Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 153 of the 153 references it cites were found in a registry or an index.

Sepsis prediction, early detection, and identification using clinical text for machine learning: a systematic review

Open access
Yan, Melissa Y, Gustad, Lise Tuset, Nytrø, Øystein · 2022 · Journal of the American Medical Informatics Association

Abstract

Objective: To determine the effects of using unstructured clinical text in machine learning (ML) for prediction, early detection, and identification of sepsis. Materials and methods: PubMed, Scopus, ACM DL, dblp, and IEEE Xplore databases were searched. Articles utilizing clinical text for ML or natural language processing (NLP) to detect, identify, recognize, diagnose, or predict the onset, development, progress, or prognosis of systemic inflammatory response syndrome, sepsis, severe sepsis, or septic shock were included. Sepsis definition, dataset, types of data, ML models, NLP techniques, and evaluation metrics were extracted. Results: The clinical text used in models include narrative notes written by nurses, physicians, and specialists in varying situations. This is often combined with common structured data such as demographics, vital signs, laboratory data, and medications. Area under the receiver operating characteristic curve (AUC) comparison of ML methods showed that utilizing both text and structured data predicts sepsis earlier and more accurately than structured data alone. No meta-analysis was performed because of incomparable measurements among the 9 included studies. Discussion: Studies focused on sepsis identification or early detection before onset; no studies used patient histories beyond the current episode of care to predict sepsis. Sepsis definition affects reporting methods, outcomes, and results. Many methods rely on continuous vital sign measurements in intensive care, making them not easily transferable to general ward units. Conclusions: Approaches were heterogeneous, but studies showed that utilizing both unstructured text and structured data in ML can improve identification and early detection of sepsis.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1093/jamia/ocab236

Cites

153 of 153 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1. PRISMA (Preferred Reporting Items for Systemic reviews and Meta-Analyses) flowchart for study selection.
Figure 1. PRISMA (Preferred Reporting Items for Systemic reviews and Meta-Analyses) flowchart for study selection.CC BY · PubMed Central
Figure 2. Overview of data from a patient timeline used to create models. The proximity of events toward a patient’s actual state and the actual documentation recorded in the electronic health records typically has delays. Green represents patient states as sepsis develops in a patient. Yellow are observations made by clinicians. Documentation includes ICU vital signsa in pink, narrative notes in blue, and ICD codes in orange. ICU vital signa documentation can be instantaneous, narrative notes can be written after observations are made, and ICD codes are typically registered after a patient is discharged. PIVC: peripheral intravenous catheter. aVital signs include temperature, pulse, blood pressure, respiratory rate, oxygen saturation, and level of consciousness and awareness.
Figure 2. Overview of data from a patient timeline used to create models. The proximity of events toward a patient’s actual state and the actual documentation recorded in the electronic health records typically has delays. Green represents patient states as sepsis develops in a patient. Yellow are observations made by clinicians. Documentation includes ICU vital signsa in pink, narrative notes in blue, and ICD codes in orange. ICU vital signa documentation can be instantaneous, narrative notes can be written after observations are made, and ICD codes are typically registered after a patient is discharged. PIVC: peripheral intravenous catheter. aVital signs include temperature, pulse, blood pressure, respiratory rate, oxygen saturation, and level of consciousness and awareness.CC BY · PubMed Central
Figure 3. Different types of windows were used to obtain longitudinal data. Each gray box represents a single window, which can vary in duration (length of time) depending on the study. One window with the whole encounter means the study used a single window containing data with a duration of the whole encounter from admittance until discharge. One window before onset signifies data from a window with a duration of time before sepsis, severe sepsis, or septic shock onset. Sliding windows are consecutive windows until before sepsis, severe sepsis, or septic shock onset; this includes non-overlapping and overlapping sliding windows. Non-overlapping sliding windows indicate that data within one window of a fixed duration does not contain data in the next window. In contrast, overlapping sliding windows indicate windows of a fixed duration overlap, and data within one window will be partially in the next window.
Figure 3. Different types of windows were used to obtain longitudinal data. Each gray box represents a single window, which can vary in duration (length of time) depending on the study. One window with the whole encounter means the study used a single window containing data with a duration of the whole encounter from admittance until discharge. One window before onset signifies data from a window with a duration of time before sepsis, severe sepsis, or septic shock onset. Sliding windows are consecutive windows until before sepsis, severe sepsis, or septic shock onset; this includes non-overlapping and overlapping sliding windows. Non-overlapping sliding windows indicate that data within one window of a fixed duration does not contain data in the next window. In contrast, overlapping sliding windows indicate windows of a fixed duration overlap, and data within one window will be partially in the next window.CC BY · PubMed Central
Figure 4. The unit of analysis used to train machine learning models for the included studies was either (1) a single note, (2) a set of many notes, or (3) keywords. In general, text was preprocessed and represented as features interpretable by a computer, then structured data were added, and the data were used to fit machine learning models.
Figure 4. The unit of analysis used to train machine learning models for the included studies was either (1) a single note, (2) a set of many notes, or (3) keywords. In general, text was preprocessed and represented as features interpretable by a computer, then structured data were added, and the data were used to fit machine learning models.CC BY · PubMed Central
Figure 5. Overview of area under the curve (AUC) values for identification or early detection of infection, sepsis, septic shock, and severe sepsis using different data types (structured data and text, structured data only, and text only).∗ Each figure contains the study and year, machine learning model,a and natural language processing techniqueb. (A) AUC values for infection identification. Horng et al47 2017: SVM (BoW) has 2 AUC values; 0.86 when using chief complaints and nursing notes and 0.83 when using only chief complaints. (B) AUC values for early sepsis detection. Amrollahi et al53 AUC values are from detecting 4 h before sepsis onset, and Qin et al55 AUC values are the average from detecting 0 to 6 h before sepsis onset. (C) AUC values for early septic shock detection. Hammoud et al54 AUC values are from detecting 30.64 h before septic shock onset, and Liu et al50 AUC values are from detecting 6.0 to 7.3 h before septic shock onset. (D) AUC values for early sepsis, severe sepsis, or septic shock detection and sepsis identification in Goh et al.52 Different symbols separate data types. (E) AUC values for early septic shock detection for Culliton et al49 using results from the test set. (F) AUC values for early septic shock detection for Culliton et al49 using results from 3-fold validation. ∗Disclaimer: AUC values should not be directly compared between studies and different figures for infection, sepsis, severe sepsis, and septic shock. Additionally, the lines connecting points do not indicate AUC values changing over time (Figure 5D and 5F); lines only separate the different methods visually. aMachine learning models: dag: dagging (partition data into disjoint subgroups); GBT: gradient boosted trees; GRU: gated recurrent unit; LSTM: long short-term memory; NB: Naïve Bayes; RF: random forest; SVM: support vector machines. bNatural language processing techniques: BoW: Bag-of-words; ClinicalBERT: Clinical Bidirectional Encoder Representations from Transformers; ClinicalBERT-m: ClinicalBERT from merging all textual features to get embeddings; ClinicalBERT-sf; finetuned ClinicalBERT from concatenating individual embeddings of each textual feature; CM: Amazon Comprehend Medical service for named entity recognition; GloVe: Global Vectors for Word Representation; LDA: Latent Dirichlet Allocation; tf-idf: term frequency-inverse document frequency.
Figure 5. Overview of area under the curve (AUC) values for identification or early detection of infection, sepsis, septic shock, and severe sepsis using different data types (structured data and text, structured data only, and text only).∗ Each figure contains the study and year, machine learning model,a and natural language processing techniqueb. (A) AUC values for infection identification. Horng et al47 2017: SVM (BoW) has 2 AUC values; 0.86 when using chief complaints and nursing notes and 0.83 when using only chief complaints. (B) AUC values for early sepsis detection. Amrollahi et al53 AUC values are from detecting 4 h before sepsis onset, and Qin et al55 AUC values are the average from detecting 0 to 6 h before sepsis onset. (C) AUC values for early septic shock detection. Hammoud et al54 AUC values are from detecting 30.64 h before septic shock onset, and Liu et al50 AUC values are from detecting 6.0 to 7.3 h before septic shock onset. (D) AUC values for early sepsis, severe sepsis, or septic shock detection and sepsis identification in Goh et al.52 Different symbols separate data types. (E) AUC values for early septic shock detection for Culliton et al49 using results from the test set. (F) AUC values for early septic shock detection for Culliton et al49 using results from 3-fold validation. ∗Disclaimer: AUC values should not be directly compared between studies and different figures for infection, sepsis, severe sepsis, and septic shock. Additionally, the lines connecting points do not indicate AUC values changing over time (Figure 5D and 5F); lines only separate the different methods visually. aMachine learning models: dag: dagging (partition data into disjoint subgroups); GBT: gradient boosted trees; GRU: gated recurrent unit; LSTM: long short-term memory; NB: Naïve Bayes; RF: random forest; SVM: support vector machines. bNatural language processing techniques: BoW: Bag-of-words; ClinicalBERT: Clinical Bidirectional Encoder Representations from Transformers; ClinicalBERT-m: ClinicalBERT from merging all textual features to get embeddings; ClinicalBERT-sf; finetuned ClinicalBERT from concatenating individual embeddings of each textual feature; CM: Amazon Comprehend Medical service for named entity recognition; GloVe: Global Vectors for Word Representation; LDA: Latent Dirichlet Allocation; tf-idf: term frequency-inverse document frequency.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 137 references

