Search Results (89)

Infant cries serve as a primary indicator of distress and pain; however, distinguishing pain-related cries from those triggered by other needs remains a challenging task, even for trained professionals. Timely and accurate pain assessment is essential for appropriate medical intervention, particularly in preverbal infants who cannot express their needs verbally. Recently, Deep Learning (DL) models have demonstrated significant potential in addressing this challenge by enabling automated and efficient pain assessment through audio signal processing. In this survey, we review methods for pain assessment from infant cry sounds, covering deep learning architectures, modern Transformer-based models, and emerging Vision-Language Model (VLM) pipelines. The review includes approaches that integrate Mel-spectrogram representations of cry audio with multimodal model frameworks to improve robustness, interpretability, and cross-modal reasoning in pain detection. By summarizing recent advancements and identifying limitations and open challenges in current methodologies, this review aims to provide insights into future research directions that may enhance the robustness, generalizability, and clinical applicability of automated infant pain assessment tools. Full article

Respiratory distress syndrome (RDS) is one of the most serious neonatal conditions, frequently leading to respiratory failure and death in low-resource settings. Early detection is therefore critical, particularly where access to advanced diagnostic tools is limited. Recent advances in machine learning have enabled non-invasive neonatal cry diagnostic systems (NCDSs) for early screening. To the best of our knowledge, this is the first cry-based RDS detection study to include both preterm and full-term infants in a subject-balanced design, using 76 neonates (38 RDS, 38 healthy; 19 per subgroup) and 8534 expiratory cry segments (4267 per class). Cry waveforms were converted to mono, high-pass-filtered, and segmented to isolate expiratory units. Mel-Frequency Cepstral Coefficients (MFCCs) and Filterbank (FBANK) features were extracted and transformed into fixed-dimensional embeddings using a lightweight X-vector model with mean-SDor attention-based pooling, followed by a binary classifier. Model parameters were optimized via grid search. Performance was evaluated using accuracy, precision, recall, F1-score, and ROC–AUC under stratified 10-fold cross-validation. MFCC + mean–SD achieved 93.59 ± 0.48% accuracy, while MFCC + attention reached 93.53 ± 0.52% accuracy with slightly higher precision, reducing false RDS alarms and improving clinical reliability. To enhance interpretability, Integrated Gradients were applied to MFCC and FBANK features to reveal the spectral regions contributing most to the decision. Overall, the proposed NCDS reliably distinguishes RDS from healthy cries and generalizes across neonatal subgroups despite the greater variability in preterm vocalizations. Full article

Background/Objectives: Worldwide, an estimated 20–30% of infants suffer from infant colic (IC), with excessive crying and unsettled behavior, during the first three months of life. These infants are often referred for a medical evaluation, but the pathogenesis of IC remains poorly understood. The aim of this narrative review is to critically appraise the available literature regarding the relation between IC and cow’s milk allergy (CMA). Methods: A literature search using the search strings cow’s milk allergy [MeSH Terms] OR food allergy [MesH Terms] AND colic [MeSH Terms] OR crying [MeSH Terms], limited to the English language, from inception to 15 June 2025, resulted in the identification of 135 articles. Of these, 18 clinical trials assessed the effect of a cow’s milk elimination diet on IC. Results: The role of CMA in IC in the absence of other allergic manifestations remains uncertain. However, when standard treatment of infant colic has failed and when other allergic symptoms are present, CMA may be considered. A diagnostic elimination diet which includes a 2–4-week trial of maternal cow’s milk elimination in breastfed infants or an extensively hydrolyzed cow’s milk or hydrolyzed rice formula should be performed. If the elimination diet results in a significant decrease in symptoms, reintroduction of cow’s milk protein into the diet is mandatory to fulfill the diagnostic criteria of CMA. Conclusions: Considering the limited current evidence, future research should prioritize large well-designed clinical trials with a focus on investigating CMA in colicky breastfed and formula-fed infants. Full article

