pith. sign in

arxiv: 2504.15290 · v2 · submitted 2025-04-07 · 📊 stat.OT

Parental Imprints On Birth Weight: A Data-Driven Model For Neonatal Prediction In Low Resource Prenatal Care

Rajeshwari Mistri , Harsh Joshi , Nachiket Kapure , Parul Kumari , Manasi Mali , Seema Purohit , Neha Sharma , Mrityunjoy Panday
show 1 more author
Chittaranjan S. Yajnik
This is my paper

Pith reviewed 2026-05-22 21:25 UTC · model grok-4.3

classification 📊 stat.OT
keywords birth weight predictionmachine learningprenatal careparental factorslow resource settingsfeature selectionensemble learningfetal growth
0
0 comments X

The pith

Machine learning predicts fetal birth weight from parental and environmental factors without imaging tools.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper builds a machine learning framework that estimates birth weight using physiological, environmental, and parental data instead of ultrasound or other scans. A multi-stage feature selection step narrows the inputs to the most relevant predictors, after which regression and ensemble models capture the non-linear patterns that link those factors to fetal growth. The work directly tests whether reliable predictions are possible in places where conventional diagnostic equipment is scarce or unavailable. A reader would care because the approach could extend accurate prenatal monitoring to low-resource clinics and homes where current methods cannot reach.

Core claim

The central claim is that birth weight can be reliably estimated without conventional diagnostic tools using a data-driven machine learning framework based on parental imprints and other factors. The model filters inputs through a multi-stage feature selection pipeline, then applies advanced regression architectures and ensemble strategies to model the relationships, producing predictions that are both interpretable and scalable for settings lacking imaging access.

What carries the argument

A multi-stage feature selection pipeline that reduces the full dataset to an optimized subset of predictors, paired with ensemble learning to capture non-linear relationships among parental, physiological, and environmental variables.

If this is right

  • Prenatal care programs could collect simple questionnaire data on parental factors to generate birth weight estimates without equipment.
  • The identified predictors highlight clinical variables that traditional imaging methods may under-emphasize.
  • Ensemble models trained this way could be deployed on basic computing devices in remote clinics.
  • The framework provides an alternative pathway that maintains clinical utility while lowering infrastructure demands.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the selected features prove stable across populations, the same pipeline could be adapted to predict other neonatal outcomes such as Apgar scores or length of gestation.
  • Mobile health applications might incorporate the model to give expectant parents early risk signals based on routine check-up data.
  • The work invites direct comparison studies against ultrasound-based estimates in the same patient groups to quantify the accuracy trade-off.
  • Feature importance outputs from the ensembles could guide targeted public health interventions aimed at modifiable parental or environmental factors.

Load-bearing premise

The multi-stage feature selection pipeline identifies a subset of predictors that capture the relevant non-linear relationships and that these relationships generalize to new patients outside the training data.

What would settle it

A blind test on a fresh cohort of births in low-resource clinics, comparing model predictions against measured birth weights, would show whether accuracy drops when the data distribution differs from the training set.

Figures

Figures reproduced from arXiv: 2504.15290 by Chittaranjan S. Yajnik, Harsh Joshi, Manasi Mali, Mrityunjoy Panday, Nachiket Kapure, Neha Sharma, Parul Kumari, Rajeshwari Mistri, Seema Purohit.

