Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study
BackgroundOwing to the nature of health data, their sharing and reuse for research are limited by legal, technical, and ethical implications. In this sense, to address that challenge and facilitate and promote the discovery of scientific knowledge, the Findable, Accessible, I...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2022-06-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2022/6/e35307 |
| _version_ | 1797735026812518400 |
|---|---|
| author | Celia Alvarez-Romero Alicia Martinez-Garcia Jara Ternero Vega Pablo Díaz-Jimènez Carlos Jimènez-Juan María Dolores Nieto-Martín Esther Román Villarán Tomi Kovacevic Darijo Bokan Sanja Hromis Jelena Djekic Malbasa Suzana Beslać Bojan Zaric Mert Gencturk A Anil Sinaci Manuel Ollero Baturone Carlos Luis Parra Calderón |
| author_facet | Celia Alvarez-Romero Alicia Martinez-Garcia Jara Ternero Vega Pablo Díaz-Jimènez Carlos Jimènez-Juan María Dolores Nieto-Martín Esther Román Villarán Tomi Kovacevic Darijo Bokan Sanja Hromis Jelena Djekic Malbasa Suzana Beslać Bojan Zaric Mert Gencturk A Anil Sinaci Manuel Ollero Baturone Carlos Luis Parra Calderón |
| author_sort | Celia Alvarez-Romero |
| collection | DOAJ |
| description |
BackgroundOwing to the nature of health data, their sharing and reuse for research are limited by legal, technical, and ethical implications. In this sense, to address that challenge and facilitate and promote the discovery of scientific knowledge, the Findable, Accessible, Interoperable, and Reusable (FAIR) principles help organizations to share research data in a secure, appropriate, and useful way for other researchers.
ObjectiveThe objective of this study was the FAIRification of existing health research data sets and applying a federated machine learning architecture on top of the FAIRified data sets of different health research performing organizations. The entire FAIR4Health solution was validated through the assessment of a federated model for real-time prediction of 30-day readmission risk in patients with chronic obstructive pulmonary disease (COPD).
MethodsThe application of the FAIR principles on health research data sets in 3 different health care settings enabled a retrospective multicenter study for the development of specific federated machine learning models for the early prediction of 30-day readmission risk in patients with COPD. This predictive model was generated upon the FAIR4Health platform. Finally, an observational prospective study with 30 days follow-up was conducted in 2 health care centers from different countries. The same inclusion and exclusion criteria were used in both retrospective and prospective studies.
ResultsClinical validation was demonstrated through the implementation of federated machine learning models on top of the FAIRified data sets from different health research performing organizations. The federated model for predicting the 30-day hospital readmission risk was trained using retrospective data from 4.944 patients with COPD. The assessment of the predictive model was performed using the data of 100 recruited (22 from Spain and 78 from Serbia) out of 2070 observed (records viewed) patients during the observational prospective study, which was executed from April 2021 to September 2021. Significant accuracy (0.98) and precision (0.25) of the predictive model generated upon the FAIR4Health platform were observed. Therefore, the generated prediction of 30-day readmission risk was confirmed in 87% (87/100) of cases.
ConclusionsImplementing a FAIR data policy in health research performing organizations to facilitate data sharing and reuse is relevant and needed, following the discovery, access, integration, and analysis of health research data. The FAIR4Health project proposes a technological solution in the health domain to facilitate alignment with the FAIR principles. |
| first_indexed | 2024-03-12T12:53:00Z |
| format | Article |
| id | doaj.art-ea5252959eb94fe3ae33423173897ca0 |
| institution | Directory Open Access Journal |
| issn | 2291-9694 |
| language | English |
| last_indexed | 2024-03-12T12:53:00Z |
| publishDate | 2022-06-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj.art-ea5252959eb94fe3ae33423173897ca02023-08-28T22:12:52ZengJMIR PublicationsJMIR Medical Informatics2291-96942022-06-01106e3530710.2196/35307Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation StudyCelia Alvarez-Romerohttps://orcid.org/0000-0001-8647-9515Alicia Martinez-Garciahttps://orcid.org/0000-0001-5614-7747Jara Ternero Vegahttps://orcid.org/0000-0002-3978-3079Pablo Díaz-Jimènezhttps://orcid.org/0000-0002-0539-2942Carlos Jimènez-Juanhttps://orcid.org/0000-0002-7389-4151María Dolores Nieto-Martínhttps://orcid.org/0000-0002-8488-2279Esther Román Villaránhttps://orcid.org/0000-0001-8360-4704Tomi Kovacevichttps://orcid.org/0000-0002-2903-5261Darijo Bokanhttps://orcid.org/0000-0002-0422-3071Sanja Hromishttps://orcid.org/0000-0001-6132-1551Jelena Djekic Malbasahttps://orcid.org/0000-0003-4936-2670Suzana Beslaćhttps://orcid.org/0000-0001-7452-0066Bojan Zarichttps://orcid.org/0000-0003-3215-8390Mert Gencturkhttps://orcid.org/0000-0003-2697-5722A Anil Sinacihttps://orcid.org/0000-0003-4397-3382Manuel Ollero Baturonehttps://orcid.org/0000-0003-4648-1826Carlos Luis