Neonatal Jaundice Diagnosis Using a Smartphone Camera Based on Eye, Skin, and Fused Features with Transfer Learning

Development of Non-Invasive Biosensors for Neonatal Jaundice Detection: A Review

One of the most common problems many babies encounter is neonatal jaundice. The symptoms are yellowing of the skin or eyes because of bilirubin (from above 2.0 to 2.5 mg/dL in the blood). If left untreated, it can lead to serious neurological complications. Traditionally, jaundice detection has relied on invasive blood tests, but developing non-invasive biosensors has provided an alternative approach. This systematic review aims to assess the advancement of these biosensors. This review discusses the many known invasive and non-invasive diagnostic modalities for detecting neonatal jaundice and their limitations. It also notes that the recent research and development on non-invasive biosensors for neonatal jaundice diagnosis is still in its early stages, with the majority of investigations being in vitro or at the pre-clinical level. Non-invasive biosensors could revolutionize neonatal jaundice detection; however, a number of issues still need to be solved before this can happen. These consist of in-depth validation studies, affordable and user-friendly gadgets, and regulatory authority approval. To create biosensors that meet regulatory requirements, additional research is required to make them more precise and affordable.

Applications of Artificial Intelligence in Neonatology

The development of artificial intelligence methods has impacted therapeutics, personalized diagnostics, drug discovery, and medical imaging. Although, in many situations, AI clinical decision-support tools may seem superior to rule-based tools, their use may result in additional challenges. Examples include the paucity of large datasets and the presence of unbalanced data (i.e., due to the low occurrence of adverse outcomes), as often seen in neonatal medicine. The most recent and impactful applications of AI in neonatal medicine are discussed in this review, highlighting future research directions relating to the neonatal population. Current AI applications tested in neonatology include tools for vital signs monitoring, disease prediction (respiratory distress syndrome, bronchopulmonary dysplasia, apnea of prematurity) and risk stratification (retinopathy of prematurity, intestinal perforation, jaundice), neurological diagnostic and prognostic support (electroencephalograms, sleep stage classification, neuroimaging), and novel image recognition technologies, which are particularly useful for prompt recognition of infections. To have these kinds of tools helping neonatologists in daily clinical practice could be something extremely revolutionary in the next future. On the other hand, it is important to recognize the limitations of AI to ensure the proper use of this technology.

Deep Learning Algorithms for Screening and Diagnosis of Systemic Diseases Based on Ophthalmic Manifestations: A Systematic Review

Deep learning (DL) is the new high-profile technology in medical artificial intelligence (AI) for building screening and diagnosing algorithms for various diseases. The eye provides a window for observing neurovascular pathophysiological changes. Previous studies have proposed that ocular manifestations indicate systemic conditions, revealing a new route in disease screening and management. There have been multiple DL models developed for identifying systemic diseases based on ocular data. However, the methods and results varied immensely across studies. This systematic review aims to summarize the existing studies and provide an overview of the present and future aspects of DL-based algorithms for screening systemic diseases based on ophthalmic examinations. We performed a thorough search in PubMed^®, Embase, and Web of Science for English-language articles published until August 2022. Among the 2873 articles collected, 62 were included for analysis and quality assessment. The selected studies mainly utilized eye appearance, retinal data, and eye movements as model input and covered a wide range of systemic diseases such as cardiovascular diseases, neurodegenerative diseases, and systemic health features. Despite the decent performance reported, most models lack disease specificity and public generalizability for real-world application. This review concludes the pros and cons and discusses the prospect of implementing AI based on ocular data in real-world clinical scenarios.

Validation of a smartphone-based screening tool (Biliscan) for neonatal jaundice in a multi-ethnic neonatal population

AIM

Neonatal jaundice is an important and prevalent condition that can cause kernicterus and mortality. This study validated a smartphone-based screening application (Biliscan) in detecting neonatal jaundice.

METHODS

A cross-sectional prospective study was conducted at the neonatal unit in a tertiary teaching hospital between August 2020 and October 2021. All babies born at the gestation of 35 weeks and above with clinical jaundice or are recommended for screening of jaundice within 21 days of post-natal age were recruited. Using Biliscan, images of the babies' skin over the sternum were taken against a standard colour card. The application uses feature extraction and machine learning regression to estimate the bilirubin level. Independent Biliscan bilirubin estimates (BsB) were made and compared with total serum bilirubin (TSB) and transcutaneous bilirubin (TcB) levels. Bland Altman plots were used to establish the agreement between BsB and TSB, as well as TcB, using the clinically acceptable limits of agreement of ±35 μmol/L, which were defined a priori. Pearson correlation coefficient was assessed to establish the strength of the relationship between BsB versus TSB and TcB. Diagnostic accuracy was assessed through receiver operating characteristic curve analysis.

RESULTS

Sixty-one paired TSB-BsB and 85 paired TcB-BsB measurements were obtained. Bland Altman plot for the entire group showed that 54% (33/61) of the pairs of TSB and BsB readings and 66% (56/85) of the pairs of TcB and BsB readings were within the maximum clinically acceptable difference of 35 μmol/L. Pearson r for BsB versus TSB and TcB was 0.54 (P < 0.001) and 0.66 (P < 0.001) respectively. Compared with TSB, the recommended gold standard measure for jaundice, Biliscan has a sensitivity of 76.92% and specificity of 70.83% for jaundice requiring phototherapy. The positive and negative predictive values in term infants were 93.3% and 36.9%, respectively.

CONCLUSION

Our results suggest that there is moderate correlation and mediocre agreement between BsB and TSB, as well as TcB. Improvement to the application algorithm and further studies that include a larger population, and a wider range of bilirubin values are necessary before the tool may be considered for use in screening of jaundice in newborns.

Management challenges in the treatment of severe hyperbilirubinemia in low- and middle-income countries: Encouraging advancements, remaining gaps, and future opportunities

Neonatal jaundice (NJ) is common in newborn infants. Severe NJ (SNJ) has potentially negative neurological sequelae that are largely preventable in high resource settings if timely diagnosis and treatment are provided. Advancements in NJ care in low- and middle-income countries (LMIC) have been made over recent years, especially with respect to an emphasis on parental education about the disease and technological advancements for improved diagnosis and treatment. Challenges remain, however, due to lack of routine screening for SNJ risk factors, fragmented medical infrastructure, and lack of culturally appropriate and regionally specific treatment guidelines. This article highlights both encouraging advancements in NJ care as well as remaining gaps. Opportunities are identified for future work in eliminating the gaps in NJ care and preventing death and disability related to SNJ around the globe.

On AI Approaches for Promoting Maternal and Neonatal Health in Low Resource Settings: A Review

A significant challenge for hospitals and medical practitioners in low- and middle-income nations is the lack of sufficient health care facilities for timely medical diagnosis of chronic and deadly diseases. Particularly, maternal and neonatal morbidity due to various non-communicable and nutrition related diseases is a serious public health issue that leads to several deaths every year. These diseases affecting either mother or child can be hospital-acquired, contracted during pregnancy or delivery, postpartum and even during child growth and development. Many of these conditions are challenging to detect at their early stages, which puts the patient at risk of developing severe conditions over time. Therefore, there is a need for early screening, detection and diagnosis, which could reduce maternal and neonatal mortality. With the advent of Artificial Intelligence (AI), digital technologies have emerged as practical assistive tools in different healthcare sectors but are still in their nascent stages when applied to maternal and neonatal health. This review article presents an in-depth examination of digital solutions proposed for maternal and neonatal healthcare in low resource settings and discusses the open problems as well as future research directions.