Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf
Background<p>With machine learning (ML) carving a niche in diverse medical disciplines, its role in sepsis prediction, a condition where the ‘golden hour’ is critical, is of paramount interest. This study assesses the factors influencing the efficacy of ML models in sepsis prediction, aiming t...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , , , , |
| Published: |
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852025916568371200 |
|---|---|
| author | Mikhail Ya Yadgarov (18543769) |
| author2 | Giovanni Landoni (504703) Levan B. Berikashvili (18543760) Petr A. Polyakov (18543766) Kristina K. Kadantseva (19857978) Anastasia V. Smirnova (18543763) Ivan V. Kuznetsov (19857981) Maria M. Shemetova (18543781) Alexey A. Yakovlev (19857984) Valery V. Likhvantsev (18543757) |
| author2_role | author author author author author author author author author |
| author_facet | Mikhail Ya Yadgarov (18543769) Giovanni Landoni (504703) Levan B. Berikashvili (18543760) Petr A. Polyakov (18543766) Kristina K. Kadantseva (19857978) Anastasia V. Smirnova (18543763) Ivan V. Kuznetsov (19857981) Maria M. Shemetova (18543781) Alexey A. Yakovlev (19857984) Valery V. Likhvantsev (18543757) |
| author_role | author |
| dc.creator.none.fl_str_mv | Mikhail Ya Yadgarov (18543769) Giovanni Landoni (504703) Levan B. Berikashvili (18543760) Petr A. Polyakov (18543766) Kristina K. Kadantseva (19857978) Anastasia V. Smirnova (18543763) Ivan V. Kuznetsov (19857981) Maria M. Shemetova (18543781) Alexey A. Yakovlev (19857984) Valery V. Likhvantsev (18543757) |
| dc.date.none.fl_str_mv | 2024-10-16T12:39:05Z |
| dc.identifier.none.fl_str_mv | 10.3389/fmed.2024.1491358.s001 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Data_Sheet_1_Early_detection_of_sepsis_using_machine_learning_algorithms_a_systematic_review_and_network_meta-analysis_pdf/27241524 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Dermatology Emergency Medicine Gastroenterology and Hepatology Geriatrics and Gerontology Intensive Care Medical Genetics (excl. Cancer Genetics) Nephrology and Urology Nuclear Medicine Orthopaedics Otorhinolaryngology Pathology (excl. Oral Pathology) Radiology and Organ Imaging Foetal Development and Medicine Obstetrics and Gynaecology Family Care Primary Health Care Medical and Health Sciences not elsewhere classified sepsis machine learning network meta-analysis decision trees neural networks |
| dc.title.none.fl_str_mv | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | Background<p>With machine learning (ML) carving a niche in diverse medical disciplines, its role in sepsis prediction, a condition where the ‘golden hour’ is critical, is of paramount interest. This study assesses the factors influencing the efficacy of ML models in sepsis prediction, aiming to optimize their use in clinical practice.</p>Methods<p>We searched Medline, PubMed, Google Scholar, and CENTRAL for studies published from inception to October 2023. We focused on studies predicting sepsis in real-time settings in adult patients in any hospital settings without language limits. The primary outcome was area under the curve (AUC) of the receiver operating characteristic. This meta-analysis was conducted according to PRISMA-NMA guidelines and Cochrane Handbook recommendations. A Network Meta-Analysis using the CINeMA approach compared ML models against traditional scoring systems, with meta-regression identifying factors affecting model quality.</p>Results<p>From 3,953 studies, 73 articles encompassing 457,932 septic patients and 256 models were analyzed. The pooled AUC for ML models was 0.825 and it significantly outperformed traditional scoring systems. Neural Network and Decision Tree models demonstrated the highest AUC metrics. Significant factors influencing AUC included ML model type, dataset type, and prediction window.</p>Conclusion<p>This study establishes the superiority of ML models, especially Neural Network and Decision Tree types, in sepsis prediction. It highlights the importance of model type and dataset characteristics for prediction accuracy, emphasizing the necessity for standardized reporting and validation in ML healthcare applications. These findings call for broader clinical implementation to evaluate the effectiveness of these models in diverse patient groups.</p>Systematic review registration<p>https://inplasy.com/inplasy-2023-12-0062/, identifier, INPLASY2023120062.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_d2d0446dcea05699c7cb3a672743e557 |
