Skip to main content
Download PDF

Artificial intelligence applied to the study of human milk and breastfeeding: a scoping review

International Breastfeeding Journal volume 19, Article number: 79 (2024) Cite this article

Abstract

Background

Breastfeeding rates remain below the globally recommended levels, a situation associated with higher infant and neonatal mortality rates. The implementation of artificial intelligence (AI) could help improve and increase breastfeeding rates. This study aimed to identify and synthesize the current information on the use of AI in the analysis of human milk and breastfeeding.

Methods

A scoping review was conducted according to the PRISMA Extension for Scoping Reviews guidelines. The literature search, performed in December 2023, used predetermined keywords from the PubMed, Scopus, LILACS, and WoS databases. Observational and qualitative studies evaluating AI in the analysis of breastfeeding patterns and human milk composition have been conducted. A thematic analysis was employed to categorize and synthesize the data.

Results

Nineteen studies were included. The primary AI approaches were machine learning, neural networks, and chatbot development. The thematic analysis revealed five major categories: 1. Prediction of exclusive breastfeeding patterns: AI models, such as decision trees and machine learning algorithms, identify factors influencing breastfeeding practices, including maternal experience, hospital policies, and social determinants, highlighting actionable predictors for intervention. 2. Analysis of macronutrients in human milk: AI predicted fat, protein, and nutrient content with high accuracy, improving the operational efficiency of milk banks and nutritional assessments. 3. Education and support for breastfeeding mothers: AI-driven chatbots address breastfeeding concerns, debunked myths, and connect mothers to milk donation programs, demonstrating high engagement and satisfaction rates. 4. Detection and transmission of drugs in breast milk: AI techniques, including neural networks and predictive models, identified drug transfer rates and assessed pharmacological risks during lactation. 5. Identification of environmental contaminants in milk: AI models predict exposure to contaminants, such as polychlorinated biphenyls, based on maternal and environmental factors, aiding in risk assessment.

Conclusion

AI-based models have shown the potential to increase breastfeeding rates by identifying high-risk populations and providing tailored support. Additionally, AI has enabled a more precise analysis of human milk composition, drug transfer, and contaminant detection, offering significant insights into lactation science and maternal-infant health. These findings suggest that AI can promote breastfeeding, improve milk safety, and enhance infant nutrition.

Background

Although breastfeeding is a public health policy with various implemented actions, breastfeeding indicators remain below targets [1]. The prevalence of breastfeeding in children under six months of age in Latin America and the Caribbean is 43% [2]. In Colombia, the rate of exclusive breastfeeding in the first month of life is 50% [3]. By the first six months, this rate decreased to less than 30% [3]. It is associated with an increased risk of short- and long-term all-cause mortality and morbidities [4, 5]. Additionally, suboptimal breastfeeding during the neonatal period increases the risk of postnatal mortality by up to four-fold, especially in developing countries ​ [6, 7].

The World Health Organization’s (WHO) goal for 2025 is to increase the rate of exclusive breastfeeding during the first six months to at least 50%, a target that currently seems distant ​ [8]. This situation necessitates the exploration of new technological developments to improve the breastfeeding indicators.

Artificial intelligence (AI) has been one of the most impactful technological advances in recent years and has been applied in various fields of medicine [9]. AI is instrumental in diagnosing clinical conditions, developing drugs, and supporting medical services in remote areas [10, 11]​​. During the COVID-19 pandemic, AI is crucial for tracking and predicting events ​ [9]. In pediatrics, AI has been evaluated for its ability to diagnose sepsis and pulmonary hypertension and analyze brain images​ ​ [12,13,14,15,16]. AI has also been used to predict low birth weight and identify risk factors for maternal health, such as anemia and gestational diabetes [17,18,19]. Additionally, AI enables automatic analysis of growth curves, particularly weight-for-age curves, and is valuable for diagnosing newborn jaundice ​ [20, 21].

In this context, AI could be fundamental for improving breastfeeding indicators and for analyzing human milk. This scoping review aims to identify and present current information on the various uses and applications of AI in the study and analysis of human milk and breastfeeding patterns. Furthermore, this study evaluated the quality of the information in the selected articles and identified gaps and opportunities for new research focused on the application of AI in this field.

Methods

The scoping review followed the recommendations of the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) [22], aiming to identify, screen, and define the inclusion of relevant articles. The study protocol was registered on the Open Science Framework Platform (osf-registrations-r89f2-v1).

Identification of the literature

The literature search was conducted in December 2023 using electronic databases, including Medline, Scopus, LILACS (American and Caribbean Literature in Health Sciences), and Web of Science. A “snowball” search was also performed, identifying additional studies from the reference lists of publications eligible for full-text review. No language or year restrictions were applied.

The search terms included a combination of keywords, synonyms, and subject-indexing terms (MeSH and DeCS), to ensure a comprehensive search strategy. For example, the term ‘milk, human’ was searched alongside synonyms like ‘breast milk’ and ‘lactation fluid,’ while ‘breastfeeding’ included variations such as ‘nursing’ and ‘infant feeding.’ Additionally, terms related to artificial intelligence, like ‘machine learning’ and ‘deep learning,’ were included to capture a broad range of studies on AI applications in the context of human milk and breastfeeding. The following search strategy was used for PubMed and adapted to the other databases:(((((((((((Milk, Human) OR (Breast Feeding)) OR (Breast Milk Expression)) OR (Lactation)) OR (Colostrum)) OR (Milk Banks)) AND ((Artificial Intelligence) OR (Deep Learning)) OR (Machine Learning)).

