Mei Chien Chua
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mei Chien Chua has a total of 105 co-authors. Here are the top co-authors by number of shared publications:
- Fabian Yap
KK Women’s and Children’s Hospital, Singapore
7 shared publications - Agathe Foussat
Danone Nutricia Research, Singapore, Singapore
4 shared publications - Daniel Chan
Duke-NUS Medical School, 8 College Rd, Singapore, 169857, Singapore, 65 93871908
4 shared publications - Jill Wong
Danone Nutricia Research, Singapore, Singapore
4 shared publications - Suresh Chandran
Department of Neonatology KK Women's and Children's Hospital Singapore
4 shared publications - Amudha Jayanthi Anand
Department of Neonatology, KK Women’s and Children’s Hospital, Singapore
3 shared publications
Latest Publications
- 14 November 2026
- Published by Springer Nature in Pediatric Research
- p. 1-6
Postprandial splanchnic hyperemia as a biomarker for gut immaturity and feeding intolerance in preterm infants
- 14 November 2026
- Published by Springer Nature in Pediatric Research
- p. 1-6
Postprandial splanchnic hyperemia as a biomarker for gut immaturity and feeding intolerance in preterm infants
- Open Access
- 11 May 2026
- Published by JMIR Publications Inc. in JMIR Pediatrics and Parenting
- Vol. 9 (1) , e86139
Usability and Acceptability of a Digital Health App to Support Infant Feeding and Lifestyle Behaviors: Mixed Methods Pilot Study
Background: Childhood obesity is a global health concern with long-term cardiometabolic and psychosocial consequences. Establishing healthy feeding and lifestyle behaviors from infancy is critical to population health efforts with a life course perspective. Recently, digital health applications have gained traction in reaching out to parents and promoting healthy feeding behaviors. Objective: The aim of this study was to evaluate the usability and acceptability of the Feeding, Lifestyle, Activity Goals app in providing parents with evidence-based guidance and tailored advice to promote healthier eating behaviors and lifestyle habits among infants. Methods: We conducted a mixed methods pilot study among parents of infants aged 0 to 24 months recruited from a tertiary maternity and children’s hospital in Singapore. Participants used the digital health app for 7 days. Usability was assessed using the validated System Usability Scale (score range 0‐100, with ≥70 indicating acceptable usability). Acceptability was explored via open-ended questionnaires on satisfaction, relevance, and user experience, with qualitative data analyzed thematically by 2 independent coders to ensure rigor. Results: A total of 26 parents of infants aged 3 weeks to 23 months completed the study. The app demonstrated good usability, with a mean System Usability Scale score of 71.3 (SD 11.0). Parents valued its role in organizing infant care; promoting self-reflection on parenting practices; and providing personalized, evidence-based recommendations. These benefits were particularly appreciated by first-time parents and those with multiple caregiving responsibilities. Challenges included an unintuitive user interface, high manual data entry burden, and advisory content that was occasionally overly general or text heavy. These insights highlight clear priorities for onward efforts in optimization. Conclusions: Results of our mixed methods evaluation indicate that our digital health app demonstrated good usability and acceptability among parents of infants. Targeted refinements to the interface, data entry processes, and content delivery are warranted before large-scale evaluation to determine its impact on early-life health behaviors and obesity prevention.
- 11 May 2026
- Published by JMIR Publications Inc. in JMIR Pediatrics and Parenting
- Vol. 9 (1) , e86139
Open AccessUsability and Acceptability of a Digital Health App to Support Infant Feeding and Lifestyle Behaviors: Mixed Methods Pilot Study
Background: Childhood obesity is a global health concern with long-term cardiometabolic and psychosocial consequences. Establishing healthy feeding and lifestyle behaviors from infancy is critical to population health efforts with a life course perspective. Recently, digital health applications have gained traction in reaching out to parents and promoting healthy feeding behaviors. Objective: The aim of this study was to evaluate the usability and acceptability of the Feeding, Lifestyle, Activity Goals app in providing parents with evidence-based guidance and tailored advice to promote healthier eating behaviors and lifestyle habits among infants. Methods: We conducted a mixed methods pilot study among parents of infants aged 0 to 24 months recruited from a tertiary maternity and children’s hospital in Singapore. Participants used the digital health app for 7 days. Usability was assessed using the validated System Usability Scale (score range 0‐100, with ≥70 indicating acceptable usability). Acceptability was explored via open-ended questionnaires on satisfaction, relevance, and user experience, with qualitative data analyzed thematically by 2 independent coders to ensure rigor. Results: A total of 26 parents of infants aged 3 weeks to 23 months completed the study. The app demonstrated good usability, with a mean System Usability Scale score of 71.3 (SD 11.0). Parents valued its role in organizing infant care; promoting self-reflection on parenting practices; and providing personalized, evidence-based recommendations. These benefits were particularly appreciated by first-time parents and those with multiple caregiving responsibilities. Challenges included an unintuitive user interface, high manual data entry burden, and advisory content that was occasionally overly general or text heavy. These insights highlight clear priorities for onward efforts in optimization. Conclusions: Results of our mixed methods evaluation indicate that our digital health app demonstrated good usability and acceptability among parents of infants. Targeted refinements to the interface, data entry processes, and content delivery are warranted before large-scale evaluation to determine its impact on early-life health behaviors and obesity prevention.