Background: Infantile colic affects up to 40% of otherwise healthy infants and can severely distress caregivers. Manual therapies are increasingly employed as non-pharmacological options, yet their effectiveness and safety remain uncertain. Methods: A scoping review was conducted in accordance with Joanna Briggs Institute methodology and reported following PRISMA-ScR. Five databases (MEDLINE, CENTRAL, Scopus, PEDro, Web of Science) were searched from December 2024 to May 2025 without restrictions at the search stage; however, only English-language randomised controlled trials published from 2012 onwards were included at the eligibility stage to ensure consistency and focus on the most recent body of evidence. Randomised controlled trials (RCTs) evaluating hands-on interventions for infants ≤ 6 months with colic were eligible. Two reviewers independently screened records, charted data, and grouped outcomes narratively. Results: Seven RCTs investigated abdominal massage, paediatric Tuina, craniosacral therapy, chiropractic manipulation, osteopathic light touch, reflexology, and acupressure. Five trials reported statistically or clinically significant reductions in daily crying (0.6–6.6 h) compared with usual care or sham. Three studies also documented meaningful gains in sleep duration (1.1–2.8 h). Parent-reported satisfaction improved in most interventions. No serious adverse events were recorded, although safety monitoring was inconsistently reported. Substantial heterogeneity in diagnostic criteria, outcome measures, and intervention dose precluded meta-analysis. Conclusions: Low-force manual therapies may offer modest short-term relief for colicky infants and improve parental experience, with an apparently favourable safety profile. However, methodological variability and small sample sizes limit certainty. Standardised protocols, objective outcome measures, and robust adverse-event surveillance are priorities for future research. Full article

Background: Shaken Baby Syndrome (SBS) is a severe form of abusive head trauma with potentially fatal consequences. Nurses and midwives play a crucial role in its prevention through early recognition and caregiver education; however, little is known about their knowledge and preparedness in the Polish context. Objectives: To assess the knowledge, perceptions, and educational experiences related to SBS among Polish nurses and midwives working with infants. Participants and Setting: A nationwide cross-sectional survey was conducted among 110 nurses and midwives employed in neonatal and pediatric care settings across Poland. Methods: An anonymous questionnaire collected demographic data and evaluated knowledge of SBS, infant crying, coping strategies, and prior training. Associations between knowledge levels and participant characteristics were analyzed using the Mann-Whitney U and Kruskal-Wallis tests. Results: Most participants (94.5%) had heard of SBS, and 78.2% correctly recognized shaking as more dangerous than a fall from a changing table. However, only 5.5% reported receiving formal training on SBS. Recognition of SBS symptoms was generally high (e.g., vomiting 100%, seizures 90.9%), but misconceptions persisted regarding coping with infant crying. More than one-quarter (27.3%) admitted experiencing a “breaking point,” and this group was more likely to acknowledge the risk of losing emotional control. Older nurses demonstrated significantly better recognition of crying patterns and colic (p = 0.0415), while SBS knowledge was positively associated with years of professional experience (p = 0.0484). Conclusions: Although general awareness of SBS is widespread, practical knowledge and training remain insufficient. Structured educational programs on SBS and infant crying management are urgently needed to better prepare healthcare professionals and reduce the risk of caregiver-related harm to infants. Full article

Background/Objectives: We examined maternal perceptions of infant cries as a mediator between maternal tobacco/cannabis use, psychological distress (depression/anger/hostility) and reported cravings for cigarettes and/or cannabis across two time points. Methods: A total of 96 substance-using mothers (35 tobacco-only and 61 tobacco/cannabis) were recruited in pregnancy. Maternal substance use and psychological distress were measured when their children were school age (5–6 years, T1). At the middle childhood assessment (9–12 years, T2), mothers listened to a standardized set of newborn cries and, afterwards, rated their aversiveness, impact on negative affect, and their tobacco/cannabis cravings. Results: Higher levels of maternal depressive symptoms at T1 were associated with perceptions of cries as being more aversive at T2, which, in turn, were associated with increased cannabis cravings at T2. At T1, higher depressive symptoms predicted increased tobacco cravings and higher maternal anger/hostility predicted increased cannabis cravings. Conclusions: Results highlight the role that infant cries and psychological distress play in cravings among tobacco/cannabis-using mothers. Full article