Study eligibility criteria

Inclusion criteria

  • Studies of AI applications for the study of breastfeeding and/or analysis of human milk.

  • Description of technological tools, specifically those utilizing artificial intelligence (AI) such as machine learning algorithms, predictive models, and data mining techniques, to characterize the components of all types of human milk, including the mother’s own milk, donor human milk, and milk from human milk banks.

  • Use of AI in clinical, environmental, and laboratory settings to study the composition of human milk.

  • Clinical trial studies, observational studies, case reports, and qualitative studies

  • No restrictions were applied regarding the publication dates.

Exclusion criteria

  • Abstracts, conference abstracts, editors’ comments, reviews of scientific literature.

  • Animal studies.

Screening and inclusion of studies

Studies were blindly and independently identified and selected by the investigators (LRA, JEA, LRD, and SAP). Initially, duplicate records due to overlap between the consulted databases were detected using the Rayyan® web tool and were suppressed. Subsequently, the same tool was used to screen the titles and abstracts. Discrepancies in the initial screening were compared and resolved by consensus among the investigators. The full texts of relevant articles were independently retrieved for in-depth reading by the researchers to determine their final inclusion. Discrepancies were resolved through consensus.

Risk of bias and study quality

The risk of bias and quality of the observational studies were independently assessed by investigators. The CONSORT tool was used for clinical trials, STROBE checklist was used for observational studies, and CARE was used for case reports.

Data extraction and synthesis

The following information was extracted: (a) name of the journal, (b) author and year, (c) geographic area where the study was conducted, (d) information on the type and characteristics of the population, (d) application of AI, (f) technologies used, and (c) objectives and/or outcomes of the use of AI.

The information was organized into tables and diagrams based on the type of AI used, characteristics of the population studied, and objectives and outcomes of the use of AI. The information was synthesized according to the objectives of the study and the characteristics of the population.

Results

Initially, 1,231 articles were identified, and 180 duplicates were removed. After screening and in-depth review, 19 articles were included in the final analysis (Fig. 1). The main reasons for exclusion were studies with outcomes not directly related to the application of AI in the analysis of human milk consumption and breastfeeding. For instance, some studies have focused on general AI applications in other areas of healthcare rather than on breastfeeding, milk composition, or lactation-related outcomes. ‘Incorrect population’ refers to studies that did not focus on lactating mothers, infants, or populations directly involved in breastfeeding practices, such as studies targeting unrelated age groups or conditions not involving breastfeeding. Additionally, studies with unsuitable designs such as narrative reviews or opinion pieces that did not provide primary data were excluded.

Fig. 1
figure 1

Flow diagram of study selection

Full size image

Regarding the study methodologies, seven were observational studies, one was a case report, and the remaining studies focused on evaluating the development and integration of AI (Table 1).

Table 1 Description and characterization of included studies
Full size table

Risk of bias and quality of studies

Regarding the quality and risk of bias in observational studies, most had a low risk of bias. The main causes of bias were the sample size and generalizability of the results (Fig. 2a). In addition, a low risk of bias was identified in the case reports, with the main factors being the timeline and clinical findings (Fig. 2b).

Fig. 2
figure 2

Evaluation of the methodological quality of included studies. Assessment using the STROBE checklist. b Assessment using the CARE checklist

Full size image

Artificial intelligence

The articles were categorized into five groups: 1. prediction of breastfeeding practices (n = 5); 2. characterization of macronutrients in human milk (n = 3); 3. Education and resolution of doubts and problems regarding breastfeeding (n = 4); 4. Detection of drug concentration and passage in human milk (n = 4), and 5. Detection of environmental contaminants in human milk (N = 3). The most common AI approaches used were machine learning, neural networks, and chatbot development and application (Table 1).

Predicting breastfeeding practices

In a study by Oliver-Roig et al., machine learning techniques, including XGBoost and a linear support vector machine (SVM), were used to analyze data from 2,042 nursing mothers [23]. The model identified the main individual, clinical, and hospital environmental factors that predicted exclusive breastfeeding, including the mother’s previous experience, admission to the neonatal intensive care unit, and institutional accreditation in breastfeeding [23]. A study conducted by Silva et al. on 1,003 infants and using decision trees to determine factors associated with breastfeeding practices in the first six months revealed that maternal and child characteristics (multiple births, maternal age, and parity), social context, work, inpatient feeding practices, and hospital policies on breastfeeding influenced breastfeeding rates [24]. The length of hospital stay was the most important predictor of feeding practices, both at hospital discharge and at the third and sixth months [24]. Using a decision tree combination algorithm, this study offers a better understanding of the risk predictors of breastfeeding cessation in an environment with a high variability in exposure [24]. Sampieri et al. used machine learning techniques to assess the influence of skin-to-skin contact on breastfeeding [25]. Using selection algorithms generated by supervised learning, this study identified a direct relationship between skin-to-skin contact at birth, prenatal breastfeeding education, initiation and duration of breastfeeding, and mothers’ perceptions of breastfeeding after childbirth [25].

By using machine learning with logistic regression on imputed data, Elgersma et al. examined data from 1,944 newborns with complex single-ventricular congenital heart disease to identify the predictive factors related to breastfeeding and direct breastfeeding at the time of neonatal discharge and after palliative surgical correction [26]. They found that presurgical breastfeeding and private health insurance were associated with an increased likelihood of some types of breastfeeding after surgery [26]. On the other hand, being African American was associated with a decrease in this likelihood [26].