- 5 February 2026
- Published by Springer Nature in Journal of Perinatology
- Vol. 46 (10) , 1922-1928
Variable clinical and hemodynamic effect of sildenafil in extreme premature infants with bronchopulmonary dysplasia-associated pulmonary hypertension
To explore the clinical and hemodynamic effects of sildenafil in extreme premature population with bronchopulmonary dysplasia (BPD) associated pulmonary hypertension (PH). Single-centre retrospective study on infants born <28 weeks with BPD-PH on sildenafil. The respiratory severity score was assessed at four time points (72 h-4wks). Echocardiographic data were compared before and after sildenafil. Sixty-four infants were included. The mean gestational age was 26.1 ± 1.6 weeks. 30(47%) infants showed improvement in RSS, 17(26%) had no change and 17(26%) showed poor RSS. 15(88) in the poor RSS group had an early onset PH. The improved RSS group reduced tricuspid regurgitation (3.3 ± 0.6 to 2.7 ± 0.5 m/s, p = 0.007). The pulmonary acceleration time (PAAT), PAAT/RVET (right ventricular ejection time), and RV fractional area change showed improvement in all groups. The poor RSS group had high pretreatment systolic blood pressure (90.7 ± 8.8 vs 82.7 ± 4.4 mmHg, p = 0.04). Variable clinical response to sildenafil warrants close monitoring of respiratory status.
- 5 February 2026
- Published by Springer Nature in Journal of Perinatology
- Vol. 46 (10) , 1922-1928
Variable clinical and hemodynamic effect of sildenafil in extreme premature infants with bronchopulmonary dysplasia-associated pulmonary hypertension
To explore the clinical and hemodynamic effects of sildenafil in extreme premature population with bronchopulmonary dysplasia (BPD) associated pulmonary hypertension (PH). Single-centre retrospective study on infants born <28 weeks with BPD-PH on sildenafil. The respiratory severity score was assessed at four time points (72 h-4wks). Echocardiographic data were compared before and after sildenafil. Sixty-four infants were included. The mean gestational age was 26.1 ± 1.6 weeks. 30(47%) infants showed improvement in RSS, 17(26%) had no change and 17(26%) showed poor RSS. 15(88) in the poor RSS group had an early onset PH. The improved RSS group reduced tricuspid regurgitation (3.3 ± 0.6 to 2.7 ± 0.5 m/s, p = 0.007). The pulmonary acceleration time (PAAT), PAAT/RVET (right ventricular ejection time), and RV fractional area change showed improvement in all groups. The poor RSS group had high pretreatment systolic blood pressure (90.7 ± 8.8 vs 82.7 ± 4.4 mmHg, p = 0.04). Variable clinical response to sildenafil warrants close monitoring of respiratory status.
