Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessment
Background: Functional Gastrointestinal Disorders (FGIDs) can pose a great burden on affected children, their families, and the healthcare system. Due to the lack of knowledge about the precise pathophysiology of FGIDs, a proper identification of children at risk to develop FGIDs has never been atte...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024175470 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533325519355904 |
|---|---|
| author | Flavia Indrio Elio Masciari Flavia Marchese Matteo Rinaldi Gianfranco Maffei Ilaria Gangai Assunta Grillo Roberta De Benedetto Enea Vincenzo Napolitano Isadora Beghetti Luigi Corvaglia Antonio Di Mauro Arianna Aceti |
| author_facet | Flavia Indrio Elio Masciari Flavia Marchese Matteo Rinaldi Gianfranco Maffei Ilaria Gangai Assunta Grillo Roberta De Benedetto Enea Vincenzo Napolitano Isadora Beghetti Luigi Corvaglia Antonio Di Mauro Arianna Aceti |
| author_sort | Flavia Indrio |
| collection | DOAJ |
| description | Background: Functional Gastrointestinal Disorders (FGIDs) can pose a great burden on affected children, their families, and the healthcare system. Due to the lack of knowledge about the precise pathophysiology of FGIDs, a proper identification of children at risk to develop FGIDs has never been attempted. The research aims to identify early-life risk factors for FGIDs such as infantile colic, regurgitation, and functional constipation, within the first year of life. Methods: This prospective observational cohort study enrolled both term and preterm infants from a tertiary care university hospital between January 1, 2020, and December 31, 2022. The study employed both traditional statistical methods and artificial intelligence (AI) techniques, specifically a random forest classification model, to identify key risk factors associated with the development of FGIDs. Based on these findings, an AI-based predictive model will be developed, along with a user-friendly, web-based interface designed for practical risk assessment. Results: 6060 infants were enrolled. 8.1 % were born preterm. According to random forest classification model by AI, birth weight (BW), cord blood pH, and maternal age were the most relevant variables linked to development of FGIDs in the first year of life. Some discrepancies between potential risk factors identified through conventional statistics and AI were detected. Conclusion: For the first time machine learning allowed to identify BW, cord blood pH and maternal age as important variable for risk prediction of FGIDs in the first year of life. This practical risk assessment tool would help clinicians to identify infants at risk of FGIDs who would benefit from a tailored preventive approach. |
| format | Article |
| id | doaj-art-a1650e1dbdb6485aa38a37263e801bcd |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-a1650e1dbdb6485aa38a37263e801bcd2025-01-17T04:51:31ZengElsevierHeliyon2405-84402025-01-01111e41516Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessmentFlavia Indrio0Elio Masciari1Flavia Marchese2Matteo Rinaldi3Gianfranco Maffei4Ilaria Gangai5Assunta Grillo6Roberta De Benedetto7Enea Vincenzo Napolitano8Isadora Beghetti9Luigi Corvaglia10Antonio Di Mauro11Arianna Aceti12Department of Experimental Medicine School of Medicine University of Salento, Lecce, Italy; Corresponding author.Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione, University Federico II, Naples, ItalyDepartment of Medical and Surgical Science Pediatric Section, University of Foggia, 71100, Foggia, ItalyDepartment of Neonatology and NICU, Ospedali Riuniti Foggia, Viale Pinto 1, 71122, Foggia, ItalyDepartment of Neonatology and NICU, Ospedali Riuniti Foggia, Viale Pinto 1, 71122, Foggia, ItalyDepartment of Medical and Surgical Science Pediatric Section, University of Foggia, 71100, Foggia, ItalyDepartment of Medical and Surgical Science Pediatric Section, University of Foggia, 71100, Foggia, ItalyDepartment of Medical and Surgical Science Pediatric Section, University of Foggia, 71100, Foggia, ItalyDipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione, University Federico II, Naples, ItalyDepartment of Medical and Surgical Sciences, University of Bologna, Bologna, ItalyDepartment of Medical and Surgical Sciences, University of Bologna, Bologna, Italy; Neonatal Intensive Care Unit, IRCCS AOUBO, Bologna, ItalyPediatric Primary Care, National Pediatric Health Care System, ASL BA, BARI, ItalyDepartment of Medical and Surgical Sciences, University of Bologna, Bologna, ItalyBackground: Functional Gastrointestinal Disorders (FGIDs) can pose a great burden on affected children, their families, and the healthcare system. Due to the lack of knowledge about the precise pathophysiology of FGIDs, a proper identification of children at risk to develop FGIDs has never been attempted. The research aims to identify early-life risk factors for FGIDs such as infantile colic, regurgitation, and functional constipation, within the first year of life. Methods: This prospective observational cohort study enrolled both term and preterm infants from a tertiary care university hospital between January 1, 2020, and December 31, 2022. The study employed both traditional statistical methods and artificial intelligence (AI) techniques, specifically a random forest classification model, to identify key risk factors associated with the development of FGIDs. Based on these findings, an AI-based predictive model will be developed, along with a user-friendly, web-based interface designed for practical risk assessment. Results: 6060 infants were enrolled. 8.1 % were born preterm. According to random forest classification model by AI, birth weight (BW), cord blood pH, and maternal age were the most relevant variables linked to development of FGIDs in the first year of life. Some discrepancies between potential risk factors identified through conventional statistics and AI were detected. Conclusion: For the first time machine learning allowed to identify BW, cord blood pH and maternal age as important variable for risk prediction of FGIDs in the first year of life. This practical risk assessment tool would help clinicians to identify infants at risk of FGIDs who would benefit from a tailored preventive approach.http://www.sciencedirect.com/science/article/pii/S2405844024175470Functional gastrointestinal disordersNeonatal risk predictionArtificial intelligence |
| spellingShingle | Flavia Indrio Elio Masciari Flavia Marchese Matteo Rinaldi Gianfranco Maffei Ilaria Gangai Assunta Grillo Roberta De Benedetto Enea Vincenzo Napolitano Isadora Beghetti Luigi Corvaglia Antonio Di Mauro Arianna Aceti Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessment Heliyon Functional gastrointestinal disorders Neonatal risk prediction Artificial intelligence |
| title | Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessment |
| title_full | Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessment |
| title_fullStr | Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessment |
| title_full_unstemmed | Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessment |
| title_short | Functional gastrointestinal disorders predictors in neonates and toddlers: A machine learning approach to risk assessment |
| title_sort | functional gastrointestinal disorders predictors in neonates and toddlers a machine learning approach to risk assessment |
| topic | Functional gastrointestinal disorders Neonatal risk prediction Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024175470 |
| work_keys_str_mv | AT flaviaindrio functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT eliomasciari functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT flaviamarchese functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT matteorinaldi functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT gianfrancomaffei functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT ilariagangai functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT assuntagrillo functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT robertadebenedetto functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT eneavincenzonapolitano functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT isadorabeghetti functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT luigicorvaglia functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT antoniodimauro functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment AT ariannaaceti functionalgastrointestinaldisorderspredictorsinneonatesandtoddlersamachinelearningapproachtoriskassessment |