He et al. explored the benefits of applying common data-mining techniques to national breastfeeding surveys, where statistical analyses are common [27]. This study aimed to analyze the factors influencing the decision to breastfeed newborns using a decision tree and regression approach for classification based on selected features [27]. In addition, a risk pattern mining method was employed to identify groups at high risk of not breastfeeding. The results suggest that data mining in national surveys can identify mothers at greater risk of non-breastfeeding, which would allow their inclusion in early care and education programs to increase breastfeeding rates [27].

Characterization of macronutrients in human milk

Wong et al. developed a machine learning-based prediction model using donor mother variables, binomial characteristics, and the milk extraction process to estimate the fat and protein contents in collected mixtures of donated human milk [28]. They analyzed samples of human milk donated to a human milk bank in Canada, combining milk from two to five donors into a single bottle, and showed that the most important variables in the prediction of total fat were the body mass index of the donor, whether the neonate was preterm or full-term, and the time of day of milk production (night vs. day) [28]. In contrast, for protein prediction, the most significant variables were the average number of days postpartum, volume of milk expressed in the bank per day, and whether the neonate was preterm or full term [28]. The model was shown to be clinically acceptable for protein-level prediction, whereas fat prediction was more difficult owing to its natural variability and measurement challenges [28].

Jansen et al. proposed a model to optimize the experimental parameters for chromatographic separation of cholesterol esters in breast milk from three samples obtained from donor mothers [29]. Using an artificial neural network-genetic algorithm (ANNGA) approach, factors such as the type of organic component in the mobile phase, column temperature, and flow rate were optimized [29]. This method led to significant improvements in the separation parameters and quality of the chromatographic results, allowing better resolution of the identified analytes [29].

Ruan et al. compared two methods for determining the macronutrient composition in the breast milk of Chinese mothers at all stages of lactation using a mid-infrared analyzer and an ultrasound-based analyzer [30]. Through machine-learning techniques using linear regression algorithms, the ultrasound results were converted to align the results from both methods, making them comparable [30]. The initial compositional results obtained using the two analysis methods differed significantly for all compounds: protein, fat, lactose, and energy [30]. However, after adjusting the values using machine learning, the data exhibited improved consistency. This approach illustrates how AI techniques enhance the accuracy and consistency of breast milk composition measurements, which is clinically important for ensuring adequate nutrition in infants, especially preterm infants [30].

Education and resolution of doubts and problems regarding breastfeeding

Correa et al. described the design process of the Lhia chatbot, a virtual tool aimed at breastfeeding education and recruiting breastfeeding mothers to donate human milk to milk banks, using text and images from Telegram and WhatsApp [31]. They adopted a co-design approach with lactation professionals, who simulated texts from mothers with potential breastfeeding issues, which helped refine the AI-based chatbot [31]. Five deep-learning-based NLP systems were trained to classify the various intentions of user mothers [31]. Throughout the co-design process, improvements were made to the content and structure of the conversation flow based on the data gathered during subsequent training sessions [31]. The final system, with optimal performance and enhanced conversation flow, was implemented in a Lhia chatbot. This tool has demonstrated high accuracy in identifying specific issues related to breastfeeding and human milk donation [31].

Achtaich et al. developed ALMA, a chatbot designed to engage in natural conversations with breastfeeding mothers via WhatsApp, using the Twilio application programming interface (API) [32]. ALMA utilizes natural language understanding and generation to respond to breastfeeding-related needs and to provide relevant information. The chatbot was evaluated by volunteer breastfeeding mothers and the results were validated with lactation consultants [32].

In a related study, Oyedove et al. explored social networks as platforms for expressing both positive and negative opinions about breastfeeding, highlighting the opportunity to analyze these perspectives [33]. They proposed using AI to identify the factors affecting breastfeeding based on an analysis of tweets [33]. Tweets on this topic were collected and analyzed for sentiment using both lexicon-based and machine-learning techniques to classify them as positive or negative [33]. Four lexicon-based sentiment classifiers were evaluated: VADER, TextBlob, Pattern, and VADEREXT. Additionally, supervised machine learning algorithms—multinomial naïve Bayes (MNB), support vector machine (SVM), logistic regression (LR), stochastic gradient descent (SGD), and random forest (RF)— have been applied for text classification. Among these, SVM showed the best performance, whereas RF performed the least [33]. This study identified factors that negatively impact breastfeeding, such as health issues (breastfeeding-related, medical, and nutritional problems), as well as social, psychological, and situational factors [33]. Positive influences included perceived benefits, maternal self-efficacy, social support, and access to educational and training resources [33].

In India, Yadav et al. evaluated the impact of chatbots on breastfeeding among mothers living in slums [34]. Initially, they developed a question-and-answer prototype by analyzing interaction patterns, perceptions, and usage contexts. The results showed that most of the nursing mothers’ questions could be effectively answered using the app [34]. Additionally, the study highlighted that many of the queries made to the chatbot were influenced by beliefs and myths held by breastfeeding mothers and their families [34].

Detection of drug concentrations and transfer in human milk

Agatonovic-Kustrin et al. applied artificial neural networks to preestablished data on milk plasma concentrations and molecular structure characteristics of 123 drugs, aiming to identify factors that predict drug concentrations in human milk [35]. They used genetic algorithms to select the most relevant features describing drug transfer into breast milk, and subsequently applied an artificial neural network (ANN) to correlate these selected features with the milk/plasma ratio, developing a quantitative structure–activity relationship (QSAR) regression model [35]. This model includes nine features that predict the milk/plasma ratio of the studied drugs, considering characteristics such as molecular size, shape, and electronic properties, without requiring additional experimental data [35].