Research works printed but not linked: 1

  1. Kind, 2011, Advances in Patient Safety: New Directions and Alternative Approaches (Vol. 2: Culture and Redesign. AHRQ Publication No. 08-0034-2)

Cited by

See all 125

Metadata

Authors
Yan, M. Y., Gustad, L. T., & Nytrø, Ø.
Affiliations
  • Norwegian University of Science and Technology (NO)
  • Department of Computer Science, Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology, Trondheim, Norway
Corresponding author
Yan, Melissa Y
Venue
Journal of the American Medical Informatics Association
Published
2021-12-13
Volume
29
Issue
3
Pages
559-575
ISSN
  • 1067-5027 (ISSN-L)
  • 1527-974X
OpenAlex
W4200334578
Cited by
119
References
137
Citations by year
2026: 26 · 2025: 41 · 2024: 24 · 2023: 23 · 2022: 5
FWCI
0.94
Type
journal article
Language
en
Open access
Locations
  • Journal of the American Medical Informatics Association (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • NORA - Norwegian Open Research Archives (submittedVersion, cc-by)
Funders
Computational Sepsis Mining and Modelling project through the Norwegian University of Science and Technology Health Strategic Area
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Sepsis Diagnosis and Treatment
  • Health Sciences › Nursing › Research and Theory › Nursing Diagnosis and Documentation
Keywords
sepsis, sepsis prediction, early detection, clinical text, natural language processing, unstructured clinical notes, structured data, septic shock, systemic inflammatory response syndrome, machine learning, vital signs, intensive care
MeSH terms
Machine Learning, Humans, Natural Language Processing, Shock, Septic, Sepsis, Vital Signs

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Sepsis prediction, early detection, and identification using clinical text for machine learning: a systematic review. https://app.cochat.ai/papers/10.1093/jamia/ocab236
The paper
Yan, M. Y., Gustad, L. T., & Nytrø, Ø. (2022). Sepsis prediction, early detection, and identification using clinical text for machine learning: a systematic review. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocab236

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.