- Open Access
Mid-Pregnancy Maternal Anxiety Mediates the Association Between Maternal Chronotype and Breastfeeding Duration
Background: Maternal chronotype, maternal sleep, and breastfeeding practices are separately associated with maternal mood. However, it is not known if maternal mood mediates the associations between maternal chronotype or maternal sleep and breastfeeding duration. Objective: To investigate whether maternal mood mediates the associations of maternal chronotype and maternal prenatal sleep with breastfeeding duration in a multiethnic cohort of Singaporean mothers. Methods: In a prospective cohort study, caregivers of term-born, singleton infants (N = 340) completed the Horne–Östberg Morningness–Eveningness Questionnaire (MEQ; 54 months), Pittsburgh Sleep Quality Index (PSQI; 26 weeks gestation), Edinburgh Postnatal Depression Scale (EPDS; 26–28 weeks gestation) and State–Trait Anxiety Inventory (STAI-state, STAI-trait; 26–28 weeks gestation) and reported breastfeeding practices from 3 weeks to ≥12 months. Regression and mediation analyses were adjusted for maternal age, parity, maternal education, ethnicity, pre-pregnancy BMI, and mode of delivery. Results: Morningness was significantly associated with a longer breastfeeding duration (β = 0.02, p = 0.037) and lower maternal anxiety symptoms (STAI-state: β = −0.19, p = 0.006 and STAI-trait: β = −0.18, p = 0.004). Lower maternal anxiety symptoms were significantly associated with a longer breastfeeding duration (STAI-state: β = −0.02, p = 0.003; STAI-trait: β = −0.02, p = 0.016). STAI-state, but not STAI-trait or EPDS, mediates the association between maternal chronotype and breastfeeding duration (βindirect = 0.004 (0.0004, 0.009)). Maternal mood did not mediate the association between maternal night sleep duration and breastfeeding duration. Conclusions: Maternal state-anxiety constitutes a behavioral pathway through which maternal chronotype influences breastfeeding duration. Strategies to target maternal anxiety in pregnant women with eveningness tendencies to promote breastfeeding duration are warranted.
Open AccessMid-Pregnancy Maternal Anxiety Mediates the Association Between Maternal Chronotype and Breastfeeding Duration
Background: Maternal chronotype, maternal sleep, and breastfeeding practices are separately associated with maternal mood. However, it is not known if maternal mood mediates the associations between maternal chronotype or maternal sleep and breastfeeding duration. Objective: To investigate whether maternal mood mediates the associations of maternal chronotype and maternal prenatal sleep with breastfeeding duration in a multiethnic cohort of Singaporean mothers. Methods: In a prospective cohort study, caregivers of term-born, singleton infants (N = 340) completed the Horne–Östberg Morningness–Eveningness Questionnaire (MEQ; 54 months), Pittsburgh Sleep Quality Index (PSQI; 26 weeks gestation), Edinburgh Postnatal Depression Scale (EPDS; 26–28 weeks gestation) and State–Trait Anxiety Inventory (STAI-state, STAI-trait; 26–28 weeks gestation) and reported breastfeeding practices from 3 weeks to ≥12 months. Regression and mediation analyses were adjusted for maternal age, parity, maternal education, ethnicity, pre-pregnancy BMI, and mode of delivery. Results: Morningness was significantly associated with a longer breastfeeding duration (β = 0.02, p = 0.037) and lower maternal anxiety symptoms (STAI-state: β = −0.19, p = 0.006 and STAI-trait: β = −0.18, p = 0.004). Lower maternal anxiety symptoms were significantly associated with a longer breastfeeding duration (STAI-state: β = −0.02, p = 0.003; STAI-trait: β = −0.02, p = 0.016). STAI-state, but not STAI-trait or EPDS, mediates the association between maternal chronotype and breastfeeding duration (βindirect = 0.004 (0.0004, 0.009)). Maternal mood did not mediate the association between maternal night sleep duration and breastfeeding duration. Conclusions: Maternal state-anxiety constitutes a behavioral pathway through which maternal chronotype influences breastfeeding duration. Strategies to target maternal anxiety in pregnant women with eveningness tendencies to promote breastfeeding duration are warranted.
