A data-driven health index for neonatal morbidities
Summary: Whereas prematurity is a major cause of neonatal mortality, morbidity, and lifelong impairment, the degree of prematurity is usually defined by the gestational age (GA) at delivery rather than by neonatal morbidity. Here we propose a multi-task deep neural network model that simultaneously...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004222004138 |
| _version_ | 1818667956478935040 |
|---|---|
| author | Davide De Francesco Yair J. Blumenfeld Ivana Marić Jonathan A. Mayo Alan L. Chang Ramin Fallahzadeh Thanaphong Phongpreecha Alex J. Butwick Maria Xenochristou Ciaran S. Phibbs Neda H. Bidoki Martin Becker Anthony Culos Camilo Espinosa Qun Liu Karl G. Sylvester Brice Gaudilliere Martin S. Angst David K. Stevenson Gary M. Shaw Nima Aghaeepour |
| author_facet | Davide De Francesco Yair J. Blumenfeld Ivana Marić Jonathan A. Mayo Alan L. Chang Ramin Fallahzadeh Thanaphong Phongpreecha Alex J. Butwick Maria Xenochristou Ciaran S. Phibbs Neda H. Bidoki Martin Becker Anthony Culos Camilo Espinosa Qun Liu Karl G. Sylvester Brice Gaudilliere Martin S. Angst David K. Stevenson Gary M. Shaw Nima Aghaeepour |
| author_sort | Davide De Francesco |
| collection | DOAJ |
| description | Summary: Whereas prematurity is a major cause of neonatal mortality, morbidity, and lifelong impairment, the degree of prematurity is usually defined by the gestational age (GA) at delivery rather than by neonatal morbidity. Here we propose a multi-task deep neural network model that simultaneously predicts twelve neonatal morbidities, as the basis for a new data-driven approach to define prematurity. Maternal demographics, medical history, obstetrical complications, and prenatal fetal findings were obtained from linked birth certificates and maternal/infant hospitalization records for 11,594,786 livebirths in California from 1991 to 2012. Overall, our model outperformed traditional models to assess prematurity which are based on GA and/or birthweight (area under the precision-recall curve was 0.326 for our model, 0.229 for GA, and 0.156 for small for GA). These findings highlight the potential of using machine learning techniques to predict multiple prematurity phenotypes and inform clinical decisions to prevent, diagnose and treat neonatal morbidities. |
| first_indexed | 2024-12-17T06:28:40Z |
| format | Article |
| id | doaj.art-a98cb6982e394532996c898457f9fd44 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-12-17T06:28:40Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-a98cb6982e394532996c898457f9fd442022-12-21T22:00:12ZengElsevieriScience2589-00422022-04-01254104143A data-driven health index for neonatal morbiditiesDavide De Francesco0Yair J. Blumenfeld1Ivana Marić2Jonathan A. Mayo3Alan L. Chang4Ramin Fallahzadeh5Thanaphong Phongpreecha6Alex J. Butwick7Maria Xenochristou8Ciaran S. Phibbs9Neda H. Bidoki10Martin Becker11Anthony Culos12Camilo Espinosa13Qun Liu14Karl G. Sylvester15Brice Gaudilliere16Martin S. Angst17David K. Stevenson18Gary M. Shaw19Nima Aghaeepour20Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Obstetrics and Gynecology, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pathology, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA; Health Economics Resource Center, VA Palo Alto Health Care System, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USADepartment of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, 300 Pasteur Drive, Stanford, CA 94305, USA; Department of Biomedical Data Sciences, Stanford University, Stanford, CA 94305, USA; Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA; Corresponding authorSummary: Whereas prematurity is a major cause of neonatal mortality, morbidity, and lifelong impairment, the degree of prematurity is usually defined by the gestational age (GA) at delivery rather than by neonatal morbidity. Here we propose a multi-task deep neural network model that simultaneously predicts twelve neonatal morbidities, as the basis for a new data-driven approach to define prematurity. Maternal demographics, medical history, obstetrical complications, and prenatal fetal findings were obtained from linked birth certificates and maternal/infant hospitalization records for 11,594,786 livebirths in California from 1991 to 2012. Overall, our model outperformed traditional models to assess prematurity which are based on GA and/or birthweight (area under the precision-recall curve was 0.326 for our model, 0.229 for GA, and 0.156 for small for GA). These findings highlight the potential of using machine learning techniques to predict multiple prematurity phenotypes and inform clinical decisions to prevent, diagnose and treat neonatal morbidities.http://www.sciencedirect.com/science/article/pii/S2589004222004138Biological sciencesCell biologyMolecular biology |
