolo, A. Z., Sandhu, A., West, J. J., Zipse, M. M., Aleong, R. G., Varosy, P. D., et al. (2023) · Journal of the American Heart Association · doi:10.1161/jaha.122.028483 · Cited by 6 · see citing works
Sakib, N., Ahamed, S. I., Khan, R. A., Griffin, P. M., & Haque, M. M. (2020) · JMIR Medical Informatics · doi:10.2196/18352 · Cited by 6 · see citing works
“…care units at Beth Israel Deaconess Medical Center in Boston, Massachusetts, including vital signs, laboratory measurements, observations and notes charted by care providers, imaging reports, fluid balance, medications, procedure codes, diagnostic codes, and hospital length of stay [17,21,37,38].”
BackgroundThe imperative need to develop guidelines to manage human versus machine intelligence
Kennedy, D. A., & Philbin, S. P. (2018) · Frontiers of Engineering Management · doi:10.15302/j-fem-2018085 · Cited by 5 · see citing works
“This includes so called arti fi cial intelligence (Warwick, 2013), such as self-driving automobiles (Ohn-Bar and Trivedi, 2016), or decision-making in healthcare applications (Tsoukalas et al., 2015).”
BackgroundSingh, P., Singh, S., Mishra, A., & Mishra, S. K. (2024) · Research on Biomedical Engineering · doi:10.1007/s42600-024-00349-4 · Cited by 5 · see citing works
“MDP provides decision support tools (Tsoukalas et al. 2015) for clinicians in the treatment planning process , allowing them to make more informed decisions about the most suitable therapy for each patient.”
Enhancing sepsis management through machine learning techniques: A review
Ocampo-Quintero, N., Vidal, P., Carbajo, L. D. R., Fdez‐Riverola, F., Reboiro‐Jato, M., & Glez‐Peña, D. (2022) · Medicina Intensiva (English Edition) · doi:10.1016/j.medine.2020.04.015 · Cited by 5 · see citing works
Pharmacometrics-based decision tools facilitate mHealth implementation
Nekka, F., Csajka, C., Wilbaux, M., Sanduja, S., Li, J., & Pfister, M. (2016) · Expert Review of Clinical Pharmacology · doi:10.1080/17512433.2017.1251837 · Cited by 5 · see citing works
Li, L., Albert-Smet, I., & Faisal, A. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06474 · Cited by 5 · see citing works
“Hauskrecht & Fraser (2000); Tsoukalas et al. (2015); Nemati et al. (2016) build POMDP frameworks in medical context but nevertheless assume discrete observation and/or action spaces and impute trivial structures on environment dynamics.”
BackgroundMishra, L., Ramaswamy, S. M., McCallum‐Hee, B. I., Wright, K., Croxford, R., Nagaraj, S. B., & Anstey, M. (2025) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2024-101354 · Cited by 4 · see citing works
Giacobbe, D. R., Ahmad, R., Akıllı, F. M., Ascandari, A., Eyre, D. W., Gallardo‐Pizarro, A., García‐Vidal, C., Lopes, B. S., Lyutsova, E., Rakhimov, R., et al. (2026) · Expert Review of Anti-infective Therapy · doi:10.1080/14787210.2026.2625382 · Cited by 4 · see citing works
Khalfallah, H. B., Jelassi, M., Jacques Demongeot, A., & Saoud, N. B. B. (2025) · Computation · doi:10.3390/computation13010008 · Cited by 4 · see citing works
Machine Learning Driven Decision Making in the Modern Data Era
Raza, H., Singh, A., Erdenetsogt, T., Kabeer, M. M., Aslam, M. A., & Farooq, M. (2026) · Perfect. · doi:10.62671/perfect.v3i1.224 · Cited by 3 · see citing works
“Machine learning powers even the simplest digital experiences such as personalized recommendation on streaming services or smart assistants on smart phones (Tsoukalas et al., 2015).”