- Open Access
- 19 October 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Usability and Acceptability of a Mobile Health Application to Support Infant Feeding and Lifestyle Behaviours: A Mixed-Methods Pilot Study (Preprint)
BACKGROUND Childhood obesity is a global health concern with long-term cardiometabolic and psychosocial consequences. Establishing healthy feeding and lifestyle behaviours from infancy is critical to population health efforts with a life course perspective. Recently, mobile health applications have gained traction in reaching out to parents and promoting healthy feeding behaviours. OBJECTIVE The aim of this study was to evaluate the usability and acceptability of the Feeding, Lifestyle, Activity Goals (FLAGs) application in providing parents with evidence-based guidance to promote healthier eating behaviors and lifestyle habits among infants. METHODS We conducted a mixed-methods pilot study among parents of infants aged 0–24 months recruited from a tertiary maternity and children’s hospital in Singapore. Participants used the mobile health application for seven days. Usability was assessed using the validated System Usability Scale (SUS; score range 0–100, with ≥70 indicating acceptable usability). Acceptability was explored via open-ended questionnaires on satisfaction, relevance, and user experience, with qualitative data analyzed thematically by two independent coders to ensure rigor. RESULTS Twenty-six parents completed the study. The application demonstrated good usability with a mean SUS score of 71.3 ±11.0. Parents valued its role in organizing infant care, promoting self-reflection on parenting practices, and providing personalized, evidence-based recommendations. These benefits were particularly appreciated by first-time parents and those with multiple caregiving responsibilities. Challenges included an unintuitive user interface, high manual data entry burden, and advisory content that was occasionally overly general or text-heavy. These insights highlight clear priorities for onward efforts in optimization. CONCLUSIONS Results of our mixed methods evaluation indicate that our mobile health application demonstrated good usability and acceptability among parents of infants. Targeted refinements to the interface, data entry processes, and content delivery are warranted before large-scale evaluation to determine its impact on early-life health behaviours and obesity prevention.
- 19 October 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUsability and Acceptability of a Mobile Health Application to Support Infant Feeding and Lifestyle Behaviours: A Mixed-Methods Pilot Study (Preprint)
BACKGROUND Childhood obesity is a global health concern with long-term cardiometabolic and psychosocial consequences. Establishing healthy feeding and lifestyle behaviours from infancy is critical to population health efforts with a life course perspective. Recently, mobile health applications have gained traction in reaching out to parents and promoting healthy feeding behaviours. OBJECTIVE The aim of this study was to evaluate the usability and acceptability of the Feeding, Lifestyle, Activity Goals (FLAGs) application in providing parents with evidence-based guidance to promote healthier eating behaviors and lifestyle habits among infants. METHODS We conducted a mixed-methods pilot study among parents of infants aged 0–24 months recruited from a tertiary maternity and children’s hospital in Singapore. Participants used the mobile health application for seven days. Usability was assessed using the validated System Usability Scale (SUS; score range 0–100, with ≥70 indicating acceptable usability). Acceptability was explored via open-ended questionnaires on satisfaction, relevance, and user experience, with qualitative data analyzed thematically by two independent coders to ensure rigor. RESULTS Twenty-six parents completed the study. The application demonstrated good usability with a mean SUS score of 71.3 ±11.0. Parents valued its role in organizing infant care, promoting self-reflection on parenting practices, and providing personalized, evidence-based recommendations. These benefits were particularly appreciated by first-time parents and those with multiple caregiving responsibilities. Challenges included an unintuitive user interface, high manual data entry burden, and advisory content that was occasionally overly general or text-heavy. These insights highlight clear priorities for onward efforts in optimization. CONCLUSIONS Results of our mixed methods evaluation indicate that our mobile health application demonstrated good usability and acceptability among parents of infants. Targeted refinements to the interface, data entry processes, and content delivery are warranted before large-scale evaluation to determine its impact on early-life health behaviours and obesity prevention.
- Open Access
Food Accessibility and Nutritional Outcomes Among Food-Insecure Pregnant Women in Singapore
Background/Objectives: Food insecurity during pregnancy is associated with higher risks of negative physical outcomes for both mother and child. This study aims to understand experiences of food insecurity among low-income Singaporean pregnant women and its impact on nutritional status. Methods: In this cross-sectional, mixed-methods study, 49 food-insecure pregnant women were recruited from KK Women’s and Children’s Hospital between November 2021 and November 2023, among which 11 in-depth interviews were conducted. Questionnaires, anthropometric measurements, 24-Hour dietary recalls, metabolic and nutritional blood tests were conducted for all subjects. Descriptive quantitative analysis was performed and integrated with qualitative thematic analysis to explain findings. Results: On average, women were overweight pre-pregnancy (body mass index 26.1 ± 6.9 kg/m2) and had low haemoglobin and 25-hydroxyvitamin D levels. Calorie intake and intake from major food groups did not meet recommendations during pregnancy, except for “Grains”. From interviews, effects of financial constraints, how participants managed their food supply and pregnancy-related symptoms, supported findings from 24-Hour dietary recalls. Conclusions: Food insecurity led to suboptimal nutritional status and diets in Singaporean pregnant women despite appearing well-nourished. Further exploration of perspectives of food-insecure mothers, healthcare providers and welfare organisations is needed to devise long-term solutions to improve food security and alleviate malnutrition.