Maeshima et al. developed a prediction model for the ratio between drug concentration in breast milk and plasma concentration (M/PAUC) using the area under the curve (AUC) as a basis [36]. They also applied a quantitative structure–activity/property relationship (QSAR/QSPR) approach to predict the compounds involved in active transport during breast milk transfer [36]. Artificial intelligence (AI) tools were used to construct binary classification models, and data on the milk-to-plasma concentration ratio (M/P ratio) were collected from the existing literature [36]. Two binary classification models were developed: artificial neural network (ANN) and support vector machine (SVM). The sensitivity of the ANN model was 0.969 for the training set and 0.833 for the test set, whereas that of the SVM model was 0.971 for the training set and 0.667 for the test set [36]. These findings suggest that AI models can identify compounds with M/P ratios greater than or equal to 1 [36]. It is important to note that while these results are useful in risk assessment, alongside infants’ responses, they are not sufficient to determine the safety of breastfeeding during pharmacological treatment based solely on M/P ratio [36].

Zhao et al. developed computational models to predict and classify the milk-to-plasma concentration ratio (M/P ratio) of 123 pharmacological compounds that are commonly used by lactating mothers [37]. They employed the support vector machine (SVM) method to assess the potential risks of these drugs to infants. Each drug was included in the model with a range of characteristics to determine the best predictive model and ultimately identify five key factors for its construction [37]. Two classification models were developed: linear discriminant analysis (LDA) and SVM with bootstrap validation based on selected molecular descriptors [37]. The results showed that the classification accuracies of the SVM method were 90.63% for the training set and 90.00% for the test set [37]. The overall accuracy of SVM was 90.48%, which was significantly higher than that of LDA (77.78%) [37]. This comparison suggests that SVM performed better than LDA in classifying the risks associated with drugs when experimental M/P ratio data were unavailable [37]. Additionally, steric and electronic factors appear to be important components of the drug transfer process, along with other physical descriptors that influence the ability of drugs to transfer between breast milk and blood plasma [37].

On the other hand, Ye et al. developed a process that combined colorimetric methods with artificial intelligence image preprocessing and backpropagation artificial neural network (BP-ANN) analysis to detect amoxicillin in breast milk [38]. This technique involves the coupling of gold nanoparticles (AuNPs) with aptamers (ssDNA) at various amoxicillin concentrations, producing distinct color results [38]. An image of the color was captured using a portable image acquisition device, followed by image pre-processing [38]. These findings suggest that the colorimetric process, combined with AI-based image preprocessing and BP-ANN, provides an accurate and rapid method for detecting amoxicillin in breast milk [38].

Detection of environmental contaminants in human milk

Kowalski et al. collected human milk samples from 193 mothers across different regions of Brazil to identify patterns that could predict the presence of polychlorinated biphenyls (PCBs) in milk [39]. They used high-resolution omics and separation technologies to analyze compounds, considering mothers’ social, environmental, clinical, and lactational factors [39]. For the data analysis, non-automated learning techniques were applied to discover patterns and relationships, generating self-organizing maps using Kohonen neural networks [39]. The key variables predicting the presence of PCBs in breast milk included the mother’s region of residence, proximity to industrial areas or contaminated rivers, lactation phase (colostrum, early milk, or late lactation), and number of previous pregnancies [39].

In a related study, Nadal et al. used Kohonen neural networks to assess the relationship between the concentrations of polychlorinated dibenzo-p-dioxins (PCDDs) and polychlorinated dibenzofurans (PCDFs) in breast milk and dietary habits across various countries [40]. Their findings indicated higher concentrations of PCDDs/PCDFs in human milk in countries with high fish consumption [40].

Using machine learning methods and the Guided Regularized Random Forest (GRRF) algorithm, Jovanovic et al. aimed to identify persistent organic compounds such as organochlorine pesticides and polychlorinated biphenyls in human milk [41]. The study included samples from seventy-nine healthy mothers along with data on their social, environmental, and occupational backgrounds [41]. The levels of organic contaminants varied between the milks of primiparous and multiparous mothers [41]. The developed model demonstrated a high capacity to reliably predict contaminants in human milk based on selected variables [41]. The primary factor influencing the model’s predictions of contaminant concentrations was the chemical structure of each contaminant, particularly the number and position of the chlorine atoms [41].

Discussion

The findings of this scoping review demonstrate the growing interest in applying AI approaches to the analysis of breastfeeding and human milk, especially regarding variables associated with the prediction of exclusive breastfeeding, education of lactating mothers, and the analysis of components and contaminants in milk. The rapid advancement of AI research in other fields of medicine contrasts with the limited number of studies that have focused on its application in human milk and lactation.

The promotion of breastfeeding has emerged as a global priority, prompting numerous interventions to achieve this goal [42]. Despite global progress, breastfeeding indicators still fall short of their proposed targets [8]. The data from this scoping review underscores the potential of applying artificial intelligence to enhance the identification of factors and patterns that predict the initiation and maintenance of breastfeeding, offering a promising approach to improve these outcomes.