| spellingShingle | Davide De Francesco Yair J. Blumenfeld Ivana Marić Jonathan A. Mayo Alan L. Chang Ramin Fallahzadeh Thanaphong Phongpreecha Alex J. Butwick Maria Xenochristou Ciaran S. Phibbs Neda H. Bidoki Martin Becker Anthony Culos Camilo Espinosa Qun Liu Karl G. Sylvester Brice Gaudilliere Martin S. Angst David K. Stevenson Gary M. Shaw Nima Aghaeepour A data-driven health index for neonatal morbidities iScience Biological sciences Cell biology Molecular biology |
| title | A data-driven health index for neonatal morbidities |
| title_full | A data-driven health index for neonatal morbidities |
| title_fullStr | A data-driven health index for neonatal morbidities |
| title_full_unstemmed | A data-driven health index for neonatal morbidities |
| title_short | A data-driven health index for neonatal morbidities |
| title_sort | data driven health index for neonatal morbidities |
| topic | Biological sciences Cell biology Molecular biology |
| url | http://www.sciencedirect.com/science/article/pii/S2589004222004138 |
| work_keys_str_mv | AT davidedefrancesco adatadrivenhealthindexforneonatalmorbidities AT yairjblumenfeld adatadrivenhealthindexforneonatalmorbidities AT ivanamaric adatadrivenhealthindexforneonatalmorbidities AT jonathanamayo adatadrivenhealthindexforneonatalmorbidities AT alanlchang adatadrivenhealthindexforneonatalmorbidities AT raminfallahzadeh adatadrivenhealthindexforneonatalmorbidities AT thanaphongphongpreecha adatadrivenhealthindexforneonatalmorbidities AT alexjbutwick adatadrivenhealthindexforneonatalmorbidities AT mariaxenochristou adatadrivenhealthindexforneonatalmorbidities AT ciaransphibbs adatadrivenhealthindexforneonatalmorbidities AT nedahbidoki adatadrivenhealthindexforneonatalmorbidities AT martinbecker adatadrivenhealthindexforneonatalmorbidities AT anthonyculos adatadrivenhealthindexforneonatalmorbidities AT camiloespinosa adatadrivenhealthindexforneonatalmorbidities AT qunliu adatadrivenhealthindexforneonatalmorbidities AT karlgsylvester adatadrivenhealthindexforneonatalmorbidities AT bricegaudilliere adatadrivenhealthindexforneonatalmorbidities AT martinsangst adatadrivenhealthindexforneonatalmorbidities AT davidkstevenson adatadrivenhealthindexforneonatalmorbidities AT garymshaw adatadrivenhealthindexforneonatalmorbidities AT nimaaghaeepour adatadrivenhealthindexforneonatalmorbidities AT davidedefrancesco datadrivenhealthindexforneonatalmorbidities AT yairjblumenfeld datadrivenhealthindexforneonatalmorbidities AT ivanamaric datadrivenhealthindexforneonatalmorbidities AT jonathanamayo datadrivenhealthindexforneonatalmorbidities AT alanlchang datadrivenhealthindexforneonatalmorbidities AT raminfallahzadeh datadrivenhealthindexforneonatalmorbidities AT thanaphongphongpreecha datadrivenhealthindexforneonatalmorbidities AT alexjbutwick datadrivenhealthindexforneonatalmorbidities AT mariaxenochristou datadrivenhealthindexforneonatalmorbidities AT ciaransphibbs datadrivenhealthindexforneonatalmorbidities AT nedahbidoki datadrivenhealthindexforneonatalmorbidities AT martinbecker datadrivenhealthindexforneonatalmorbidities AT anthonyculos datadrivenhealthindexforneonatalmorbidities AT camiloespinosa datadrivenhealthindexforneonatalmorbidities AT qunliu datadrivenhealthindexforneonatalmorbidities AT karlgsylvester datadrivenhealthindexforneonatalmorbidities AT bricegaudilliere datadrivenhealthindexforneonatalmorbidities AT martinsangst datadrivenhealthindexforneonatalmorbidities AT davidkstevenson datadrivenhealthindexforneonatalmorbidities AT garymshaw datadrivenhealthindexforneonatalmorbidities AT nimaaghaeepour datadrivenhealthindexforneonatalmorbidities |