Open AccessFood Accessibility and Nutritional Outcomes Among Food-Insecure Pregnant Women in Singapore
Background/Objectives: Food insecurity during pregnancy is associated with higher risks of negative physical outcomes for both mother and child. This study aims to understand experiences of food insecurity among low-income Singaporean pregnant women and its impact on nutritional status. Methods: In this cross-sectional, mixed-methods study, 49 food-insecure pregnant women were recruited from KK Women’s and Children’s Hospital between November 2021 and November 2023, among which 11 in-depth interviews were conducted. Questionnaires, anthropometric measurements, 24-Hour dietary recalls, metabolic and nutritional blood tests were conducted for all subjects. Descriptive quantitative analysis was performed and integrated with qualitative thematic analysis to explain findings. Results: On average, women were overweight pre-pregnancy (body mass index 26.1 ± 6.9 kg/m2) and had low haemoglobin and 25-hydroxyvitamin D levels. Calorie intake and intake from major food groups did not meet recommendations during pregnancy, except for “Grains”. From interviews, effects of financial constraints, how participants managed their food supply and pregnancy-related symptoms, supported findings from 24-Hour dietary recalls. Conclusions: Food insecurity led to suboptimal nutritional status and diets in Singaporean pregnant women despite appearing well-nourished. Further exploration of perspectives of food-insecure mothers, healthcare providers and welfare organisations is needed to devise long-term solutions to improve food security and alleviate malnutrition.
- Open Access
- 22 November 2024
- Published by JMIR Publications Inc. in JMIR Pediatrics and Parenting
- Vol. 7 (1) , e59564
Exploring the Use of a Length AI Algorithm to Estimate Children’s Length from Smartphone Images in a Real-World Setting: Algorithm Development and Usability Study
Background: Length measurement in young children younger than 18 months is important for monitoring growth and development. Accurate length measurement requires proper equipment, standardized methods, and trained personnel. In addition, length measurement requires young children’s cooperation, making it particularly challenging during infancy and toddlerhood. Objective: This study aimed to develop a length artificial intelligence (LAI) algorithm to aid users in determining recumbent length conveniently from smartphone images and explore its performance and suitability for personal and clinical use. Methods: This proof-of-concept study in healthy children (aged 0-18 months) was performed at KK Women’s and Children’s Hospital, Singapore, from November 2021 to March 2022. Smartphone images were taken by parents and investigators. Standardized length-board measurements were taken by trained investigators. Performance was evaluated by comparing the tool’s image-based length estimations with length-board measurements (bias [mean error, mean difference between measured and predicted length]; absolute error [magnitude of error]). Prediction performance was evaluated on an individual-image basis and participant-averaged basis. User experience was collected through questionnaires. Results: A total of 215 participants (median age 4.4, IQR 1.9-9.7 months) were included. The tool produced a length prediction for 99.4% (2211/2224) of photos analyzed. The mean absolute error was 2.47 cm for individual image predictions and 1.77 cm for participant-averaged predictions. Investigators and parents reported no difficulties in capturing the required photos for most participants (182/215, 84.7% participants and 144/200, 72% participants, respectively). Conclusions: The LAI algorithm is an accessible and novel way of estimating children’s length from smartphone images without the need for specialized equipment or trained personnel. The LAI algorithm’s current performance and ease of use suggest its potential for use by parents or caregivers with an accuracy approaching what is typically achieved in general clinics or community health settings. The results show that the algorithm is acceptable for use in a personal setting, serving as a proof of concept for use in clinical settings. Trial Registration: ClinicalTrials.gov NCT05079776; https://clinicaltrials.gov/ct2/show/NCT05079776
- 22 November 2024
- Published by JMIR Publications Inc. in JMIR Pediatrics and Parenting
- Vol. 7 (1) , e59564
Open AccessExploring the Use of a Length AI Algorithm to Estimate Children’s Length from Smartphone Images in a Real-World Setting: Algorithm Development and Usability Study