Traditionally, conventional statistical methods have identified key factors, such as early skin-to-skin contact, education of healthcare providers and mothers, early detection of breastfeeding challenges, and certain social determinants that contribute to improved breastfeeding rates [43,44,45,46]. However, AI-based approaches offer unique advantages and can complement the traditional data analysis methods. For example, efficient processing of large datasets, uncovering complex patterns, and enabling the integration of diverse data sources, such as clinical, genomic, and lifestyle information [47, 48]. This integration enriches existing analytical frameworks and provides deeper insights that are difficult to achieve using traditional methods alone. For instance, studies by He et al. [27] and Silva et al. [24], included in the scoping review, demonstrated that AI techniques, such as data mining, applied to national surveys can refine the identification of predictive factors for breastfeeding patterns and better understand the risk predictors of breastfeeding cessation in diverse environments.

Although AI can complement traditional methods, it is essential to recognize its limitations. The reliability of AI models depends on the quality of the training data, and non-representative datasets can introduce biases, potentially compromising care for marginalized groups [49, 50]. This is particularly critical for breastfeeding and infant nutrition, as disparities can have significant health impacts. Ensuring the selection of high-quality representative data and developing models that address biases are crucial for effective AI implementation.

Moreover, AI’s ability of AI to analyze large datasets can aid healthcare providers in developing tailored strategies for promoting breastfeeding and supporting exclusively breastfed infants. However, overreliance on AI recommendations could diminish the critical judgment and personal touch that are essential in the mother–child care relationship, especially in breastfeeding support [49, 50]. Thus, AI should serve as a complement to human expertise, not as a replacement, while preserving the personalized support that remains vital for successful breastfeeding outcomes.

The use of user-friendly interfaces such as mobile health (mHealth) technologies has demonstrated the ability to provide valuable information to patients, enhance their engagement, and enable timely medical responses [51]. These technologies have proven effective in delivering breastfeeding education within communities and have become key strategies for improving exclusive breastfeeding rates [51, 52]. This is particularly relevant in light of the findings from this study, which suggest that implementing artificial intelligence through chatbots offers a valuable tool for providing education, addressing breastfeeding-related questions, and fostering support networks for breastfeeding mothers. Such technological approaches can establish accessible communication channels, reduce delays in in-person care at primary care centers, and offer guidance to postpartum women and their families [53]. Furthermore, these platforms can increase awareness of breastfeeding and support informed decision making among mothers and expectant families.

However, the use of chatbots in patient management and community health applications requires a careful approach to ensure their safety and effectiveness. It is essential to safeguard the privacy and security of collected data by adhering to data protection regulations to prevent exposure to sensitive information. Transparency is the key to maintaining patient trust, as it allows users to understand that chatbots complement, rather than replace, in-person medical consultations. Additionally, educating patients about when to seek direct medical attention is crucial to avoid the potential misinterpretation of symptoms [47]. These precautions are vital for ensuring that chatbots are safe and effective tools for enhancing the quality of care without compromising user safety.

In addition, this scoping review highlights the potential of AI for analyzing drug concentrations, toxic compounds, and nutrients in human milk. By leveraging pre-established pharmacokinetic data and considering the chemical and structural properties of these substances, AI can accurately predict their presence in breast milk and their transfer to infants. This approach circumvents the ethical and clinical risks associated with direct research on lactating mothers and infants, and offers a safe and effective alternative based on pharmacokinetic and chemical data from the existing literature.

Traditional analytical methods, such as mass spectrometry and nuclear magnetic resonance (NMR), are essential for accuracy but often require significant time, financial investment, and the participation of large groups of patients and lactating mothers [54, 55]. These requirements limit the feasibility of routine monitoring and its rapid application in clinical settings [56, 57]. In contrast, AI-based approaches can streamline the analysis process by automating routine tasks and simplifying the interpretation of results. This not only accelerates the identification of toxic compounds and nutrients but also reduces operational costs, making it a more accessible option for healthcare providers [58, 59].

Furthermore, AI’s ability of AI to analyze large datasets allows for the systematic study of contaminants in breast milk across diverse populations, providing insights that are challenging to achieve through traditional methods. By offering a rapid, scalable, and cost-effective solution, AI holds significant promise for enhancing public health initiatives, supporting informed decision-making in clinical practice, and reducing disparities in access to safe breastfeeding practices [60].

Despite the numerous opportunities presented by the application of artificial intelligence (AI) in the study of human milk, several challenges and limitations persist. First, human milk is a complex and dynamic substance that varies between individuals and over time, posing a challenge to understanding and standardizing AI. Second, the lack of representative evidence limits the ability of algorithms to provide accurate results. Additionally, access to AI technologies requires significant investment of resources by research institutions, which could limit their use in resource-limited settings.

Conclusion

In conclusion, the use of artificial intelligence is experiencing promising growth and development in the analysis of breastfeeding patterns, education, and support, as well as in the analysis of the composition and contamination of human milk. The benefit of this technology in clinical practice is reflected in its rapid detection and resource optimization without the need for complex and time-consuming instruments. It is crucial to develop research that integrates AI workflows to analyze contaminants and nutrients at both laboratory and community levels.

Data availability

No datasets were generated or analysed during the current study.

Abbreviations

AI:

Artificial intelligence

ANN:

Artificial neural network

LR:

Logistic Regression

MNB:

Multinomial naïve Bayes

RF:

Random forest

SGD:

Stochastic gradient descent

SVM:

Support Vector Machine

WHO:

World Health Organization

References

  1. Neves PAR, Vaz JS, Maia FS, Baker P, Gatica-Domínguez G, Piwoz E, et al. Rates and time trends in the consumption of breastmilk, formula, and animal milk by children younger than 2 years from 2000 to 2019: analysis of 113 countries. Lancet Child Adolesc Health. 2021;5:619–30.