Tegenaw, G. S., Amenu, D., Teklemariam, G. K., Verbeke, F., Cornelis, J. P., & Jansen, B. (2022) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-06368-8_13 · Cited by 3 · see citing works
Analytical Solution to A Discrete-Time Model for Dynamic Learning and Decision-Making
Zhang, H. (2021) · Management Science · doi:10.1287/mnsc.2021.4194 · Cited by 3 · see citing works
Predicting The Likelihood of Patients Developing Sepsis Based on Compound Ensemble Learning
Zhao, L., Lin, R., Liu, Z., & Yuan, H. (2022) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm55620.2022.9995054 · Cited by 3 · see citing works
“These methods can be roughly divided into three directions, prediction of sepsis [4]–[11], treatment methods [12]–[15], and prognosis evaluation [16]– [18].”
MethodCausal Analytics and Risk Analytics
Cox, L. A., Popken, D. A., & Sun, R. X. (2018) · International series in management science/operations research/International series in operations research & management science · doi:10.1007/978-3-319-78242-3_1 · Cited by 3 · see citing works
Proximity of Cellular and Physiological Response Failures in Sepsis
Jazayeri, A. R., Capan, M., Ivy, J. S., Arnold, R. C., & Yang, C. C. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3098428 · Cited by 3 · see citing works
Zorraquino, V., Quiñones-Soto, S., Kim, M., Rai, N., & Tagkopoulos, I. (2014) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/010595 · Cited by 3 · see citing works
Self-citationLatif, J., Zhang, S., Rehman, S. U., Wajahat, A., Nazir, A., & Imran, A. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133502 · Cited by 2 · see citing works
Intelligent Support for Clinical Processes Based on Automaton Approach
Vatian, A. S., Dobrenko, N., Tkachenko, M., Gusarova, N., Shalyto, A. A., Boytsov, V., Egorov, N., Treshkur, T. V., Ryngach, E. A., Tatarinova, A., et al. (2019) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct48121.2019.8981508 · Cited by 2 · see citing works
“There are certain examples of using the concept of states and transitions between them when constructing CDSS. Authors [64] define states, actions, observations and rewards based on clinical practice, expert knowledge and data representations in an EHR dataset of 1492 patients and infer the…”
BackgroundHospital Rapid Response Systems
Sebat, C. M., Sinigayan, V., & Albertson, T. E. (2017) · Hospital Medicine Clinics · doi:10.1016/j.ehmc.2017.05.004 · Cited by 2 · see citing works
Self-citationDai, M., Jian, Y., Zhao, X., Wang, Y., & Zhou, B. (2024) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2024.108383 · Cited by 1 · see citing works
Acharjee, A., Kumar, S. P., Acharjee, P., & Ball, G. (2024) · Springer eBooks · doi:10.1007/978-981-97-5272-0_38 · Cited by 1 · see citing works
Rachmoune, K., Aknouch, A., Belcadi, H., El-ouardi, Y., Mouniane, Y., Aitouhanni, I., Mabsor-Zgandaoui, S., Rhazi, M., Belkadi, M. C., & Moutaouakkil, A. (2025) · IGI Global eBooks · doi:10.4018/979-8-3693-9112-9.ch003 · Cited by 1 · see citing works
Big Data to Big Knowledge for Next Generation Medicine: A Data Science Roadmap
Sethi, T. (2017) · Studies in big data · doi:10.1007/978-3-319-53817-4_14 · Cited by 1 · see citing works
Drug-Drug Interaction Extraction-Based System: an NLP ApproachPreprint
Sousa, R., Machado, J. M., Rodrigues, C., & Gomes, L. M. (2023) · doi:10.22541/au.167766849.91957820/v1 · Cited by 1 · see citing works
in Escherichia coli under complex evolutionary scenarios 2
Zorraquino, V., Quiñones-Soto, S., Kim, M., & Rai, N. (2014)
Barrett, C. D., Kim, R., Sink, E. M., Tumolo, A. Z., Zipse, M. M., Aleong, R. G., Garg, L., Sandhu, A., West, J. J., Varosy, P. D., et al. (2022) · doi:10.2196/preprints.38097
Pons, E., Braun, L., Kors, J. A., & Hunink, M. G. M. (2018) · doi:10.2196/preprints.10132
The Transition Law of Sepsis Patients’ Illness States Based on Complex Network
Wang, R., Liu, J., Chen, Z., Gong, M., Li, C., & Guo, W. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-09342-5_31
Dai, M., Jian, Y., Zhao, X., Wang, Y., & Zhou, B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4757064
Khatim, N. A., Irfan, A. A. A., Hayah, A. M., & Arief, M. (2024) · International Conference on Intelligent Medicine and Image Processing (IMIP) · doi:10.1145/3669828.3669835
“This approach echoes earlier works that have leveraged systematic algorithms and optimization models to address similar challenges and incorporates decision making under uncertainty, such as Markov Decision Processes (MDPs) or Partially Observable MDPs (POMDPs) [19, 22, 23].”