| identifier_str_mv | 10.3389/fmed.2024.1491358.s001 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27241524 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdfMikhail Ya Yadgarov (18543769)Giovanni Landoni (504703)Levan B. Berikashvili (18543760)Petr A. Polyakov (18543766)Kristina K. Kadantseva (19857978)Anastasia V. Smirnova (18543763)Ivan V. Kuznetsov (19857981)Maria M. Shemetova (18543781)Alexey A. Yakovlev (19857984)Valery V. Likhvantsev (18543757)DermatologyEmergency MedicineGastroenterology and HepatologyGeriatrics and GerontologyIntensive CareMedical Genetics (excl. Cancer Genetics)Nephrology and UrologyNuclear MedicineOrthopaedicsOtorhinolaryngologyPathology (excl. Oral Pathology)Radiology and Organ ImagingFoetal Development and MedicineObstetrics and GynaecologyFamily CarePrimary Health CareMedical and Health Sciences not elsewhere classifiedsepsismachine learningnetwork meta-analysisdecision treesneural networksBackground<p>With machine learning (ML) carving a niche in diverse medical disciplines, its role in sepsis prediction, a condition where the ‘golden hour’ is critical, is of paramount interest. This study assesses the factors influencing the efficacy of ML models in sepsis prediction, aiming to optimize their use in clinical practice.</p>Methods<p>We searched Medline, PubMed, Google Scholar, and CENTRAL for studies published from inception to October 2023. We focused on studies predicting sepsis in real-time settings in adult patients in any hospital settings without language limits. The primary outcome was area under the curve (AUC) of the receiver operating characteristic. This meta-analysis was conducted according to PRISMA-NMA guidelines and Cochrane Handbook recommendations. A Network Meta-Analysis using the CINeMA approach compared ML models against traditional scoring systems, with meta-regression identifying factors affecting model quality.</p>Results<p>From 3,953 studies, 73 articles encompassing 457,932 septic patients and 256 models were analyzed. The pooled AUC for ML models was 0.825 and it significantly outperformed traditional scoring systems. Neural Network and Decision Tree models demonstrated the highest AUC metrics. Significant factors influencing AUC included ML model type, dataset type, and prediction window.</p>Conclusion<p>This study establishes the superiority of ML models, especially Neural Network and Decision Tree types, in sepsis prediction. It highlights the importance of model type and dataset characteristics for prediction accuracy, emphasizing the necessity for standardized reporting and validation in ML healthcare applications. These findings call for broader clinical implementation to evaluate the effectiveness of these models in diverse patient groups.</p>Systematic review registration<p>https://inplasy.com/inplasy-2023-12-0062/, identifier, INPLASY2023120062.</p>2024-10-16T12:39:05ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.3389/fmed.2024.1491358.s001https://figshare.com/articles/dataset/Data_Sheet_1_Early_detection_of_sepsis_using_machine_learning_algorithms_a_systematic_review_and_network_meta-analysis_pdf/27241524CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/272415242024-10-16T12:39:05Z |
| spellingShingle | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf Mikhail Ya Yadgarov (18543769) Dermatology Emergency Medicine Gastroenterology and Hepatology Geriatrics and Gerontology Intensive Care Medical Genetics (excl. Cancer Genetics) Nephrology and Urology Nuclear Medicine Orthopaedics Otorhinolaryngology Pathology (excl. Oral Pathology) Radiology and Organ Imaging Foetal Development and Medicine Obstetrics and Gynaecology Family Care Primary Health Care Medical and Health Sciences not elsewhere classified sepsis machine learning network meta-analysis decision trees neural networks |
| status_str | publishedVersion |
| title | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf |
| title_full | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf |
| title_fullStr | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf |
| title_full_unstemmed | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf |
| title_short | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf |
| title_sort | Data_Sheet_1_Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis.pdf |
| topic | Dermatology Emergency Medicine Gastroenterology and Hepatology Geriatrics and Gerontology Intensive Care Medical Genetics (excl. Cancer Genetics) Nephrology and Urology Nuclear Medicine Orthopaedics Otorhinolaryngology Pathology (excl. Oral Pathology) Radiology and Organ Imaging Foetal Development and Medicine Obstetrics and Gynaecology Family Care Primary Health Care Medical and Health Sciences not elsewhere classified sepsis machine learning network meta-analysis decision trees neural networks |