Figure 1
Figure 1. Figure 1: Data Source [9] Phase 2 of the study focused solely on maternal characteristics, analyzing key health indicators such as anthropometric measurements, biochemical markers, and obstetric history to predict BW outcomes [9]. While this phase provided valuable insights, the absence of paternal accounts limits the scope of predictive modeling. Phase 3 expands upon this prior research by incorporating 5,979 featu… view at source ↗
Figure 2
Figure 2. Figure 2: Distribution of Features Exploratory Data Analysis (EDA) shows that approximately 70% of fetuses fall within the normal BW range (2,500–4,000 grams), while 29% are classified as moderately LBW 10 [PITH_FULL_IMAGE:figures/full_fig_p010_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: BW Classification on Basis of WHO Standards [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Feature Importance CatBoost [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: PDP Plot for Placental Weight [PITH_FULL_IMAGE:figures/full_fig_p014_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: PDP Plot for Paternal Platelet Count [PITH_FULL_IMAGE:figures/full_fig_p014_8.png] view at source ↗
Figure 10
Figure 10. Figure 10: Residual vs predicted scatter Plot for BART [PITH_FULL_IMAGE:figures/full_fig_p015_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Histogram and KDE Plot for BART Residuals [PITH_FULL_IMAGE:figures/full_fig_p015_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Residual vs. Predicted Values scatter plots for BART [PITH_FULL_IMAGE:figures/full_fig_p016_12.png] view at source ↗
read the original abstract

Accurate fetal birth weight prediction is a cornerstone of prenatal care, yet traditional methods often rely on imaging technologies that remain inaccessible in resource-limited settings. This study presents a novel machine learning-based framework that circumvents these conventional dependencies, using a diverse set of physiological, environmental, and parental factors to refine birth weight estimation. A multi-stage feature selection pipeline filters the dataset into an optimized subset, demonstrating previously underexplored yet clinically relevant predictors of fetal growth. By integrating advanced regression architectures and ensemble learning strategies, the model captures non-linear relationships often overlooked by traditional approaches, offering a predictive solution that is both interpretable and scalable. Beyond predictive accuracy, this study addresses a question: whether birth weight can be reliably estimated without conventional diagnostic tools. The findings challenge entrenched methodologies by introducing an alternative pathway that enhances accessibility without compromising clinical utility. While limitations exist, the study lays the foundation for a new era in prenatal analytics, one where data-driven inference competes with, and potentially redefines, established medical assessments. By bridging computational intelligence with obstetric science, this research establishes a framework for equitable, technology-driven advancements in maternal-fetal healthcare.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The manuscript proposes a machine learning framework for fetal birth weight prediction that relies on parental imprints, physiological, and environmental factors rather than imaging. It employs a multi-stage feature selection pipeline followed by advanced regression and ensemble methods to capture non-linear relationships, with the central claim that birth weight can be reliably estimated without conventional diagnostic tools in low-resource settings.

Significance. A validated, interpretable model that achieves clinically useful accuracy from non-imaging inputs could improve equitable access to prenatal risk stratification. The multi-stage selection and ensemble approach, if shown to generalize, would represent a practical contribution to applied statistical modeling in obstetrics.

major comments (3)
  1. [Abstract] Abstract: the assertions that the framework 'captures non-linear relationships often overlooked by traditional approaches' and 'challenges entrenched methodologies' are presented without any reported performance metrics (MAE, R², AUC), hold-out validation results, or direct comparisons against ultrasound-based baselines on unseen data.
  2. [Methods (feature selection description)] The multi-stage feature selection pipeline is described as identifying an 'optimized subset' of predictors, yet no cross-validation scheme, stability analysis across folds, or external-cohort performance is supplied to support the claim that the selected parental/environmental variables generalize beyond the training distribution.
  3. [Abstract and Results] The reliability assertion ('birth weight can be reliably estimated without conventional diagnostic tools') is load-bearing for the paper's contribution, but the manuscript supplies no quantitative evidence that the fitted model meets clinically relevant error thresholds on independent test data.
minor comments (2)
  1. [Methods] Notation for the ensemble components and the exact regression architectures is not defined; a table listing model hyperparameters and the final selected feature set would improve reproducibility.
  2. [Discussion] The abstract states that 'limitations exist' but does not enumerate them; a dedicated limitations paragraph should be added.

Simulated Author's Rebuttal

3 responses · 1 unresolved

We thank the referee for their constructive feedback. We address each major comment below, indicating where revisions have been made to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the assertions that the framework 'captures non-linear relationships often overlooked by traditional approaches' and 'challenges entrenched methodologies' are presented without any reported performance metrics (MAE, R², AUC), hold-out validation results, or direct comparisons against ultrasound-based baselines on unseen data.

