1
|
Bowe AK, Barrett PM. Bridging the academic practice gap in public health-The role of the clinical academic in public health. Public Health 2024; 227:e1-e2. [PMID: 38242829 DOI: 10.1016/j.puhe.2023.12.026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Accepted: 12/21/2023] [Indexed: 01/21/2024]
Affiliation(s)
- A K Bowe
- INFANT Research Centre, Cork, Ireland; Department of Public Health - HSE South West, Health Service Executive, St. Finbarr's Hospital, Douglas Road, Cork, Ireland.
| | - P M Barrett
- INFANT Research Centre, Cork, Ireland; Department of Public Health - HSE South West, Health Service Executive, St. Finbarr's Hospital, Douglas Road, Cork, Ireland; School of Public Health, Western Gateway Building, University College Cork, Cork, Ireland
| |
Collapse
|
2
|
Bowe AK, Lightbody G, O'Boyle DS, Staines A, Murray DM. Predicting low cognitive ability at age 5 years using perinatal data and machine learning. Pediatr Res 2024:10.1038/s41390-023-02914-6. [PMID: 38177251 DOI: 10.1038/s41390-023-02914-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Revised: 10/06/2023] [Accepted: 11/03/2023] [Indexed: 01/06/2024]
Abstract
BACKGROUND There are no early, accurate, scalable methods for identifying infants at high risk of poor cognitive outcomes in childhood. We aim to develop an explainable predictive model, using machine learning and population-based cohort data, for this purpose. METHODS Data were from 8858 participants in the Growing Up in Ireland cohort, a nationally representative study of infants and their primary caregivers (PCGs). Maternal, infant, and socioeconomic characteristics were collected at 9-months and cognitive ability measured at age 5 years. Data preprocessing, synthetic minority oversampling, and feature selection were performed prior to training a variety of machine learning models using ten-fold cross validated grid search to tune hyperparameters. Final models were tested on an unseen test set. RESULTS A random forest (RF) model containing 15 participant-reported features in the first year of infant life, achieved an area under the receiver operating characteristic curve (AUROC) of 0.77 for predicting low cognitive ability at age 5. This model could detect 72% of infants with low cognitive ability, with a specificity of 66%. CONCLUSIONS Model performance would need to be improved before consideration as a population-level screening tool. However, this is a first step towards early, individual, risk stratification to allow targeted childhood screening. IMPACT This study is among the first to investigate whether machine learning methods can be used at a population-level to predict which infants are at high risk of low cognitive ability in childhood. A random forest model using 15 features which could be easily collected in the perinatal period achieved an AUROC of 0.77 for predicting low cognitive ability. Improved predictive performance would be required to implement this model at a population level but this may be a first step towards early, individual, risk stratification.
Collapse
Affiliation(s)
- Andrea K Bowe
- INFANT Research Centre, University College Cork, Cork, Ireland.
| | - Gordon Lightbody
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Electrical and Electronic Engineering, University College Cork, Cork, Ireland
| | | | - Anthony Staines
- School of Nursing, Psychotherapy, and Community Health, Dublin City University, Dublin, Ireland
| | - Deirdre M Murray
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics, Cork University Hospital, Cork, Ireland
| |
Collapse
|
3
|
Bowe AK, Lightbody G, Staines A, Murray DM, Norman M. Prediction of 2-Year Cognitive Outcomes in Very Preterm Infants Using Machine Learning Methods. JAMA Netw Open 2023; 6:e2349111. [PMID: 38147334 PMCID: PMC10751596 DOI: 10.1001/jamanetworkopen.2023.49111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Accepted: 11/09/2023] [Indexed: 12/27/2023] Open
Abstract
Importance Early intervention can improve cognitive outcomes for very preterm infants but is resource intensive. Identifying those who need early intervention most is important. Objective To evaluate a model for use in very preterm infants to predict cognitive delay at 2 years of age using routinely available clinical and sociodemographic data. Design, Setting, and Participants This prognostic study was based on the Swedish Neonatal Quality Register. Nationwide coverage of neonatal data was reached in 2011, and registration of follow-up data opened on January 1, 2015, with inclusion ending on September 31, 2022. A variety of machine learning models were trained and tested to predict cognitive delay. Surviving infants from neonatal units in Sweden with a gestational age younger than 32 weeks and complete data for the Bayley