Rapid Response Teams for Proactive Sepsis TreatmentPreprint
Chang, C., Chan, C. W., Goyal, V., & Ranard, B. L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5205758
Chicco, D., & Oneto, L. (2021) · Figshare · doi:10.6084/m9.figshare.13710982
Zhang, Y., Xu, W., Yang, P., & Zhang, A. (2023) · Figshare · doi:10.6084/m9.figshare.24792237
Alonzi, F. A. F., Almutiri, B. M. N., Alahmadi, A. M. A., Alreshidi, A. S. M., Albalawi, A. S., Albalawi, A. S., Alharbi, N. M. M., Alruwaili, S. R. F., Alruwaili, J. M. J., Al-Rashidi, A. O. M., et al. (2024) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.4856
“Studies have shown that improved situational awareness through dashboard use can lead to earlier detection of patient deterioration, reducing the need for rapid response team activation and potentially decreasing rates of failure-to-rescue events [10].”
Jafaripakzad, M., Acuna, J. A., Dombrowski, K. E., & Zayas-Castro, J. L. (2026) · Digital Health · doi:10.1177/20552076261443021
“Tsoukalas et al. 14 used SVMs to classify LOS in 1,492 sepsis patients with thresholds at 4, 8, and 12 days, reporting 0.69–0.82 accuracy and 0.69–0.73 area under curve (AUC).”
InfluentialKaul, B., Raj, R. N., Mayya, V., & Shetty, R. D. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01733-y
“Tsoukalas et al. [37] offer a probabilistic framework designed to improve clinical judgment when treating sepsis.”
Hueda-Zavaleta, M., Flores-Palacios, R., Bardales-Silva, F., Cotacallapa-Pino, E., Frenkel, A., Minchón-Vizconde, D., & de la Torre, J. C. G. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1944745
“The oldest study in this review (Tsoukalas 2015) (23) used a partially observable Markov decision process (POMDP) to derive optimal antibiotic administration policies for 1,492 sepsis patients from a single US center.”
Measuring Calibration in Deep Learning
Nixon, J., Dusenberry, M., Jerfel, G., Nguyen, T., Liu, J., Zhang, L., & Tran, D. (2019) · arXiv · doi:10.48550/arxiv.1904.01685 · Cited by 209 · see citing works
“Decision costs along both ethical and monetary axes are non-uniform, and thus clinical decision policies necessitate a comprehensive view of the likelihoods of potential outcomes (e.g., Tsoukalas et al., 2015).”
Background
- Authors
- Tsoukalas, A., Albertson, T., & Tagkopoulos, I.
- Affiliations
- VA Northern California Health Care System (US)
- University of California, Davis (US)
- Corresponding author
- Tagkopoulos, Ilias
- Venue
- JMIR Medical Informatics
- Publisher
- JMIR Publications Inc.
- Published
- 2015-02-24
- Volume
- 3
- Issue
- 1
- Pages
- e11
- ISSN
- 2291-9694 (ISSN-L)
- PMC
- PMC4376114
- OpenAlex
- W2000658385
- Cited by
- 96
- References
- 34
- Citations by year
- 2026: 6 · 2025: 7 · 2024: 11 · 2023: 9 · 2022: 10 · 2021: 10 · 2020: 7 · 2019: 11 · 2018: 8 · 2017: 8 · 2016: 4 · 2015: 3 · 2014: 2
- FWCI
- 7.50
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Medical Informatics (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Center for Information Technology Research in the Interest of Society
- National Institutes of Health (UL1TR000002, TR000002)
- Center for Information Technology
- National Center for Advancing Translational Sciences (#TR 000002)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Epidemiology › Sepsis Diagnosis and Treatment
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Keywords
- sepsis, clinical decision support, partially observable Markov decision processes, electronic health records, mortality prediction, length of stay prediction, missing data, sensitivity analysis, probabilistic decision making, antibiotic combinations, sepsis management guidelines
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