    Authors: We agree that the abstract would be strengthened by including supporting metrics. The revised abstract now reports key hold-out validation results including MAE and R², along with a concise statement on performance relative to traditional approaches. Full metrics, validation details, and any available comparisons appear in the Results section. revision: yes

  2. Referee: [Methods (feature selection description)] The multi-stage feature selection pipeline is described as identifying an 'optimized subset' of predictors, yet no cross-validation scheme, stability analysis across folds, or external-cohort performance is supplied to support the claim that the selected parental/environmental variables generalize beyond the training distribution.

    Authors: Feature selection was performed within a cross-validated framework. The Methods section has been expanded to describe the cross-validation procedure and to report stability metrics across folds. External-cohort evaluation was not feasible given available data. revision: partial

  3. Referee: [Abstract and Results] The reliability assertion ('birth weight can be reliably estimated without conventional diagnostic tools') is load-bearing for the paper's contribution, but the manuscript supplies no quantitative evidence that the fitted model meets clinically relevant error thresholds on independent test data.

    Authors: Quantitative results on the independent test set, including error metrics relative to clinically relevant thresholds, have been added to the Results section. The abstract has been updated to reference these findings in support of the reliability claim. revision: yes

standing simulated objections not resolved
  • External-cohort validation, as no independent external cohorts were available for analysis.

Circularity Check

0 steps flagged

No circularity; empirical ML model with no derivations or self-referential reductions

full rationale

The paper describes a data-driven ML pipeline (multi-stage feature selection, regression architectures, ensemble learning) for birth weight prediction from parental/environmental factors. No equations, first-principles derivations, or parameter-free results are present. The central claim rests on fitted model performance rather than any step that reduces by construction to its own inputs. None of the six enumerated circularity patterns apply; the work is self-contained as an empirical study without load-bearing self-citations or ansatz smuggling.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim depends on the untested assumption that the chosen parental and environmental variables contain sufficient signal for accurate out-of-sample prediction and that the multi-stage selection process does not introduce selection bias.

axioms (1)
  • domain assumption Machine learning regression and ensemble models can capture clinically relevant non-linear relationships from the selected features.
    Invoked when the abstract states that the architectures 'capture non-linear relationships often overlooked by traditional approaches'.

pith-pipeline@v0.9.0 · 5773 in / 1021 out tokens · 107826 ms · 2026-05-22T21:25:16.412684+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

31 extracted references · 31 canonical work pages · 1 internal anchor

  1. [1]

    Maternal nutritional factors enhance birthweight prediction: A super learner ensemble approach,

    M. Mursil, H. A. Rashwan, P. Cavall´ e-Busquets, L. A. Santos-Calder´ on, M. M. Murphy, and D. Puig, “Maternal nutritional factors enhance birthweight prediction: A super learner ensemble approach,” Information, vol. 15, no. 11, 2024. [Online]. Available: https://www.mdpi.com/2078-2489/15/11/714

    work page 2024

  2. [2]

    Fetal birthweight prediction with measured data by a temporal machine learning method,

    J. Tao, Z. Yuan, L. Sun, K. Yu, and Z. Zhang, “Fetal birthweight prediction with measured data by a temporal machine learning method,” BMC Medical Informatics and Decision Making , vol. 21, no. 1, p. 26, 2021. [Online]. Available: https://doi.org/10.1186/s12911-021-01388-y

    work page doi:10.1186/s12911-021-01388-y 2021

  3. [3]

    Prediction of fetal weight at varying gestational age in the absence of ultrasound examination using ensemble learning,

    Y. Lu, X. Fu, F. Chen, and K. K. L. Wong, “Prediction of fetal weight at varying gestational age in the absence of ultrasound examination using ensemble learning,” Artificial Intelligence in Medicine , vol. 102, p. 101748, 2020. [Online]. Available: https://doi.org/10.1016/j.artmed.2019.101748

    work page doi:10.1016/j.artmed.2019.101748 2020

  4. [4]

    Prediction and feature selection of low birth weight using machine learning algorithms,