    Article  PubMed  PubMed Central  Google Scholar 

  2. OMS. Lactancia materna y alimentación complementaria - OPS/OMS | Organización Panamericana de la Salud. SALUD; 2020.

  3. Jiménez Soto AZ, Triana Reyes CA, Florez Nieto CE, Camargo Lemos DM, Cadena Gaona EM, Ardila Pinto FG. Documento general de análisis Encuesta Nacional de la Situación Nutricional en Colombia - ENSIN 2015 [General Analysis Document of the National Survey of Nutritional Situation in Colombia - ENSIN 2015]. Bogotá; 2019.

  4. Edmond K, Newton S, Hurt L, Shannon CS, Kirkwood BR, Mazumder S, et al. Timing of initiation, patterns of breastfeeding, and infant survival: Prospective analysis of pooled data from three randomised trials. Lancet Glob Health. 2016;4:e266–75.

    Article  Google Scholar 

  5. Victora CG, Bahl R, Barros AJD, França GVA, Horton S, Krasevec J, et al. Breastfeeding in the 21st century: epidemiology, mechanisms, and lifelong effect. Lancet. 2016;387:475–90.

    Article  PubMed  Google Scholar 

  6. Upadhyay RP, Martines JC, Taneja S, Mazumder S, Bahl R, Bhandari N, et al. Risk of postneonatal mortality, hospitalisation and suboptimal breast feeding practices in low birthweight infants from rural Haryana, India: findings from a secondary data analysis. BMJ Open. 2018;8:e020384.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Raihana S, Dibley MJ, Rahman MM, Tahsina T, Siddique MAB, Rahman QS, et al. Early initiation of breastfeeding and severe illness in the early newborn period: An observational study in rural Bangladesh. PLoS Med. 2019;16:e1002904.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Global breastfeeding scorecard 2023 rates of breastfeeding increase around the world through improved protection and support. 2023.

  9. Basu K, Sinha R, Ong A, Basu T. Artificial intelligence: How is it changing medical sciences and its future? Indian J Dermatol. 2020;65:365.

    Article  PubMed  PubMed Central  Google Scholar 

  10. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–8.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Amisha, Malik P, Pathania M, Rathaur VK. Overview of artificial intelligence in medicine. J Family Med Prim Care. 2019;8:2328.

  12. Patel SJ, Chamberlain DB, Chamberlain JM. A machine learning approach to predicting need for hospitalization for pediatric asthma exacerbation at the time of emergency department triage. Acad Emerg Med. 2018;25:1463–70.

    Article  PubMed  Google Scholar 

  13. Li YW, Liu F, Zhang TN, Xu F, Gao YC, Wu T. Artificial intelligence in pediatrics. Chin Med J (Engl). 2020;133:358.

    Article  PubMed  Google Scholar 

  14. Gomberg-Maitland M, Souza R. Uncovering small secrets in big data sets: How math can identify biology in rare conditions (pediatric pulmonary hypertension). Circ Res. 2017;121:317–9.

    Article  CAS  PubMed  Google Scholar 

  15. Hazlett HC, Gu H, Munsell BC, Kim SH, Styner M, Wolff JJ, et al. Early brain development in infants at high risk for autism spectrum disorder. Nature. 2017;542:348–51.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Kamaleswaran R, Akbilgic O, Hallman MA, West AN, Davis RL, Shah SH. Applying artificial intelligence to identify physiomarkers predicting severe sepsis in the PICU. Pediatr Crit Care Med. 2018;19:E495-503.

    Article  PubMed  Google Scholar 

  17. Assaduzzaman M, Al MA, Hasan MZ, Early prediction of maternal health risk factors using machine learning techniques. In,. International Conference for Advancement in Technology (ICONAT). IEEE. 2023;2023:4659–66.

    Google Scholar 

  18. Khan M, Khurshid M, Vatsa M, Singh R, Duggal M, Singh K. On AI approaches for promoting maternal and neonatal health in low resource settings: A Review. Front Public Health. 2022;30:880034.

    Article  Google Scholar 

  19. Patil SV, Gupta YH. Nutrition detection during gestation period using ML algorithms. Int J Latest Res Eng Manag. 2023;7:01–6.

    Google Scholar 

  20. Nel S, Feucht UD, Nel AL, Becker PJ, Wenhold FAM. A novel screening tool to predict severe acute malnutrition through automated monitoring of weight-for-age growth curves. Matern Child Nutr. 2022;18:e13364.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Hao S, Geng S, Fan L, Chen J, Zhang Q, Li L. Intelligent diagnosis of jaundice with dynamic uncertain causality graph model. J Zhejiang Univ Sci B. 2017;18:393–401.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Tricco AC, Lillie E, Zarin W, O’Brien KK, Colquhoun H, Levac D, et al. PRISMA extension for scoping reviews (PRISMA-ScR): Checklist and Explanation. Ann Intern Med. 2018;169:467–73.

    Article  PubMed  Google Scholar 

  23. Oliver-Roig A, Rico-Juan JR, Richart-Martínez M, Cabrero-García J. Predicting exclusive breastfeeding in maternity wards using machine learning techniques. Comput Methods Programs Biomed. 2022;221:106837.

    Article  PubMed  Google Scholar 

  24. Silva MD, de Oliveira RD, da Silveira Barroso Alves D, Melo EC. Predicting risk of early discontinuation of exclusive breastfeeding at a Brazilian referral hospital for high-risk neonates and infants: a decision-tree analysis. Int Breastfeed J. 2021;16:2.