Scales of Infant and Toddler Development, Third Edition cognitive index or cognitive scale scores at 2 years of corrected age were assessed. Infants with major congenital anomalies were excluded. Exposures A total of 90 variables (containing sociodemographic and clinical information on conditions, investigations, and treatments initiated during pregnancy, delivery, and neonatal unit admission) were examined for predictability. Main Outcomes and Measures The main outcome was cognitive function at 2 years, categorized as screening positive for cognitive delay (cognitive index score <90) or exhibiting typical cognitive development (score ≥90). Results A total of 1062 children (median [IQR] birth weight, 880 [720-1100] g; 566 [53.3%] male) were included in the modeling process, of whom 231 (21.8%) had cognitive delay. A logistic regression model containing 26 predictive features achieved an area under the receiver operating curve of 0.77 (95% CI, 0.71-0.83). The 5 most important features for cognitive delay were non-Scandinavian family language, prolonged duration of hospitalization, low birth weight, discharge to other destination than home, and the infant not receiving breastmilk on discharge. At discharge from the neonatal unit, the full model could correctly identify 605 of 650 infants who would have cognitive delay at 24 months (sensitivity, 0.93) and 1081 of 2350 who would not (specificity, 0.46). Conclusions and Relevance The findings of this study suggest that predictive modeling in neonatal care could enable early and targeted intervention for very preterm infants most at risk for developing cognitive impairment.
Collapse
Affiliation(s)
- Andrea K. Bowe
- INFANT Research Centre, University College Cork, Cork, Ireland
| | - Gordon Lightbody
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Electrical and Electronic Engineering, University College Cork, Cork, Ireland
| | - Anthony Staines
- School of Nursing, Psychotherapy, and Community Health, Dublin City University, Dublin, Ireland
| | - Deirdre M. Murray
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics, Cork University Hospital, Cork, Ireland
| | - Mikael Norman
- Department of Clinical Science, Intervention, and Technology, Karolinska University Hospital, Karolinska Institutet, Stockholm, Sweden
- Department of Neonatal Medicine, Karolinska University Hospital, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
4
|
Bowe AK, Lightbody G, Staines A, Murray DM. Big data, machine learning, and population health: predicting cognitive outcomes in childhood. Pediatr Res 2023; 93:300-307. [PMID: 35681091 PMCID: PMC7614199 DOI: 10.1038/s41390-022-02137-1] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/02/2022] [Revised: 05/05/2022] [Accepted: 05/17/2022] [Indexed: 11/09/2022]
Abstract
The application of machine learning (ML) to address population health challenges has received much less attention than its application in the clinical setting. One such challenge is addressing disparities in early childhood cognitive development-a complex public health issue rooted in the social determinants of health, exacerbated by inequity, characterised by intergenerational transmission, and which will continue unabated without novel approaches to address it. Early life, the period of optimal neuroplasticity, presents a window of opportunity for early intervention to improve cognitive development. Unfortunately for many, this window will be missed, and intervention may never occur or occur only when overt signs of cognitive delay manifest. In this review, we explore the potential value of ML and big data analysis in the early identification of children at risk for poor cognitive outcome, an area where there is an apparent dearth of research. We compare and contrast traditional statistical methods with ML approaches, provide examples of how ML has been used to date in the field of neurodevelopmental disorders, and present a discussion of the opportunities and risks associated with its use at a population level. The review concludes by highlighting potential directions for future research in this area. IMPACT: To date, the application of machine learning to address population health challenges in paediatrics lags behind other clinical applications. This review provides an overview of the public health challenge we face in addressing disparities in childhood cognitive development and focuses on the cornerstone of early intervention. Recent advances in our ability to collect large volumes of data, and in analytic capabilities, provide a potential opportunity to improve current practices in this field. This review explores the potential role of machine learning and big data analysis in the early identification of children at risk for poor cognitive outcomes.
