CoChat
Sign Up
Cited by 37Machine Learning in HealthcareSepsis Diagnosis and TreatmentArtificial Intelligence in Healthcare

Predicting bloodstream infection outcome using machine learning

Open access
Zoabi, Yazeed, Kehat, Orli, Lahav, Dan, Weiss-Meilik, Ahuva, Adler, Amos, Shomron, Noam·2021·Scientific Reports
DOI 10.1038/s41598-021-99105-2PMC PMC8505419

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Bloodstream infections (BSI) are a main cause of infectious disease morbidity and mortality worldwide. Early prediction of BSI patients at high risk of poor outcomes is important for earlier decision making and effective patient stratification. We developed electronic medical record-based machine learning models that predict patient outcomes of BSI. The area under the receiver-operating characteristics curve was 0.82 for a full featured inclusive model, and 0.81 for a compact model using only 25 features. Our models were trained using electronic medical records that include demographics, blood tests, and the medical and diagnosis history of 7889 hospitalized patients diagnosed with BSI. Among the implications of this work is implementation of the models as a basis for selective rapid microbiological identification, toward earlier administration of appropriate antibiotic therapy. Additionally, our models may help reduce the development of BSI and its associated adverse health outcomes and complications.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-021-99105-2

Cites

6 of 6 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Recent studies have explored various ML algorithms, such as logistic regression, random forest, support vector machines, and gradient boosting, to assess the risk of BSIs in real time.

    “Recent studies have explored various ML algorithms, such as logistic regression, random forest, support vector machines, and gradient boosting, to assess the risk of BSIs in real time [10–14].”

    From Early prediction of bloodstream infections in ICU patients using machine learning methods based on routine laboratory parameters (2025) · cites this paper as [13]

    The Methods (Development of the models) describe a gradient-boosting model, and the Methods (Variable and feature selection) say its inputs were available when a blood sample was sent for culture, apart from gram-stain information in the inclusive model. But the Introduction specifies that this study predicted poor outcomes among patients with confirmed BSI, not the risk of developing BSI. Our copy does not show this study using logistic regression, random forests, or support vector machines. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Machine learning models have demonstrated significant potential in predicting BSIs by analyzing readily available clinical and laboratory data.

    “Machine learning models have demonstrated significant potential in predicting BSIs by analyzing readily available clinical and laboratory data.”

    From Early prediction of bloodstream infections in ICU patients using machine learning methods based on routine laboratory parameters (2025) · cites this paper as [13]

    The Abstract and Discussion report that machine-learning models used electronic medical records, including demographics and blood tests, to predict outcomes in patients with BSI. The Introduction explicitly distinguishes this from predicting who will develop BSI: the study included patients with confirmed infections. Thus the data and predictive potential are supported, but predicting BSIs themselves is not. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Most reported ML-based BSI prediction models integrate a combination of vital signs, clinical scores, and laboratory values.

    “However, most reported ML-based BSI prediction models integrate a combination of vital signs, clinical scores, and laboratory values.”

    From Early prediction of bloodstream infections in ICU patients using machine learning methods based on routine laboratory parameters (2025) · cites this paper as [13]

    The Methods section (Variable and feature selection; page unavailable) lists laboratory results among the inputs to this paper’s own BSI outcome models, while the Discussion compares those models with a clinical score. Neither section says that most reported ML-based BSI models combine vital signs, clinical scores, and laboratory values; searches for that combination found no supporting passage in our copy. (LLM, conf=0.72)