    T. B. Reza and N. Salma, “Prediction and feature selection of low birth weight using machine learning algorithms,” Journal of Health, Population and Nutrition , vol. 43, p. 157, 2024. [Online]. Available: https://doi.org/10.1186/s41043-024-00647-8

    work page doi:10.1186/s41043-024-00647-8 2024

  5. [5]

    Development and validation of a prognostic model to predict birth weight: individual participant data meta-analysis,

    J. Allotey, L. Archer, K. Snell, D. Coomar, J. Masse, L. Sletner, H. Wolf, G. Daskalakis, S. Saito, W. Ganzevoort, A. Ohkuchi, H. Mistry, D. Farrar, F. Mone, J. Zhang, P. Seed, H. Teede, F. Da Silva Costa, A. Souka, M. Smuk, S. Ferrazzani, S. Salvi, F. Pre- fumo, R. Gabbay-Benziv, C. Nagata, S. Takeda, E. Sequeira, O. Lapaire, J. Cecatti, R. Morris, A. Ba...

    work page 2024

  6. [6]

    Exploring the father’s role in determining neonatal birth weight: A narrative review,

    A. Libretti, F. Savasta, A. Nicosia, C. Corsini, A. D. Pedrini, L. Leo, A. S. Lagan` a, L. Tro` ıa, M. Dellino, R. Tinelli et al. , “Exploring the father’s role in determining neonatal birth weight: A narrative review,” Medicina, vol. 60, p. 1661, 2024. [Online]. Available: https://doi.org/10.3390/medicina60101661

    work page doi:10.3390/medicina60101661 2024

  7. [7]

    A new birthweight reference by gestational age: A population study based on the generalized additive model for location, scale, and shape method,

    Q. Wu, H.-Y. Zhang, L. Zhang, Y.-Q. Xu, J. Sun, N.-N. Gao, X.-Y. Qiao, and Y. Li, “A new birthweight reference by gestational age: A population study based on the generalized additive model for location, scale, and shape method,” Frontiers in Pediatrics , vol. 10, p. 810203, 2022. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/35386253/

    work page arXiv 2022

  8. [8]

    Handling missing data in longitudinal anthropometric data using multiple imputation method,

    D. Varma, C. S. Yajnik, A. Thorave, and N. Sharma, “Handling missing data in longitudinal anthropometric data using multiple imputation method,” Data Management, Analytics and Innovation , 2024. [Online]. Available: https: //easychair.org/publications/preprint/vbF7 19

    work page 2024

  9. [9]

    Predicting Fetal Birthweight from High Dimensional Data using Advanced Machine Learning

    N. Kapure, H. Joshi, R. Mistri, P. Kumari, M. Mali, S. Purohit, N. Sharma, M. Panday, and C. S. Yajnik, “Predicting fetal birthweight from high-dimensional data using advanced machine learning,” arXiv, 2025. [Online]. Available: https: //doi.org/10.48550/arXiv.2502.14270

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2502.14270 2025

  10. [10]

    Interpretable machine learning to identify important predictors of birth weight: A prospective cohort study,

    Z. Liu, N. Han, T. Su, Y. Ji, H. Bao, S. Zhou, S. Luo, H. Wang, J. Liu, and H.-J. Wang, “Interpretable machine learning to identify important predictors of birth weight: A prospective cohort study,” Frontiers in Pediatrics, vol. 10, p. 899954, 2022. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/36440327/

    work page arXiv 2022

  11. [11]

    Rural population - india,

    Macrotrends, “Rural population - india,” 2024, accessed: 2024-12-04. [On- line]. Available: https://www.macrotrends.net/global-metrics/countries/ind/india/ rural-population

    work page 2024

  12. [12]

    Maternal early pregnancy dietary glycemic index and load, fetal growth, and the risk of adverse birth outcomes,

    R. Wahab, J. Scholing, and R. Gaillard, “Maternal early pregnancy dietary glycemic index and load, fetal growth, and the risk of adverse birth outcomes,” European Journal of Nutrition , vol. 60, no. 3, pp. 1301–1311, 2021. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/32666314/

    work page arXiv 2021

  13. [13]

