This preprint is under consideration at BMC Medical Informatics and Decision Making. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Research article
Tatsuma Shoji
Department of Anestheology and Pain Medicine, Fujita Health Bantane Hopspital
Corresponding Author
ORCiD: https://orcid.org/0000-0001-6512-7924
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background
The increasing availability of electronic health records has made it possible to construct and implement models for predicting intensive care unit (ICU) mortality using machine learning. However, the algorithms used are not clearly described, and the performance of the model remains low owing to several missing values, which is unavoidable in big databases.
Methods
We developed an algorithm for subgrouping patients based on missing event patterns using the Philips eICU Research Institute (eRI) database as an example. The eRI database contains data associated with 200,859 ICU admissions from many hospitals (>400) and is freely available. We then constructed a model for each subgroup using random forest classifiers and integrated the models. Finally, we compared the performance of the integrated model with the Acute Physiology and Chronic Health Evaluation (APACHE) scoring system, one of the best known predictors of patient mortality, and the imputation approach-based model.
Results
Subgrouping and patient mortality prediction were separately performed on two groups: the sepsis group (the ICU admission diagnosis of which is sepsis) and the non-sepsis group (a complementary subset of the sepsis group). The subgrouping algorithm identified a unique, clinically interpretable missing event patterns and divided the sepsis and non-sepsis groups into five and seven subgroups, respectively. The integrated model, which comprises five models for the sepsis group or seven models for the non-sepsis group, greatly outperformed the APACHE IV or IVa, with an area under the receiver operating characteristic (AUROC) of 0.91 (95% confidence interval 0.89–0.92) compared with 0.79 (0.76–0.81) for the APACHE system in the sepsis group and an AUROC of 0.90 (0.89–0.91) compared with 0.86 (0.85–0.87) in the non-sepsis group. Moreover, our model outperformed the imputation approach-based model, which had an AUROC of 0.85 (0.83–0.87) and 0.87 (0.86–0.88) in the sepsis and non-sepsis groups, respectively.
Conclusions
We developed a method to predict patient mortality based on missing event patterns. Our method more accurately predicts patient mortality than others. Our results indicate that subgrouping, based on missing event patterns, instead of imputation is essential and effective for machine learning against patient heterogeneity.
Trial registration
Not applicable.
Keywords
ICU, patient mortality, Acute Physiology and Chronic Health Evaluation scoring, machine learning, missing values
Figure 1
Figure 2
Figure 3
Figure 4
This is a list of supplementary files associated with this preprint. Click to download.
- supp1.xlsx
Supplementary tables.
- Additionalfile2.pdf
Supplementary figures.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 1
Posted 31 Mar, 2021
No community comments so far
Editorial decision: Withdrawn by author
On 24 Apr, 2021
Review #3 received
Received 22 Apr, 2021
Review #2 received
Received 18 Apr, 2021
Reviewer #3 agreed
On 06 Apr, 2021
Reviewer #2 agreed
On 04 Apr, 2021
Review #1 received
Received 04 Apr, 2021
Reviewers invited
Invitations sent on 03 Apr, 2021
Reviewer #1 agreed
On 03 Apr, 2021
Editor assigned
On 31 Mar, 2021
Submission checks complete
On 25 Mar, 2021
Editor invited
On 21 Mar, 2021
First submitted
On 19 Mar, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Medical Informatics
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
This preprint is under consideration at BMC Medical Informatics and Decision Making. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research article
Tatsuma Shoji
Department of Anestheology and Pain Medicine, Fujita Health Bantane Hopspital
Corresponding Author
ORCiD: https://orcid.org/0000-0001-6512-7924
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 1
Posted 31 Mar, 2021
No community comments so far
Editorial decision: Withdrawn by author
On 24 Apr, 2021
Review #3 received
Received 22 Apr, 2021
Review #2 received
Received 18 Apr, 2021
Reviewer #3 agreed
On 06 Apr, 2021
Reviewer #2 agreed
On 04 Apr, 2021
Review #1 received
Received 04 Apr, 2021
Reviewers invited
Invitations sent on 03 Apr, 2021
Reviewer #1 agreed
On 03 Apr, 2021
Editor assigned
On 31 Mar, 2021
Submission checks complete
On 25 Mar, 2021
Editor invited
On 21 Mar, 2021
First submitted
On 19 Mar, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Medical Informatics
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background
The increasing availability of electronic health records has made it possible to construct and implement models for predicting intensive care unit (ICU) mortality using machine learning. However, the algorithms used are not clearly described, and the performance of the model remains low owing to several missing values, which is unavoidable in big databases.
Methods
We developed an algorithm for subgrouping patients based on missing event patterns using the Philips eICU Research Institute (eRI) database as an example. The eRI database contains data associated with 200,859 ICU admissions from many hospitals (>400) and is freely available. We then constructed a model for each subgroup using random forest classifiers and integrated the models. Finally, we compared the performance of the integrated model with the Acute Physiology and Chronic Health Evaluation (APACHE) scoring system, one of the best known predictors of patient mortality, and the imputation approach-based model.
Results
Subgrouping and patient mortality prediction were separately performed on two groups: the sepsis group (the ICU admission diagnosis of which is sepsis) and the non-sepsis group (a complementary subset of the sepsis group). The subgrouping algorithm identified a unique, clinically interpretable missing event patterns and divided the sepsis and non-sepsis groups into five and seven subgroups, respectively. The integrated model, which comprises five models for the sepsis group or seven models for the non-sepsis group, greatly outperformed the APACHE IV or IVa, with an area under the receiver operating characteristic (AUROC) of 0.91 (95% confidence interval 0.89–0.92) compared with 0.79 (0.76–0.81) for the APACHE system in the sepsis group and an AUROC of 0.90 (0.89–0.91) compared with 0.86 (0.85–0.87) in the non-sepsis group. Moreover, our model outperformed the imputation approach-based model, which had an AUROC of 0.85 (0.83–0.87) and 0.87 (0.86–0.88) in the sepsis and non-sepsis groups, respectively.
Conclusions
We developed a method to predict patient mortality based on missing event patterns. Our method more accurately predicts patient mortality than others. Our results indicate that subgrouping, based on missing event patterns, instead of imputation is essential and effective for machine learning against patient heterogeneity.
Trial registration
Not applicable.
Figure 1
Figure 2
Figure 3
Figure 4
This is a list of supplementary files associated with this preprint. Click to download.
- supp1.xlsx
Supplementary tables.
- Additionalfile2.pdf
Supplementary figures.
Loading...