Background/Objectives: Providing appropriate treatment for pediatric patients after traffic accidents remains a significant challenge. Furthermore, limited studies have validated the long-term effectiveness and safety of integrative Korean medicine treatment (IKMT) based on follow-up periods of 6 months or longer for pediatric patients. Methods: A retrospective chart review was conducted, focused on children aged 0–6 years who visited one of seven Korean medicine hospitals after traffic accident injuries and received IKMT between 1 January 2019 and 30 June 2023. The primary outcome was the Numeric Rating Scale (NRS) scores of chief complaints, and the secondary outcomes were quality of life, adverse events, and satisfaction with IKMT. Statistical analyses were conducted using paired t-tests and descriptive statistics, with a significance level of 5%. Results: Sixty-four participants were included in the retrospective chart review, and fifty-seven guardians responded to the surveys (mean age: 4.84 ± 1.26 years; mean duration of treatment: 19.20 ± 25.38 days). Among the immediate symptoms after the accidents, flashbacks and intrusive symptoms as well as nightmares and crying were the most common (50.9%). Following treatment, the NRS scores for flashbacks and intrusive symptoms and for nightmares and crying showed meaningful improvements from the time right after the accidents to the survey period. Follow-up confirmed that quality of life scores on all dimensions corresponded with those of healthy children. Nine adverse events were reported, and the participants fully recovered without the need for additional treatment. Furthermore, 91.2% of the survey respondents were satisfied with IKMT. Conclusions: IKMT was effective and safe for alleviating the post-accident symptoms in infants and young children aged 0–6 years involved in traffic accidents. Full article

Background/Objective: A growing body of international research continues to show evidence of worsening youth mental health since the beginning of the COVID-19 global pandemic, yet very little research in this area has included young children under 6 years. Given the potential impact of early life stress during this critical period of development, it is crucial to better understand the effects on this age group. The objective of this study was to better understand the impact of the COVID-19 pandemic on the emotional health of very young children. Methods: This study utilized retrospective chart review of primary care records to compare the prevalence of markers of stress in two cohorts of children under the age of 6 years, comparing children presenting for care prior to the pandemic (1 April 2019–31 March 2020; control period) with those presenting for care during the first year of the pandemic (1 April 2020–31 March 2021; study period) in a large pediatric primary care clinic in Washington, DC, USA. Based on power calculations, charts of 200 patients from each cohort were reviewed and prevalence of stress markers were summarized using counts and percentages and compared between groups using chi-squared tests. Multivariable logistic regression models were also conducted for each domain adjusting for age, gender, and insurance type. Results: Overall, sleep difficulties were significantly more prevalent during the pandemic period compared to the control period (14% vs. 6.5%, p = 0.013). In addition, signs of stress presented differently across age groups. For example, during the pandemic period toddlers (13–35 months) were 13 times more likely (OR = 13, 95% CI [2.82, 60.4], p < 0.001) and preschool-aged children (36–71 months) were 18.5 times more likely (OR = 18.5, 95% CI [4.0, 86], p < 0.001) than infants to present with behavior problems, indicating substantially higher risk of externalizing symptoms in older children compared to infants. Toddlers were less likely than infants to present with mood changes (e.g., fussiness or crying) (OR = 0.15, 95% CI [0.03, 0.65], p = 0.011). In addition, toddlers (OR = 0.55, 95% CI [0.31, 0.97], p = 0.038) and preschool-aged children (OR = 0.15, 95% CI [0.06, 0.4], p < 0.001) were also less likely to present with feeding difficulties compared to infants. Conclusions: One of the very few studies of young children under 6 years (including infants) during the COVID-19 pandemic, this study found that even very young children experienced stress during the pandemic. Signs of emotional stress were identified in a primary care office during routine care, highlighting an important opportunity for early intervention and/or prevention, such as counseling and resources for caregivers, in settings where young children are already presenting for routine care. Full article

Background and Clinical Significance: Prader–Willi syndrome (PWS) is a rare genetic disease caused by imprinted gene dysfunction, typically involving deletion of the chromosome 15q11.2-q13 region, balanced translocation, or related gene mutations in this region. PWS presents with complex and varied clinical manifestations. Abnormalities can be observed from the fetal stage and change with age, resulting in growth, developmental, and metabolic issues throughout different life stages. Case Presentation: We report the prenatal characteristics observed from the second to third trimester of pregnancy in a neonate with PWS. Prenatal ultrasound findings included a single umbilical artery, poor abdominal circumference growth from 26 weeks, normal head circumference and femur length growth, increased amniotic fluid volume after 30 weeks, undescended fetal testicles in the third trimester, small kidneys, and reduced fetal movement. The male infant was born at 38 weeks of gestation with a birth weight of 2580 g. He had a weak cry; severe hypotonia; small eyelid clefts; bilateral cryptorchidism; low responsiveness to medical procedures such as blood drawing; and poor sucking, necessitating tube feeding. Blood methylation-specific multiple ligation-dependent probe amplification (MS-MLPA) showed paternal deletion PWS. Notably, this case revealed two previously unreported prenatal features in PWS: a single umbilical artery and small kidneys. Conclusions: Through literature review and our case presentation, we suggest that a combination of specific sonographic features, including these newly identified markers, may aid clinicians in the early diagnosis of PWS. Full article