    Experimental — accuracy not yet measured

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

Flagged first, then by citations

Research works printed but not linked: 44

  1. [1]Goto M Al-Hasan MN Overall burden of bloodstream infection and nosocomial bloodstream infection in North America and Europe Clin. Microbiol. Infect. 2013 19 501 509 10.1111/1469-0691.12195 23473333 · DOI
  2. [2]Pittet D Tarara D Wenzel RP Nosocomial bloodstream infection in critically III patients: Excess length of stay, extra costs, and attributable mortality JAMA 1994 271 1598 1601 10.1001/jama.1994.03510440058033 8182812 · DOI
  3. [3]Rudd KE Johnson SC Agesa KM Global, regional, and national sepsis incidence and mortality, 1990–2017: Analysis for the Global Burden of Disease Study The Lancet 2020 395 200 211 10.1016/S0140-6736(19)32989-7 PMC6970225 31954465 · DOI · Paper page
  4. [4]Angus DC Linde-Zwirble WT Lidicker J Epidemiology of severe sepsis in the United States: Analysis of incidence, outcome, and associated costs of care Crit. Care Med. 2001 29 1303 1310 10.1097/00003246-200107000-00002 11445675 · DOI · Paper page
  5. [6]MacVane SH Nolte FS Benefits of adding a rapid PCR-based blood culture identification panel to an established antimicrobial stewardship program J. Clin. Microbiol. 2016 54 2455 2463 10.1128/JCM.00996-16 27487951 PMC5035429 · DOI · Paper page
  6. [7]Gyawali B Ramakrishna K Dhamoon AS Sepsis: The evolution in definition, pathophysiology, and management SAGE Open Med. 2019 10.1177/2050312119835043 30915218 PMC6429642 · DOI
  7. [8]Taylor RA Pare JR Venkatesh AK Prediction of In-hospital mortality in emergency department patients with sepsis: A local big data-driven, machine learning approach Acad. Emerg. Med. 2016 23 269 278 10.1111/acem.12876 26679719 PMC5884101 · DOI
  8. [9]Gultepe E Green JP Nguyen H From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system J. Am. Med. Inform. Assoc. 2014 21 315 325 10.1136/amiajnl-2013-001815 23959843 PMC3932455 · DOI
  9. [10]Nemati S Holder A Razmi F An interpretable machine learning model for accurate prediction of sepsis in the ICU Crit. Care Med. 2018 46 547 553 10.1097/CCM.0000000000002936 29286945 PMC5851825 · DOI · Paper page
  10. [13]Desautels T Calvert J Hoffman J Prediction of sepsis in the intensive care unit with minimal electronic health record data: A machine learning approach JMIR Med. Inform. 2016 4 e5909 10.2196/medinform.5909 PMC5065680 27694098 · DOI · Paper page
  11. [14]Thottakkara P Ozrazgat-Baslanti T Hupf BB Application of machine learning techniques to high-dimensional clinical data to forecast postoperative complications PLoS ONE 2016 11 e0155705 10.1371/journal.pone.0155705 27232332 PMC4883761 · DOI
  12. [16]Caliendo AM Gilbert DN Ginocchio CC Better tests, better care: Improved diagnostics for infectious diseases Clin. Infect. Dis. 2013 57 Suppl 3 S139 170 10.1093/cid/cit578 24200831 PMC3820169 · DOI
  13. [17]Yoo J-W Ju S Lee SJ Red cell distribution width/albumin ratio is associated with 60-day mortality in patients with acute respiratory distress syndrome Infect. Dis. 2020 52 266 270 10.1080/23744235.2020.1717599 31996066 · DOI
  14. [18]Zhang Z Xu X Ni H Deng H Red cell distribution width is associated with hospital mortality in unselected critically ill patients J. Thorac. Dis. 2013 5 730 736 10.3978/j.issn.2072-1439.2013.11.14 24409348 PMC3886701 · DOI
  15. [20]Chen L Lu XY Zhu CQ Prognostic value of albumin-red cell distribution width score in patients with severe community-acquired pneumonia Ann. Palliat. Med. 2020 9 75965 75765 10.21037/apm.2020.04.22 32312071 · DOI