  25. Sampieri CL, Fragoso KG, Córdoba-Suárez D, Zenteno-Cuevas R, Montero H. Influence of skin-to-skin contact on breastfeeding: Results of the mexican national survey of demographic dynamics, 2018. Int Breastfeed J. 2022;17:49.

    Article  PubMed  PubMed Central  Google Scholar 

  26. Elgersma KM, Wolfson J, Fulkerson JA, Georgieff MK, Looman WS, Spatz DL, et al. Predictors of human milk feeding and direct breastfeeding for infants with single ventricle congenital heart disease: Machine learning analysis of the national pediatric cardiology quality improvement collaborative registry. J Pediatr. 2023;261:113562.

    Article  PubMed  PubMed Central  Google Scholar 

  27. He H, Jin H, Chen J, Mcaullay D, Li J, Fallon T. Analysis of breast feeding data using data mining methods. In: Proceedings of the Fifth Australasian Data Mining Conference. Sydney; 2006. p. 123–30.

  28. Wong RK, Pitino MA, Mahmood R, Zhu IY, Stone D, O’Connor DL, et al. Predicting protein and fat content in human donor milk using machine learning. J Nutr. 2021;151:2075–83.

    Article  PubMed  Google Scholar 

  29. Jansen MA, Kiwata J, Arceo J, Faull KF, Hanrahan G, Porter E. Evolving neural network optimization of cholesteryl ester separation by reversed-phase HPLC. Anal Bioanal Chem. 2010;397:2367–74.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Ruan H, Tang Q, Zhang Y, Zhao X, Xiang Y, Feng Y, et al. Comparing human milk macronutrients measured using analyzers based on mid-infrared spectroscopy and ultrasound and the application of machine learning in data fitting. BMC Pregnancy Childbirth. 2022;22:562.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  31. Corrêa JS, Neto AP, Pinto GR, Lima LD, Teles AS. Lhia: A smart chatbot for breastfeeding education and recruitment of human milk donors. Appl Sci. 2023;13:6923.

    Article  Google Scholar 

  32. Achtaich K, Achtaich N, Fagroud FZ, Toumi H. ALMA: Machine learning breastfeeding chatbot. Math Model Comput. 2023;10:487–97.

    Article  Google Scholar 

  33. Oyebode O, Lomotey R, Orji R. “I tried to breastfeed but...”: Exploring factors influencing breastfeeding behaviours based on tweets using machine learning and thematic analysis. IEEE Access. 2021;9:61074–89.

    Article  Google Scholar 

  34. Yadav D, Malik P, Dabas K, Singh P. Feedpal: Understanding opportunities for chatbots in breastfeeding education of women in India. Proc ACM Hum Comput Interact. 2019;3:1–30.

    Google Scholar 

  35. Agatonovic-Kustrin S, Ling LH, Tham SY, Alany RG. Molecular descriptors that influence the amount of drugs transfer into human breast milk. J Pharm Biomed Anal. 2002;29:103–19.

    Article  CAS  PubMed  Google Scholar 

  36. Maeshima T, Yoshida S, Watanabe M, Itagaki F. Prediction model for milk transfer of drugs by primarily evaluating the area under the curve using QSAR/QSPR. Pharm Res. 2023;40:711–9.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Zhao C, Zhang H, Zhang X, Zhang R, Luan F, Liu M, et al. Prediction of milk/plasma drug concentration (M/P) ratio using support vector machine (SVM) method. Pharm Res. 2006;23:41–8.

    Article  CAS  PubMed  Google Scholar 

  38. Ye Z, Du J, Li K, Zhang Z, Xiao P, Yan T, et al. Coupled gold nanoparticles with aptamers colorimetry for detection of amoxicillin in human breast milk based on image preprocessing and BP-ANN. Foods. 2022;11:4101.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  39. Kowalski CH, Da Silva GA, Godoy HT, Poppi RJ, Augusto F. Application of Kohonen neural network for evaluation of the contamination of Brazilian breast milk with polychlorinated biphenyls. Talanta. 2013;116:315–21.

    Article  CAS  PubMed  Google Scholar 

  40. Nadal M, Espinosa G, Schuhmacher M, Domingo JL. Patterns of PCDDs and PCDFs in human milk and food and their characterization by artificial neural networks. Chemosphere. 2004;54:1375–82.

    Article  CAS  PubMed  Google Scholar 

  41. Jovanović G, Romanić SH, Stojić A, Klinčić D, Sarić MM, Letinić JG, et al. Introducing of modeling techniques in the research of POPs in breast milk – A pilot study. Ecotoxicol Environ Saf. 2019;172:341–7.

    Article  PubMed  Google Scholar 

  42. Hansen K. Breastfeeding: a smart investment in people and in economies. Lancet. 2016;387(10017):416.

    Article  PubMed  Google Scholar 

  43. Cohen SS, Alexander DD, Krebs NF, Young BE, Cabana MD, Erdmann P, et al. Factors associated with breastfeeding initiation and continuation: A Meta-Analysis. J Pediatr. 2018;203:190-196.e21.

    Article  PubMed  Google Scholar 

  44. Martínez-Vázquez S, Hernández-Martínez A, Rodríguez-Almagro J, Peinado-Molina RA, Martínez-Galiano JM. Determinants and factors associated with the maintenance of exclusive breastfeeding after hospital discharge after birth. Healthcare (Basel). 2022;14;10(4):733.