Collapse
Affiliation(s)
- Andrea K. Bowe
- grid.7872.a0000000123318773INFANT Research Centre, University College Cork, Cork, Ireland
| | - Gordon Lightbody
- grid.7872.a0000000123318773INFANT Research Centre, University College Cork, Cork, Ireland ,grid.7872.a0000000123318773Department of Electrical and Electronic Engineering, University College Cork, Cork, Ireland
| | - Anthony Staines
- grid.15596.3e0000000102380260School of Nursing, Psychotherapy, and Community Health, Dublin City University, Dublin, Ireland
| | - Deirdre M. Murray
- grid.7872.a0000000123318773INFANT Research Centre, University College Cork, Cork, Ireland
| |
Collapse
|
5
|
Bowe AK, Lightbody G, Staines A, Kiely ME, McCarthy FP, Murray DM. Predicting Low Cognitive Ability at Age 5-Feature Selection Using Machine Learning Methods and Birth Cohort Data. Int J Public Health 2022; 67:1605047. [PMID: 36439276 PMCID: PMC9684182 DOI: 10.3389/ijph.2022.1605047] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2022] [Accepted: 10/24/2022] [Indexed: 02/10/2024] Open
Abstract
Objectives: In this study, we applied the random forest (RF) algorithm to birth-cohort data to train a model to predict low cognitive ability at 5 years of age and to identify the important predictive features. Methods: Data was from 1,070 participants in the Irish population-based BASELINE cohort. A RF model was trained to predict an intelligence quotient (IQ) score ≤90 at age 5 years using maternal, infant, and sociodemographic features. Feature importance was examined and internal validation performed using 10-fold cross validation repeated 5 times. Results The five most important predictive features were the total years of maternal schooling, infant Apgar score at 1 min, socioeconomic index, maternal BMI, and alcohol consumption in the first trimester. On internal validation a parsimonious RF model based on 11 features showed excellent predictive ability, correctly classifying 95% of participants. This provides a foundation suitable for external validation in an unseen cohort. Conclusion: Machine learning approaches to large existing datasets can provide accurate feature selection to improve risk prediction. Further validation of this model is required in cohorts representative of the general population.
Collapse
Affiliation(s)
| | - Gordon Lightbody
- INFANT Research Centre, Cork, Ireland
- Department of Electrical and Electronic Engineering, University College Cork, Cork, Ireland
| | - Anthony Staines
- School of Nursing, Psychotherapy, and Community Health, Dublin City University, Dublin, Ireland
| | - Mairead E. Kiely
- INFANT Research Centre, Cork, Ireland
- Cork Centre for Vitamin D and Nutrition Research, School of Food and Nutritional Sciences, University College Cork, Cork, Ireland
| | - Fergus P. McCarthy
- INFANT Research Centre, Cork, Ireland
- Department of Obstetrics and Gynaecology, Cork University Maternity Hospital, Cork, Ireland
| | - Deirdre M. Murray
- INFANT Research Centre, Cork, Ireland
- Department of Paediatrics, Cork University Hospital, Cork, Ireland
| |
Collapse
|
6
|
Bowe AK, Hourihane J, Staines A, Murray DM. The predictive value of the ages and stages questionnaire in late infancy for low average cognitive ability at age 5. Acta Paediatr 2022; 111:1194-1200. [PMID: 35202483 PMCID: PMC9314849 DOI: 10.1111/apa.16309] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/29/2021] [Revised: 02/10/2022] [Accepted: 02/22/2022] [Indexed: 12/01/2022]
Abstract
Aim This retrospective, longitudinal study examined the predictive value of the ages and stages questionnaire (ASQ) in late infancy for identifying children who progressed to have low cognitive ability at 5 years of age. Methods The ASQ was performed on 755 participants from the Irish BASELINE birth cohort at 24 or 27 months of age. Intelligence quotient was measured at age 5 with the Kaufmann Brief Intelligence Test, Second Edition, and low cognitive ability was defined as a score more than 1 standard deviation below the mean. The ASQ’s predictive value was examined, together with other factors associated with low cognitive ability at 5 years. Results When the ASQ was performed at 24 or 27 months, the overall sensitivity for identifying low cognitive ability at 5 years was 20.8% and the specificity was 91.1%. Using a total score cut‐off point increased the sensitivity to 46.6% and 71.4% at 24 and 27 months, but specificity fell to 74.1% and 67.2%, respectively. After adjusting for ASQ performance, maternal education and family income were strongly associated with cognitive outcomes at 5 years. Conclusion The ASQ did not detect the majority of children with low cognitive ability at age 5. Alternative methods need investigation.