  16. [21]Lee JH Chung HJ Kim K Red cell distribution width as a prognostic marker in patients with community-acquired pneumonia Am. J. Emerg. Med. 2013 31 72 79 10.1016/j.ajem.2012.06.004 22867824 · DOI
  17. [22]Hannan JL Radwany SM Albanese T In-hospital mortality in patients older than 60 years with very low albumin levels J. Pain Symptom Manage. 2012 43 631 637 10.1016/j.jpainsymman.2011.04.009 21925833 · DOI
  18. [23]Akirov A Masri-Iraqi H Atamna A Shimon I Low albumin levels are associated with mortality risk in hospitalized patients Am. J. Med. 2017 130 1465.e11 1465.e19 10.1016/j.amjmed.2017.07.020 28803138 · DOI
  19. [24]Goldwasser P Feldman J Association of serum albumin and mortality risk J. Clin. Epidemiol. 1997 50 693 703 10.1016/s0895-4356(97)00015-2 9250267 · DOI
  20. [25]Bannay A Chaignot C Blotiere P-O The best use of the Charlson Comorbidity Index with electronic health care database to predict mortality Med. Care 2016 54 188 10.1097/MLR.0000000000000471 26683778 · DOI
  21. [26]Huang Y Gou R Diao Y Charlson comorbidity index helps predict the risk of mortality for patients with type 2 diabetic nephropathy J. Zhejiang Univ. Sci. B 2014 15 58 66 10.1631/jzus.B1300109 24390745 PMC3891119 · DOI
  22. [27]Tabaie A Orenstein EW Nemati S Predicting presumed serious infection among hospitalized children on central venous lines with machine learning Comput. Biol. Med. 2021 132 104289 10.1016/j.compbiomed.2021.104289 33667812 PMC9207586 · DOI
  23. [28]Roimi M Neuberger A Shrot A Early diagnosis of bloodstream infections in the intensive care unit using machine-learning algorithms Intensive Care Med. 2020 46 454 462 10.1007/s00134-019-05876-8 31912208 · DOI · Paper page
  24. [29]Mahmoud E Al Dhoayan M Bosaeed M Developing machine-learning prediction algorithm for bacteremia in admitted patients Infect. Drug Resist. 2021 14 757 765 10.2147/IDR.S293496 33658812 PMC7920583 · DOI
  25. [30]Zhang G Xu J Yu M A machine learning approach for mortality prediction only using non-invasive parameters Med. Biol. Eng. Comput. 2020 58 2195 2238 10.1007/s11517-020-02174-0 32691219 · DOI
  26. [31]Morgan DJ Bame B Zimand P Assessment of machine learning vs standard prediction rules for predicting hospital readmissions JAMA Netw. Open 2019 2 e190348 10.1001/jamanetworkopen.2019.0348 30848808 PMC6484642 · DOI
  27. [32]Bernhard M Lichtenstern C Eckmann C Weigand MA The early antibiotic therapy in septic patients: Milestone or sticking point? Crit. Care 2014 18 671 10.1186/s13054-014-0671-1 25672873 PMC4331420 · DOI
  28. [33]Falcone M Bassetti M Tiseo G Time to appropriate antibiotic therapy is a predictor of outcome in patients with bloodstream infection caused by KPC-producing Klebsiella pneumoniae Crit. Care 2020 24 29 10.1186/s13054-020-2742-9 32000834 PMC6993311 · DOI
  29. [34]Phelan M Bhavsar NA Goldstein BA Illustrating informed presence bias in electronic health records data: How patient interactions with a health system can impact inference EGEMS 2017 10.5334/egems.243 29930963 PMC5994954 · DOI
  30. [35]Dagan N Cohen-Stavi C Leventer-Roberts M Balicer RD External validation and comparison of three prediction tools for risk of osteoporotic fractures using data from population based electronic health records: retrospective cohort study BMJ 2017 356 i6755 10.1136/bmj.i6755 28104610 PMC5244817 · DOI
  31. [36]Vollmer S Mateen BA Bohner G Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness BMJ 2020 368 l6927 10.1136/bmj.l6927 32198138 PMC11515850 · DOI