  45. Brown CRL, Dodds L, Legge A, Bryanton J, Semenic S. Factors influencing the reasons why mothers stop breastfeeding. Can J Public Health. 2014;105:e179–85.

    Article  PubMed  PubMed Central  Google Scholar 

  46. Moore ER, Bergman N, Anderson GC, Medley N. Early skin-to-skin contact for mothers and their healthy newborn infants. Cochrane Database Syst Rev. 2016;11:CD003519.

  47. Robinson R, Liday C, Lee S, Williams IC, Wright M, An S, et al. Artificial intelligence in health care—understanding patient information needs and designing comprehensible transparency: Qualitative study. JMIR AI. 2023;2:e46487.

    Article  PubMed  PubMed Central  Google Scholar 

  48. Nomura A, Noguchi M, Kometani M, Furukawa K, Yoneda T. Artificial intelligence in current diabetes management and prediction. Curr Diab Rep. 2021;21:61.

    Article  PubMed  PubMed Central  Google Scholar 

  49. Shuaib A. Transforming healthcare with AI: Promises, pitfalls, and pathways forward. Int J Gen Med. 2024;17:1765–71.

    Article  PubMed  PubMed Central  Google Scholar 

  50. Upadhyay U, Gradisek A, Iqbal U, Dhar E, Li Y-C, Syed-Abdul S. Call for the responsible artificial intelligence in the healthcare. BMJ Health Care Inform. 2023;30:e100920.

    Article  PubMed  PubMed Central  Google Scholar 

  51. Pitts A, Faucher MA, Spencer R. Incorporating breastfeeding education into prenatal care. Breastfeed Med. 2015;10:118–23.

    Article  PubMed  Google Scholar 

  52. Chen H, Chai Y, Dong L, Niu W, Zhang P. Effectiveness and appropriateness of mHealth interventions for maternal and child health: Systematic review. JMIR Mhealth Uhealth. 2018;6:e7.

    Article  PubMed  PubMed Central  Google Scholar 

  53. dos Santos JB, Junior, Dias L, Figueiredo L, de Brito LF, Coutinho, et al. Uma proposta de ChatBot para tele orientação sobre aleitamento materno [A ChatBot Proposal for Tele Orientation on Breastfeeding]. Revista Ibérica de Sistemas e Tecnologias de Informação. 2021:367–73.

  54. Bardanzellu F, Fanos V, Reali A. “Omics” in human colostrum and mature milk: Looking to old data with new eyes. Nutrients. 2017;9:843.

    Article  PubMed  PubMed Central  Google Scholar 

  55. Serreau R, Terbeche Y, Rigourd V. Pollutants in breast milk: A scoping review of the most recent data in 2024. Healthcare. 2024;12:680.

    Article  PubMed  PubMed Central  Google Scholar 

  56. Qi S-Y, Xu X-L, Ma W-Z, Deng S-L, Lian Z-X, Yu K. Effects of organochlorine pesticide residues in maternal body on infants. Front Endocrinol (Lausanne). 2022;13:890307.

    Article  PubMed  Google Scholar 

  57. Benkerroum N, Ismail A. Human breast milk contamination with aflatoxins, impact on children’s health, and possible control means: A review. Int J Environ Res Public Health. 2022;19:16792.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  58. Al Kuwaiti A, Nazer K, Al-Reedy A, Al-Shehri S, Al-Muhanna A, Subbarayalu AV, et al. A review of the role of artificial intelligence in healthcare. J Pers Med. 2023;13:951.

    Article  PubMed  PubMed Central  Google Scholar 

  59. Isha Mishra, Vedika Kashyap, Dr. Ritu Pahwa, Dr. R. Dheivanai. Revolutionizing healthcare: The impact and growth of artificial intelligence(AI). Int Res J Adv Eng Hub. 2024;2:1875–81.

  60. Amiri P, Karahanna E. Chatbot use cases in the Covid-19 public health response. J Am Med Inform Assoc. 2022;29:1000–10.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

This work was supported by the Universidad de La Sabana (grant number: MED-6–2024).

Author information

Authors and Affiliations

  1. Department of Pediatrics, School of Medicine, Universidad de La Sabana, Chía, Cundinamarca, Colombia

    Sergio Agudelo-Pérez, Daniel Botero-Rosas, Laura Rodríguez-Alvarado, Julián Espitia-Angel & Lina Raigoso-Díaz

Authors
  1. Sergio Agudelo-Pérez
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Daniel Botero-Rosas
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Laura Rodríguez-Alvarado
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Julián Espitia-Angel
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Lina Raigoso-Díaz
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

SAP and DBR conceived and designed the study. SAP, LRA, JEA and LRD carried out the study selection and data extraction. SAP, DBR, LRA, JEA and LRD supported the analysis and writing of the draft manuscript. SAP, DBR, LRA, JEA and LRD reviewed the manuscript. All the authors have read and approved the final manuscript.

Corresponding author

Correspondence to Sergio Agudelo-Pérez.

Ethics declarations

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Agudelo-Pérez, S., Botero-Rosas, D., Rodríguez-Alvarado, L. et al. Artificial intelligence applied to the study of human milk and breastfeeding: a scoping review. Int Breastfeed J 19, 79 (2024). https://doiorg.publicaciones.saludcastillayleon.es/10.1186/s13006-024-00686-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doiorg.publicaciones.saludcastillayleon.es/10.1186/s13006-024-00686-1

Keywords

International Breastfeeding Journal

ISSN: 1746-4358