Background: Length measurement in young children younger than 18 months is important for monitoring growth and development. Accurate length measurement requires proper equipment, standardized methods, and trained personnel. In addition, length measurement requires young children’s cooperation, making it particularly challenging during infancy and toddlerhood. Objective: This study aimed to develop a length artificial intelligence (LAI) algorithm to aid users in determining recumbent length conveniently from smartphone images and explore its performance and suitability for personal and clinical use. Methods: This proof-of-concept study in healthy children (aged 0-18 months) was performed at KK Women’s and Children’s Hospital, Singapore, from November 2021 to March 2022. Smartphone images were taken by parents and investigators. Standardized length-board measurements were taken by trained investigators. Performance was evaluated by comparing the tool’s image-based length estimations with length-board measurements (bias [mean error, mean difference between measured and predicted length]; absolute error [magnitude of error]). Prediction performance was evaluated on an individual-image basis and participant-averaged basis. User experience was collected through questionnaires. Results: A total of 215 participants (median age 4.4, IQR 1.9-9.7 months) were included. The tool produced a length prediction for 99.4% (2211/2224) of photos analyzed. The mean absolute error was 2.47 cm for individual image predictions and 1.77 cm for participant-averaged predictions. Investigators and parents reported no difficulties in capturing the required photos for most participants (182/215, 84.7% participants and 144/200, 72% participants, respectively). Conclusions: The LAI algorithm is an accessible and novel way of estimating children’s length from smartphone images without the need for specialized equipment or trained personnel. The LAI algorithm’s current performance and ease of use suggest its potential for use by parents or caregivers with an accuracy approaching what is typically achieved in general clinics or community health settings. The results show that the algorithm is acceptable for use in a personal setting, serving as a proof of concept for use in clinical settings. Trial Registration: ClinicalTrials.gov NCT05079776; https://clinicaltrials.gov/ct2/show/NCT05079776
- Open Access
Breastfeeding Practices and Postpartum Weight Retention in an Asian Cohort
This study examines relationships between breastfeeding practices and postpartum weight retention (PPWR) at 6 and 12 months postpartum among 379 first-time mothers participating in a clinical trial in Singapore. We categorized feeding modes at 6 months into exclusive breastfeeding, mixed feeding, and exclusive formula feeding. Participants were analyzed in two groups based on their PPWR assessment at 6 and 12 months postpartum, with complete datasets available for each assessment. We calculated PPWR by subtracting pre-pregnancy weight from self-reported weight at 6 and 12 months postpartum, defining substantial PPWR as ≥5 kg retention. Modified Poisson regression models adjusted for potential confounders were performed. At 6 and 12 months, 35% (n = 132/379) and 31% (n = 109/347) of women experienced substantial PPWR, respectively. Compared to exclusive breastfeeding, mixed feeding (risk ratio 1.85; 95% confidence interval 1.15, 2.99) and exclusive formula feeding (2.11; 1.32, 3.28) were associated with a higher risk of substantial PPWR at 6 months. These associations were slightly attenuated at 12 months and appeared stronger in women with pre-pregnancy overweight or obesity. This study suggests that breastfeeding by 6 months postpartum may help mitigate PPWR, particularly with exclusive breastfeeding. It also draws attention to targeted interventions to promote breastfeeding among women with overweight or obesity.
Open AccessBreastfeeding Practices and Postpartum Weight Retention in an Asian Cohort
This study examines relationships between breastfeeding practices and postpartum weight retention (PPWR) at 6 and 12 months postpartum among 379 first-time mothers participating in a clinical trial in Singapore. We categorized feeding modes at 6 months into exclusive breastfeeding, mixed feeding, and exclusive formula feeding. Participants were analyzed in two groups based on their PPWR assessment at 6 and 12 months postpartum, with complete datasets available for each assessment. We calculated PPWR by subtracting pre-pregnancy weight from self-reported weight at 6 and 12 months postpartum, defining substantial PPWR as ≥5 kg retention. Modified Poisson regression models adjusted for potential confounders were performed. At 6 and 12 months, 35% (n = 132/379) and 31% (n = 109/347) of women experienced substantial PPWR, respectively. Compared to exclusive breastfeeding, mixed feeding (risk ratio 1.85; 95% confidence interval 1.15, 2.99) and exclusive formula feeding (2.11; 1.32, 3.28) were associated with a higher risk of substantial PPWR at 6 months. These associations were slightly attenuated at 12 months and appeared stronger in women with pre-pregnancy overweight or obesity. This study suggests that breastfeeding by 6 months postpartum may help mitigate PPWR, particularly with exclusive breastfeeding. It also draws attention to targeted interventions to promote breastfeeding among women with overweight or obesity.