Collapse
Affiliation(s)
- Andrea K. Bowe
- INFANT Research Centre, Paediatric Academic Unit Cork University Hospital Cork Ireland
- Department of Paediatrics, School of Medicine University College Cork Cork Ireland
| | - Jonathan Hourihane
- INFANT Research Centre, Paediatric Academic Unit Cork University Hospital Cork Ireland
- Paediatrics Royal College of Surgeons in Ireland Dublin Ireland
| | - Anthony Staines
- School of Nursing, Psychotherapy and Community Health Dublin City University Dublin Ireland
| | - Deirdre M. Murray
- INFANT Research Centre, Paediatric Academic Unit Cork University Hospital Cork Ireland
- Department of Paediatrics, School of Medicine University College Cork Cork Ireland
| |
Collapse
|
7
|
Bowe AK, Staines A, Murray DM. Below Average Cognitive Ability-An under Researched Risk Factor for Emotional-Behavioural Difficulties in Childhood. Int J Environ Res Public Health 2021; 18:ijerph182412923. [PMID: 34948532 PMCID: PMC8702024 DOI: 10.3390/ijerph182412923] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Revised: 11/24/2021] [Accepted: 11/25/2021] [Indexed: 11/22/2022]
Abstract
Children with below average cognitive ability represent a substantial yet under-researched population for whom cognitive and social demands, which increase in complexity year by year, may pose significant challenges. This observational study examines the longitudinal relationship between early cognitive ability and emotional-behavioral difficulties (EBDs) between the age of three and nine. Participants include 7134 children from the population-based cohort study growing up in Ireland. Cognitive ability was measured at age three using the Picture Similarities Scale. A t-score one to two standard deviations below the mean was defined as below average cognitive ability (n = 767). EBDs were measured using the Strengths and Difficulties Questionnaire (SDQ) at three, five, and nine years of age. Generalized linear mixed models and logistic regression were used to examine the relationship. Below average cognitive ability was an independent predictor of higher longitudinal SDQ scores. After adjustment, children with below average cognitive ability were 1.39 times more likely (AOR 1.39, 95% CI 1.17–1.66, p < 0.001) to experience a clinically significant EBD between the ages of three to nine years. This study demonstrates the increased risk of EBDs for children with below average cognitive ability. A scalable method of early identification of at-risk children should be a research priority for public health, enabling early intervention for cognitive and adaptive outcomes.
Collapse
Affiliation(s)
- Andrea K. Bowe
- INFANT Research Centre, Department of Paediatrics, University College Cork, T12 K8AF Cork, Ireland;
- Correspondence:
| | - Anthony Staines
- School of Nursing, Psychotherapy and Community Health, Dublin City University, 9 Dublin, Ireland;
| | - Deirdre M. Murray
- INFANT Research Centre, Department of Paediatrics, University College Cork, T12 K8AF Cork, Ireland;
- Department of Paediatrics and Child Health, Cork University Maternity Hospital, Wilton, T12 DC4A Cork, Ireland
| |
Collapse
|
8
|
Bowe AK, Healy C, Cannon M, Codd MB. Physical activity and emotional-behavioural difficulties in young people: a longitudinal population-based cohort study. Eur J Public Health 2021; 31:167-173. [PMID: 33176354 DOI: 10.1093/eurpub/ckaa182] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Abstract
BACKGROUND There is growing concern around youth mental health. A population health approach to improve mental health must address, among other issues, economic insecurity, access to housing and education, harm reduction from substance use. As a universal public health intervention, increasing physical activity at a population level may have an important role in our approach. The aim of this study was to examine the longitudinal association between physical activity patterns between childhood and early adolescence and emotional-behavioural difficulties in later adolescence. METHODS This study was based on data from the '98 Child cohort of the Growing Up in Ireland Study. Participants were categorized according to physical activity levels at ages 9 and 13. Emotional-behavioural difficulties at age 17 were measured using the parent-reported Strengths and Difficulties Questionnaire. Logistic regression was used to examine the association between physical activity and emotional-behavioural outcomes. RESULTS Among 4618 participants included in the regression model, those categorized as Inactive (n=1607) or Reducer (n=1662) were more than twice as likely to have emotional-behavioural difficulties at age 17 compared with those who were Active [adjusted odds ratio (AOR) 2.1, 95% CI 1.46-3.01, P<0.001; AOR 1.93, 95% CI 1.34-2.76, P<0.001, respectively]. Among those with emotional-behavioural difficulties at baseline (n=525), those categorized as Active had 2.3-fold reduced odds for emotional-behavioural problems at age 17 compared with those who were Inactive (AOR 0.43, 95% CI 0.23-0.78, P=0.006). CONCLUSIONS Increasing physical activity among adolescents is a safe and sustainable public health intervention associated with improved mental health.