    Maternal dietary glycemic index and glycemic load in early pregnancy are associated with offspring adiposity in childhood: the southampton women’s survey,

    H. Okubo, S. Crozier, N. Harvey et al., “Maternal dietary glycemic index and glycemic load in early pregnancy are associated with offspring adiposity in childhood: the southampton women’s survey,” American Journal of Clinical Nutrition , vol. 100, no. 2, pp. 676–683, 2014. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/24944056/

    work page arXiv 2014

  14. [14]

    International tables of glycemic index and glycemic load values 2021: a systematic review,

    F. Atkinson, K. Foster-Powell, and J. Brand-Miller, “International tables of glycemic index and glycemic load values 2021: a systematic review,” American Journal of Clinical Nutrition , vol. 114, no. 5, pp. 1625–1632, 2021. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/34257626/

    work page arXiv 2021

  15. [15]

    Placental weight and its ratio to birth weight in normal pregnancy at songkhlanagarind hospital,

    M. Janthanaphan, O. Kor-Anantakul, and A. Geater, “Placental weight and its ratio to birth weight in normal pregnancy at songkhlanagarind hospital,” Journal of the Medical Association of Thailand, vol. 89, no. 2, pp. 130–137, 2006. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/16623040/

    work page arXiv 2006

  16. [16]

    Predicting birth weight at booking,

    E. Prior, S. Uthaya, and E. Harding, “Predicting birth weight at booking,” BMJ Medicine, vol. 3, p. e001018, 2024. [Online]. Available: https://bmjmedicine.bmj.com/ content/3/1/e001018

    work page 2024

  17. [17]

    Birth weight prediction models for the different gestational age stages in a chinese population,

    C. Li, Y. Peng, B. Zhang et al. , “Birth weight prediction models for the different gestational age stages in a chinese population,” Scientific Reports, vol. 9, p. 10834,

    work page

  18. [18]

    Available: https://www.nature.com/articles/s41598-019-47056-0

    [Online]. Available: https://www.nature.com/articles/s41598-019-47056-0

    work page

  19. [19]

    Competing-risks model for prediction of small-for-gestational-age neonate from estimated fetal weight at 19–24 weeks’ gestation,

    I. Papastefanou, U. Nowacka, A. Syngelaki, V. Dragoi, G. Karamanis, D. Wright, and K. Nicolaides, “Competing-risks model for prediction of small-for-gestational-age neonate from estimated fetal weight at 19–24 weeks’ gestation,” Ultrasound in Obstetrics & Gynecology , vol. 57, no. 6, pp. 917–924, 2021. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/...

    work page arXiv 2021

  20. [20]

    Establishment of the early prediction models of low-birth-weight reveals influential genetic and environmental factors: a prospective cohort study,

    S. Mizuno, S. Nagaie, G. Tamiya et al. , “Establishment of the early prediction models of low-birth-weight reveals influential genetic and environmental factors: a prospective cohort study,” BMC Pregnancy and Childbirth , vol. 23, p. 628, 2023. [Online]. Available: https://bmcpregnancychildbirth.biomedcentral.com/articles/10. 1186/s12884-023-05919-5

    work page 2023

  21. [21]

    Factors affecting clinical over and underestimation of fetal weight: A retrospective cohort,

    G. Cohen, H. Shalev-Ram, H. Schreiber et al. , “Factors affecting clinical over and underestimation of fetal weight: A retrospective cohort,” Journal of Clinical Medicine , vol. 11, no. 22, p. 6760, 2022. [Online]. Available: https://www.mdpi.com/2077-0383/11/22/6760

    work page 2022

  22. [22]

    Pre-conceptional maternal vitamin b12 supplementation improves offspring neurodevelopment at 2 years of age: Priya trial,