- Open Access
- 21 June 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Exploring the Use of a Length AI Algorithm to Estimate Children’s Length from Smartphone Images in a Real-World Setting: Algorithm Development and Usability Study (Preprint)
BACKGROUND Length measurement in young children younger than 18 months is important for monitoring growth and development. Accurate length measurement requires proper equipment, standardized methods, and trained personnel. In addition, length measurement requires young children’s cooperation, making it particularly challenging during infancy and toddlerhood. OBJECTIVE This study aimed to develop a length artificial intelligence (LAI) algorithm to aid users in determining recumbent length conveniently from smartphone images and explore its performance and suitability for personal and clinical use. METHODS This proof-of-concept study in healthy children (aged 0-18 months) was performed at KK Women’s and Children’s Hospital, Singapore, from November 2021 to March 2022. Smartphone images were taken by parents and investigators. Standardized length-board measurements were taken by trained investigators. Performance was evaluated by comparing the tool’s image-based length estimations with length-board measurements (bias [mean error, mean difference between measured and predicted length]; absolute error [magnitude of error]). Prediction performance was evaluated on an individual-image basis and participant-averaged basis. User experience was collected through questionnaires. RESULTS A total of 215 participants (median age 4.4, IQR 1.9-9.7 months) were included. The tool produced a length prediction for 99.4% (2211/2224) of photos analyzed. The mean absolute error was 2.47 cm for individual image predictions and 1.77 cm for participant-averaged predictions. Investigators and parents reported no difficulties in capturing the required photos for most participants (182/215, 84.7% participants and 144/200, 72% participants, respectively). CONCLUSIONS The LAI algorithm is an accessible and novel way of estimating children’s length from smartphone images without the need for specialized equipment or trained personnel. The LAI algorithm’s current performance and ease of use suggest its potential for use by parents or caregivers with an accuracy approaching what is typically achieved in general clinics or community health settings. The results show that the algorithm is acceptable for use in a personal setting, serving as a proof of concept for use in clinical settings. CLINICALTRIAL ClinicalTrials.gov NCT05079776; https://clinicaltrials.gov/ct2/show/NCT05079776
- 21 June 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessExploring the Use of a Length AI Algorithm to Estimate Children’s Length from Smartphone Images in a Real-World Setting: Algorithm Development and Usability Study (Preprint)
BACKGROUND Length measurement in young children younger than 18 months is important for monitoring growth and development. Accurate length measurement requires proper equipment, standardized methods, and trained personnel. In addition, length measurement requires young children’s cooperation, making it particularly challenging during infancy and toddlerhood. OBJECTIVE This study aimed to develop a length artificial intelligence (LAI) algorithm to aid users in determining recumbent length conveniently from smartphone images and explore its performance and suitability for personal and clinical use. METHODS This proof-of-concept study in healthy children (aged 0-18 months) was performed at KK Women’s and Children’s Hospital, Singapore, from November 2021 to March 2022. Smartphone images were taken by parents and investigators. Standardized length-board measurements were taken by trained investigators. Performance was evaluated by comparing the tool’s image-based length estimations with length-board measurements (bias [mean error, mean difference between measured and predicted length]; absolute error [magnitude of error]). Prediction performance was evaluated on an individual-image basis and participant-averaged basis. User experience was collected through questionnaires. RESULTS A total of 215 participants (median age 4.4, IQR 1.9-9.7 months) were included. The tool produced a length prediction for 99.4% (2211/2224) of photos analyzed. The mean absolute error was 2.47 cm for individual image predictions and 1.77 cm for participant-averaged predictions. Investigators and parents reported no difficulties in capturing the required photos for most participants (182/215, 84.7% participants and 144/200, 72% participants, respectively). CONCLUSIONS The LAI algorithm is an accessible and novel way of estimating children’s length from smartphone images without the need for specialized equipment or trained personnel. The LAI algorithm’s current performance and ease of use suggest its potential for use by parents or caregivers with an accuracy approaching what is typically achieved in general clinics or community health settings. The results show that the algorithm is acceptable for use in a personal setting, serving as a proof of concept for use in clinical settings. CLINICALTRIAL ClinicalTrials.gov NCT05079776; https://clinicaltrials.gov/ct2/show/NCT05079776
- 1 February 2022
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 146, 219-227
Neonatal brain and physiological reactivity in preschoolers: An initial investigation in an Asian sample
- 1 February 2022
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 146, 219-227
Neonatal brain and physiological reactivity in preschoolers: An initial investigation in an Asian sample