Collapse
Affiliation(s)
- Andrea K Bowe
- School of Public Health, Physiotherapy and Sports Science, University College Dublin, Dublin, Ireland
| | - Colm Healy
- Department of Psychiatry, Royal College of Surgeons in Ireland, Dublin, Ireland
| | - Mary Cannon
- Department of Psychiatry, Royal College of Surgeons in Ireland, Dublin, Ireland
| | - Mary B Codd
- School of Public Health, Physiotherapy and Sports Science, University College Dublin, Dublin, Ireland
| |
Collapse
|
9
|
Bowe AK, Owens M, Codd MB, Lawlor BA, Glynn RW. Physical activity and mental health in an Irish population. Ir J Med Sci 2018; 188:625-631. [PMID: 30019096 DOI: 10.1007/s11845-018-1863-5] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2018] [Accepted: 07/07/2018] [Indexed: 12/24/2022]
Abstract
BACKGROUND Physical activity represents a modifiable behaviour which may be associated with increased likelihood of experiencing positive mental health. AIMS The aim of this study was to examine the association between self-rated physical activity and subjective indicators of both positive and negative mental health in an Irish adult population. METHODS Based on data from a population-based, observational, cross-sectional study, participants were categorised using the International Physical Activity Questionnaire (IPAQ) into those who reported that they did and did not meet recommended physical activity requirements. Self-reported positive and negative mental health indicators were assessed using the Energy and Vitality Index (EVI) and the Mental Health Index-5 (MHI-5) from the SF-36 Health Survey Instrument, respectively. Binary logistic regression was used to identify variables independently associated with self-reported positive and negative mental health. RESULTS A total of 7539 respondents were included in analysis. Overall, 32% reported that they met recommended minimal physical activity requirements. Self-reported positive and negative mental health were reported by 16 and 9% of respondents, respectively. Compared with those who reported meeting-recommended physical activity requirements, those performing no physical activity were three times less likely to report positive mental health (adjusted odds ratio (OR) 0.39, 95% confidence interval (CI) 0.28-0.55) and three times more likely to report negative mental health (OR 3.27, 95% CI 2.38-4.50). CONCLUSION Compared with those who do not, those who report meeting-recommended physical activity requirements are more and less likely to report experiencing positive and negative mental health, respectively. Future policy development around physical activity should take cognisance of the impact of this activity on both physical and mental health outcomes.
Collapse
Affiliation(s)
- Andrea K Bowe
- School of Public Health, Physiotherapy and Sports Science, University College Dublin, Belfield, Dublin 4, Ireland.
- James Connolly Memorial Hospital, Blanchardstown, Dublin 15, Ireland.
| | - Miriam Owens
- Department of Health, Hawkins House, Dublin 2, Ireland
| | - Mary B Codd
- School of Public Health, Physiotherapy and Sports Science, University College Dublin, Belfield, Dublin 4, Ireland
| | - Brian A Lawlor
- NEIL Research Programme, Trinity College Institute of Neuroscience, College Green, Dublin 2, Ireland
- Mercer's Institute for Successful Ageing, St. James's Hospital, Ushers, Dublin 8, Ireland
| | - Ronan W Glynn
- Department of Public Health Medicine, Health Service Executive, Dr. Steevens' Hospital, Steeven's Lane, Dublin 8, Ireland
| |
Collapse
|