  32. [37]Hastie T Tibshirani R Friedman J Hastie T Tibshirani R Friedman J Boosting and additive trees The Elements of Statistical Learning: Data Mining, Inference, and Prediction 2009 Springer 337 387
  33. [40]Ke G Meng Q Finley T Guyon I Luxburg UV Bengio S LightGBM: A highly efficient gradient boosting decision tree Advances in Neural Information Processing Systems 30 2017 Curran Associates Inc 3146 3154
  34. [41]Wang T Liu G Lin H A machine learning approach to predict intravenous immunoglobulin resistance in Kawasaki disease patients: A study based on a Southeast China population PLoS ONE 2020 15 e0237321 10.1371/journal.pone.0237321 32853226 PMC7451628 · DOI
  35. [42]Zoabi Y Deri-Rozov S Shomron N Machine learning-based prediction of COVID-19 diagnosis based on symptoms npj Digit. Med. 2021 4 1 5 10.1038/s41746-020-00372-6 33398013 PMC7782717 · DOI
  36. [43]Artzi NS Shilo S Hadar E Prediction of gestational diabetes based on nationwide electronic health records Nat. Med. 2020 26 71 76 10.1038/s41591-019-0724-8 31932807 · DOI
  37. [45]Shin Y Kim S Chung J Emergency department return prediction system using blood samples with LightGBM for smart health care services IEEE Consum. Electron. Mag. 2020 10.1109/MCE.2020.3015439 · DOI
  38. [46]Razavian N Major VJ Sudarshan M A validated, real-time prediction model for favorable outcomes in hospitalized COVID-19 patients npj Digit. Med. 2020 3 1 13 10.1038/s41746-020-00343-x 33083565 PMC7538971 · DOI
  39. [47]Josse, J., Prost, N., Scornet, E. & Varoquaux, G. On the consistency of supervised learning with missing values. arXiv:190206931 [cs, math, stat] (2019).
  40. [48]Chen, T. & Guestrin, C. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery 785–794 (2016).
  41. [49]Raskutti, G., Wainwright, M. J. & Yu, B. Early stopping for non-parametric regression: An optimal data-dependent stopping rule. In 2011 49th Annual Allerton Conference on Communication, Control, and Computing (Allerton) 1318–1325 (2011).
  42. [50]Lundberg, S. & Lee, S.-I. A Unified Approach to Interpreting Model Predictions. arXiv:170507874 [cs, stat] (2017).
  43. [51]Lundberg SM Nair B Vavilala MS Explainable machine-learning predictions for the prevention of hypoxaemia during surgery Nat. Biomed. Eng. 2018 2 749 760 10.1038/s41551-018-0304-0 31001455 PMC6467492 · DOI · Paper page
  44. [52]Efron B Tibshirani RJ An Introduction to the bootstrap 1994 CRC Press

Cited by

Sorted by citations

Authors
Zoabi, Y., Kehat, O., Lahav, D., Weiss-Meilik, A., Adler, A., & Shomron, N.
Affiliations
  • Tel Aviv University (IL)
  • Tel Aviv Sourasky Medical Center (IL)
Corresponding author
  • Adler, Amos
  • Shomron, Noam
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2021-10-11
Volume
11
Issue
1
Pages
20101-20101
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-021-99105-2
PMC
PMC8505419
OpenAlex
W3205795773
Cited by
37
References
6
Citations by year
2026: 3 · 2025: 8 · 2024: 17 · 2023: 5 · 2022: 3 · 2021: 1
FWCI
2.19
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • medRxiv (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
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 › Artificial Intelligence in Healthcare
Keywords
bloodstream infection, outcome prediction, electronic health records, hospitalized patients, patient stratification, antibiotic therapy, clinical decision support, machine learning models
MeSH terms
Machine Learning, Aged, Anti-Bacterial Agents, Bacteria, Female, Humans, Male, Retrospective Studies, Risk Factors, ROC Curve, Bacteremia, Sepsis, Electronic Health Records

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