    N. D’souza, R. V. Behere, B. Patni, M. Deshpande, D. Bhat, A. Bhalerao, S. Sonawane, R. Shah, R. Ladkat, P. Yajnik, S. K. Bandyopadhyay, K. Kumaran, C. Fall, and C. S. Yajnik, “Pre-conceptional maternal vitamin b12 supplementation improves offspring neurodevelopment at 2 years of age: Priya trial,” Frontiers in Pediatrics, vol. 9, 2021. [Online]. Availabl...

    work page doi:10.3389/fped.2021.755977 2021

  23. [23]

    A study of k-nearest neighbour as an imputation method,

    G. E. Batista and M. C. Monard, “A study of k-nearest neighbour as an imputation method,” in Proceedings of the International Conference on Health Information Science , 2002. [Online]. Available: https://www.researchgate.net/ publication/220981745 A Study of K-Nearest Neighbour as an Imputation Method

    work page arXiv 2002

  24. [24]

    Multiple imputation by chained equations: what is it and how does it work?

    M. J. Azur, E. A. Stuart, C. Frangakis, and P. J. Leaf, “Multiple imputation by chained equations: what is it and how does it work?” International Journal of Methods in Psychiatric Research , vol. 20, no. 1, pp. 40–49, 2011. [Online]. Available: https://doi.org/10.1002/mpr.329

    work page doi:10.1002/mpr.329 2011

  25. [25]

    Feature selection approaches for newborn birthweight prediction in multiple linear regression models,

    E. Liu, P. X. Lin, Q. Wang, and K. C. Feng, “Feature selection approaches for newborn birthweight prediction in multiple linear regression models,” arXiv preprint arXiv:2411.11167, 2024. [Online]. Available: https://arxiv.org/abs/2411.11167

    work page arXiv 2024

  26. [26]

    Birthweight range prediction and classification: A machine learning-based sustainable approach,

    D. A. Alabbad, S. Y. Ajibi, R. B. Alotaibi, N. K. Alsqer, R. A. Alqahtani, N. M. Felemban, A. Rahman, S. S. Aljameel, M. I. B. Ahmed, and M. M. Youldash, “Birthweight range prediction and classification: A machine learning-based sustainable approach,” Machine Learning and Knowledge Extraction , vol. 6, no. 2, pp. 770–788,

    work page

  27. [27]

    Available: https://doi.org/10.3390/make6020036

    [Online]. Available: https://doi.org/10.3390/make6020036

    work page doi:10.3390/make6020036

  28. [28]

    Predictive models for small-for-gestational-age births in women exposed to pesticides before pregnancy based on multiple machine learning algorithms,

    X. Bai, Z. Zhou, M. Su, Y. Li, L. Yang, K. Liu, H. Yang, H. Zhu, S. Chen, and H. Pan, “Predictive models for small-for-gestational-age births in women exposed to pesticides before pregnancy based on multiple machine learning algorithms,” Frontiers in Public Health , vol. 10, p. 940182, 2022. [Online]. Available: https://doi.org/10.3389/fpubh.2022.940182

    work page doi:10.3389/fpubh.2022.940182 2022

  29. [29]

    Bayesian additive regression trees: A review and look forward,

    J. Hill, A. R. Linero, and J. S. Murray, “Bayesian additive regression trees: A review and look forward,” Annual Review of Statistics and Its Application , vol. 7, pp. 251–278,

    work page

  30. [30]

    Available: https://doi.org/10.1146/annurev-statistics-031219-041110 21

    [Online]. Available: https://doi.org/10.1146/annurev-statistics-031219-041110 21

    work page doi:10.1146/annurev-statistics-031219-041110

  31. [31]

    Association of placental parameters with low birth weight among neonates born in the public hospitals of hadiya zone, southern ethiopia: An institution-based cross-sectional study,

    S. M. Leyto and K. U. Mare, “Association of placental parameters with low birth weight among neonates born in the public hospitals of hadiya zone, southern ethiopia: An institution-based cross-sectional study,” International Journal of General Medicine , vol. 15, pp. 5005–5014, 2022. [Online]. Available: https://doi.org/10.2147/IJGM.S354909 22

    work page doi:10.2147/ijgm.s354909 2022