This study investigates the ability of well-known deep learning models, such as ResNet and EfficientNet, to perform audio-based infant cry detection. By comparing the performance of different machine learning algorithms, this study seeks to determine the most effective approach for the detection of infant crying, enhancing the functionality of baby monitoring systems and contributing to a more advanced understanding of audio-based deep learning applications. Understanding and accurately detecting a baby’s cries is crucial for ensuring their safety and well-being, a concern shared by new and expecting parents worldwide. Despite advancements in child health, as noted by UNICEF’s 2022 report of the lowest ever recorded child mortality rate, there is still room for technological improvement. This paper presents a comprehensive evaluation of deep learning models for infant cry detection, analyzing the performance of various architectures on spectrogram and MFCC feature representations. A key focus is the comparison between pretrained and non-pretrained models, assessing their ability to generalize across diverse audio environments. Through extensive experimentation, ResNet50 and DenseNet trained on spectrograms emerged as the most effective architectures, significantly outperforming other models in classification accuracy. Additionally, the study investigates the impact of feature extraction techniques, dataset augmentation, and model fine-tuning, providing deeper insights into the role of representation learning in audio classification. The findings contribute to the growing field of audio-based deep learning applications, offering a detailed comparative study of model architectures, feature representations, and training strategies for infant cry detection. Full article

Background/Objectives: Cow’s milk allergy (CMA) presents a significant clinical burden. The Cow’s Milk-related Symptom Score (CoMiSS™) is a widely used clinical screening tool designed to raise awareness of CMA among healthcare professionals. This qualitative study aimed to assess the need for a parent-reported CoMiSS™ tool (Pre-CoMiSS™) and explore its potential usefulness for parents and primary care physicians (PCPs). Methods: Participants were parents of infants aged 2–12 months and PCPs from Germany, Sweden, Spain, and the United Kingdom (UK) selected from a local panel of potential respondents. Interviews, conducted by experienced qualitative research moderators, consisted of pre-decided standardised questions. Thematic analysis was undertaken, and themes were derived from the data. Results: A total of 26 parent interviews and 18 primary care physician interviews were conducted. Parents from all countries found the Pre-CoMiSS™ tool helpful for understanding their baby’s signs, easy to use, and useful for facilitating consultation with the physician. Physicians in the UK, Spain, and Sweden found that the Pre-CoMiSS™ tool was helpful for improving symptom reporting and for medical consultations; however, in Germany, physicians had mixed opinions, expressing concerns that the tool might increase parental anxiety, lead to overdiagnosis of CMA, and add to their workload. Conclusions: A parent-specific tool for recording cow’s milk-related symptoms was generally well received by parents and most physicians, though concerns about parental anxiety and workload were noted, particularly in Germany. With further validation and refinement, Pre-CoMiSS™ may be a useful tool for parents to record their infant’s symptoms related to feeding and support PCPs in considering CMA in these infants. Full article

Newborns cry intensely, and most parents struggle to understand the reason behind their crying, as the baby cannot verbally express their needs. This makes it challenging for parents to know if their child has a need or a health issue. An embedded solution based on a Raspberry Pi is presented to address this problem. The module analyzes audio techniques to capture, analyze, classify, and remotely monitor a baby’s cries. These techniques rely on prosodic and cepstral features, such as MFCC coefficients. They can differentiate the reason behind a baby’s cry, such as hunger, stomach pain, or discomfort. A machine learning model was trained to anticipate the reason based on audio features. The embedded system includes a microphone to capture real-time cries and a display screen to show the anticipated reason. In addition, the system sends the collected data to a web server for storage, enabling remote monitoring and more detailed data analysis. A cell phone application has also been developed to notify parents in real time of why their baby is crying. This application enables parents to adapt quickly and efficiently to their infant’s needs, even when they are not around. Full article

