Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical Care
We propose a novel method that uses associative classification and odds ratios to predict in-hospital mortality in emergency and critical care. Manual mortality risk scores have previously been used to assess the care needed for each patient and their need for palliative measures. Automated approach...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-11-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2021.785711/full |
| _version_ | 1818407004285173760 |
|---|---|
| author | Oliver Haas Oliver Haas Andreas Maier Eva Rothgang |
| author_facet | Oliver Haas Oliver Haas Andreas Maier Eva Rothgang |
| author_sort | Oliver Haas |
| collection | DOAJ |
| description | We propose a novel method that uses associative classification and odds ratios to predict in-hospital mortality in emergency and critical care. Manual mortality risk scores have previously been used to assess the care needed for each patient and their need for palliative measures. Automated approaches allow providers to get a quick and objective estimation based on electronic health records. We use association rule mining to find relevant patterns in the dataset. The odds ratio is used instead of classical association rule mining metrics as a quality measure to analyze association instead of frequency. The resulting measures are used to estimate the in-hospital mortality risk. We compare two prediction models: one minimal model with socio-demographic factors that are available at the time of admission and can be provided by the patients themselves, namely gender, ethnicity, type of insurance, language, and marital status, and a full model that additionally includes clinical information like diagnoses, medication, and procedures. The method was tested and validated on MIMIC-IV, a publicly available clinical dataset. The minimal prediction model achieved an area under the receiver operating characteristic curve value of 0.69, while the full prediction model achieved a value of 0.98. The models serve different purposes. The minimal model can be used as a first risk assessment based on patient-reported information. The full model expands on this and provides an updated risk assessment each time a new variable occurs in the clinical case. In addition, the rules in the models allow us to analyze the dataset based on data-backed rules. We provide several examples of interesting rules, including rules that hint at errors in the underlying data, rules that correspond to existing epidemiological research, and rules that were previously unknown and can serve as starting points for future studies. |
| first_indexed | 2024-12-14T09:20:56Z |
| format | Article |
| id | doaj.art-1eeed6ee220448a6aad391d4e27c93b8 |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-12-14T09:20:56Z |
| publishDate | 2021-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-1eeed6ee220448a6aad391d4e27c93b82022-12-21T23:08:19ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2021-11-01810.3389/fmed.2021.785711785711Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical CareOliver Haas0Oliver Haas1Andreas Maier2Eva Rothgang3Department of Industrial Engineering and Health, Institute of Medical Engineering, Technical University Amberg-Weiden, Weiden, GermanyPattern Recognition Lab, Department of Computer Science, Technical Faculty, Friedrich-Alexander University, Erlangen, GermanyPattern Recognition Lab, Department of Computer Science, Technical Faculty, Friedrich-Alexander University, Erlangen, GermanyDepartment of Industrial Engineering and Health, Institute of Medical Engineering, Technical University Amberg-Weiden, Weiden, GermanyWe propose a novel method that uses associative classification and odds ratios to predict in-hospital mortality in emergency and critical care. Manual mortality risk scores have previously been used to assess the care needed for each patient and their need for palliative measures. Automated approaches allow providers to get a quick and objective estimation based on electronic health records. We use association rule mining to find relevant patterns in the dataset. The odds ratio is used instead of classical association rule mining metrics as a quality measure to analyze association instead of frequency. The resulting measures are used to estimate the in-hospital mortality risk. We compare two prediction models: one minimal model with socio-demographic factors that are available at the time of admission and can be provided by the patients themselves, namely gender, ethnicity, type of insurance, language, and marital status, and a full model that additionally includes clinical information like diagnoses, medication, and procedures. The method was tested and validated on MIMIC-IV, a publicly available clinical dataset. The minimal prediction model achieved an area under the receiver operating characteristic curve value of 0.69, while the full prediction model achieved a value of 0.98. The models serve different purposes. The minimal model can be used as a first risk assessment based on patient-reported information. The full model expands on this and provides an updated risk assessment each time a new variable occurs in the clinical case. In addition, the rules in the models allow us to analyze the dataset based on data-backed rules. We provide several examples of interesting rules, including rules that hint at errors in the underlying data, rules that correspond to existing epidemiological research, and rules that were previously unknown and can serve as starting points for future studies.https://www.frontiersin.org/articles/10.3389/fmed.2021.785711/fullin-hospital mortalitycritical careodds ratioassociative classificationmachine learningartificial intelligence |
| spellingShingle | Oliver Haas Oliver Haas Andreas Maier Eva Rothgang Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical Care Frontiers in Medicine in-hospital mortality critical care odds ratio associative classification machine learning artificial intelligence |
| title | Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical Care |
| title_full | Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical Care |
| title_fullStr | Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical Care |
| title_full_unstemmed | Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical Care |
| title_short | Rule-Based Models for Risk Estimation and Analysis of In-hospital Mortality in Emergency and Critical Care |
| title_sort | rule based models for risk estimation and analysis of in hospital mortality in emergency and critical care |
| topic | in-hospital mortality critical care odds ratio associative classification machine learning artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2021.785711/full |
| work_keys_str_mv | AT oliverhaas rulebasedmodelsforriskestimationandanalysisofinhospitalmortalityinemergencyandcriticalcare AT oliverhaas rulebasedmodelsforriskestimationandanalysisofinhospitalmortalityinemergencyandcriticalcare AT andreasmaier rulebasedmodelsforriskestimationandanalysisofinhospitalmortalityinemergencyandcriticalcare AT evarothgang rulebasedmodelsforriskestimationandanalysisofinhospitalmortalityinemergencyandcriticalcare |