Parra Calderónhttps://orcid.org/0000-0003-2609-575X BackgroundOwing to the nature of health data, their sharing and reuse for research are limited by legal, technical, and ethical implications. In this sense, to address that challenge and facilitate and promote the discovery of scientific knowledge, the Findable, Accessible, Interoperable, and Reusable (FAIR) principles help organizations to share research data in a secure, appropriate, and useful way for other researchers. ObjectiveThe objective of this study was the FAIRification of existing health research data sets and applying a federated machine learning architecture on top of the FAIRified data sets of different health research performing organizations. The entire FAIR4Health solution was validated through the assessment of a federated model for real-time prediction of 30-day readmission risk in patients with chronic obstructive pulmonary disease (COPD). MethodsThe application of the FAIR principles on health research data sets in 3 different health care settings enabled a retrospective multicenter study for the development of specific federated machine learning models for the early prediction of 30-day readmission risk in patients with COPD. This predictive model was generated upon the FAIR4Health platform. Finally, an observational prospective study with 30 days follow-up was conducted in 2 health care centers from different countries. The same inclusion and exclusion criteria were used in both retrospective and prospective studies. ResultsClinical validation was demonstrated through the implementation of federated machine learning models on top of the FAIRified data sets from different health research performing organizations. The federated model for predicting the 30-day hospital readmission risk was trained using retrospective data from 4.944 patients with COPD. The assessment of the predictive model was performed using the data of 100 recruited (22 from Spain and 78 from Serbia) out of 2070 observed (records viewed) patients during the observational prospective study, which was executed from April 2021 to September 2021. Significant accuracy (0.98) and precision (0.25) of the predictive model generated upon the FAIR4Health platform were observed. Therefore, the generated prediction of 30-day readmission risk was confirmed in 87% (87/100) of cases. ConclusionsImplementing a FAIR data policy in health research performing organizations to facilitate data sharing and reuse is relevant and needed, following the discovery, access, integration, and analysis of health research data. The FAIR4Health project proposes a technological solution in the health domain to facilitate alignment with the FAIR principles.https://medinform.jmir.org/2022/6/e35307 |
| spellingShingle | Celia Alvarez-Romero Alicia Martinez-Garcia Jara Ternero Vega Pablo Díaz-Jimènez Carlos Jimènez-Juan María Dolores Nieto-Martín Esther Román Villarán Tomi Kovacevic Darijo Bokan Sanja Hromis Jelena Djekic Malbasa Suzana Beslać Bojan Zaric Mert Gencturk A Anil Sinaci Manuel Ollero Baturone Carlos Luis Parra Calderón Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study JMIR Medical Informatics |
| title | Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study |
| title_full | Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study |
| title_fullStr | Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study |
| title_full_unstemmed | Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study |
| title_short | Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study |
| title_sort | predicting 30 day readmission risk for patients with chronic obstructive pulmonary disease through a federated machine learning architecture on findable accessible interoperable and reusable fair data development and validation study |
| url | https://medinform.jmir.org/2022/6/e35307 |
| work_keys_str_mv | AT celiaalvarezromero predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT aliciamartinezgarcia predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT jaraternerovega predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT pablodiazjimenez predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT carlosjimenezjuan predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT mariadoloresnietomartin predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT estherromanvillaran predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT tomikovacevic predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT darijobokan predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT sanjahromis predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT jelenadjekicmalbasa predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT suzanabeslac predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT bojanzaric predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT mertgencturk predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT aanilsinaci predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT manuelollerobaturone predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy AT carlosluisparracalderon predicting30dayreadmissionriskforpatientswithchronicobstructivepulmonarydiseasethroughafederatedmachinelearningarchitectureonfindableaccessibleinteroperableandreusablefairdatadevelopmentandvalidationstudy |