Objectives: To report the prevalence of invasive bacterial infection (IBI) in febrile infants ≤90 days presenting to hospital within 72 h of meningococcal B (MenB) immunisation. Methods: A secondary analysis of data from two previous multicentre studies of febrile infants conducted at UK and Irish hospitals. The first study was a retrospective study, conducted at six sites between 31 August 2018 and 1 September 2019. The second study was a prospective study conducted at 35 sites between 6 July 2022 and 31 August 2023. Febrile infants ≤90 days who had received the MenB vaccine within 72 h preceding presentation were included. Results: A total of 102 infants met the inclusion criteria, with a median age of 61 days and a male predominance of 65.7%. The most reported clinical features were an abnormal cry, decreased feeding and coryzal symptoms. In total, 68/102 (66.7%) were admitted to hospital; the median length of stay was 1 day. Median C-reactive protein (CRP) was 20.5 mg/L, mean white cell count was 13.7 × 10⁹/L, mean neutrophil count was 7.3 × 10⁹/L and mean lymphocyte count was 4.7 × 10⁹/L. In total, 38/102 (37.3%) had blood cultures performed, 26/102 (25.5%) had respiratory viral testing performed, 55/102 (53.9%) had urine culture performed and 14/102 (13.7%) had lumbar puncture performed. Additionally, 26/102 (25.5%) received parenteral antibiotics. There were no cases of IBI, and 3/102 (2.9%) cases of urinary tract infection. Conclusions: The rate of IBI is negligible in febrile infants following MenB immunisations. Current blood tests such as CRP are unreliable in this cohort, as many exhibit a moderate CRP rise above suggested international cut-offs for this age range. Full article

Neonatal mortality remains a critical global challenge, particularly in resource-limited settings with restricted access to advanced diagnostic tools. Early detection of life-threatening conditions like Sepsis and Respiratory Distress Syndrome (RDS), which significantly contribute to neonatal deaths, is crucial for timely interventions and improved survival rates. This study investigates the use of newborn cry sounds, specifically the expiratory segments (the most informative parts of cry signals) as non-invasive biomarkers for early disease diagnosis. We utilized an expanded and balanced cry dataset, applying Self-Supervised Learning (SSL) models—wav2vec 2.0, WavLM, and HuBERT—to extract feature representations directly from raw cry audio signals. This eliminates the need for manual feature extraction while effectively capturing complex patterns associated with sepsis and RDS. A classifier consisting of a single fully connected layer was placed on top of the SSL models to classify newborns into Healthy, Sepsis, or RDS groups. We fine-tuned the SSL models and classifiers by optimizing hyperparameters using two learning rate strategies: linear and annealing. Results demonstrate that the annealing strategy consistently outperformed the linear strategy, with wav2vec 2.0 achieving the highest accuracy of approximately 90% (89.76%). These findings highlight the potential of integrating this method into Newborn Cry Diagnosis Systems (NCDSs). Such systems could assist medical staff in identifying critically ill newborns, prioritizing care, and improving neonatal outcomes through timely interventions. Full article

Background/Objectives: Infant regulatory problems (RPs), i.e., crying, sleeping, and feeding problems, are associated with unfavorable outcomes in later childhood. RPs increased during the pandemic; however, their occurrence in the face of today’s societal challenges remains unclear. RPs are strongly linked to parenting stress and less positive parenting behaviors, but their interplay is less investigated. Methods: In this cross-sectional, questionnaire-based study (ntotal = 7039), we compared the incidences of crying, sleeping, and feeding problems in infants (0–2 years) in pandemic (npandemic = 1391) versus post-pandemic (npost-pandemic = 5648) samples in Germany. We also investigated the relationship between post-pandemic infant RPs and parenting behaviors with parenting stress as a potential mediator for fathers and mothers. Results: Crying/whining/sleeping problems (34.8%) and excessive crying (6.3%) were significantly more prevalent in the post-pandemic sample. In both mothers and fathers, infant RPs were significantly associated with less positive parenting behaviors. Parenting stress partially mediated this relationship. Conclusions: RPs in the post-pandemic era are even more prevalent than during the pandemic, highlighting the imperative for health care professionals to focus on infant mental health. Parenting stress emerges as an entry point for addressing the cycle of infant RPs and maladaptive behaviors in both fathers and mothers. Full article