Recent advances in developing biosensing based platforms for neonatal sepsis

Retinopathy of prematurity (ROP) is a potentially blinding disorder seen in low birth weight preterm infants. In India, the burden of ROP is high, with nearly 200,000 premature infants at risk. Early detection through screening and treatment can prevent this blindness. The automatic screening systems developed so far can detect “severe ROP” or “plus disease,” but this information does not help schedule follow-up. Identifying vascularized retinal zones and detecting the ROP stage is essential for follow-up or discharge from screening. There is no automatic system to assist these crucial decisions to the best of the authors’ knowledge. The low contrast of images, incompletely developed vessels, macular structure, and lack of public data sets are a few challenges in creating such a system. In this paper, a novel method using an ensemble of “U-Network” and “Circle Hough Transform” is developed to detect zones I, II, and III from retinal images in which macula is not developed. The model developed is generic and trained on mixed images of different sizes. It detects zones in images of variable sizes captured by two different imaging systems with an accuracy of 98%. All images of the test set (including the low-quality images) are considered. The time taken for training was only 14 min, and a single image was tested in 30 ms. The present study can help medical experts interpret retinal vascular status correctly and reduce subjective variation in diagnosis.

Assistive Framework for Automatic Detection of All the Zones in Retinopathy of Prematurity Using Deep Learning

Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review

In recent years, baby care has become more important and challenging for working mothers. Even at home, working mothers will not have enough time to monitor their babies continuously. They give the responsibility of their baby to either a baby caretaker or they send the baby to their grandparents' house. In the proposed work, a smart cradle with an automated baby monitoring system was developed. In the baby monitoring system, the necessary parameters of the infant like temperature, heartbeat rate, gas molecules, capture the motion and position of the baby were measured and monitored. The S.ODI board is used for interfacing the sensors and actuators. The baby monitoring system is attached to the cradle so that an incubator kind of environment will be created for the baby. The baby monitoring system monitors the baby 24×7. The measured parameters regarding the baby's health like temperature, heartbeat rate, dampness on the baby bed will be displayed in the mobile application. If the recorded readings show any abnormalities, the necessary actions like controlling temperature, switching on or off the fan, setting up cradle's movement, playing music for the baby will be taken. If the readings seem abnormal, the caretaker along with the parents will get an alert message. The motion and posture status of the infant can be monitored using motion Eye OS. The baby monitoring system prototype helps the parents in time management and makes it easier for the caretakers as well. This baby monitoring system is proven to have less harm for the baby with the most accuracy. This monitoring system is a highly efficient IoT based system for realtime monitoring with the best security measures.

IoT based Smart Cradle for Baby Monitoring System

Background Critical care units (CCUs) with extensive use of various monitoring devices generate massive data. To utilize the valuable information of these devices; data are collected and stored using systems like clinical information system and laboratory information management system. These systems are proprietary, allow limited access to their database and, have the vendor-specific clinical implementation. In this study, we focus on developing an open-source web-based meta-data repository for CCU representing stay of the patient with relevant details. Methods After developing the web-based open-source repository named data dictionary (DD), we analyzed prospective data from 2 sites for 4 months for data quality dimensions (completeness, timeliness, validity, accuracy, and consistency), morbidity, and clinical outcomes. We used a regression model to highlight the significance of practice variations linked with various quality indicators. Results DD with 1555 fields (89.6% categorical and 11.4% text fields) is presented to cover the clinical workflow of a CCU. The overall quality of 1795 patient days data with respect to standard quality dimensions is 87%. The data exhibit 88% completeness, 97% accuracy, 91% timeliness, and 94% validity in terms of representing CCU processes. The data scores only 67% in terms of consistency. Furthermore, quality indicators and practice variations are strongly correlated (P < 0.05). Conclusion This study documents DD for standardized data collection in CCU. DD provides robust data and insights for audit purposes and pathways for CCU to target practice improvements leading to specific quality improvements.

/pdf/development-of-data-dictionary-for-neonatal-intensive-care-1ecmh7dfoc.pdf

Development of data dictionary for neonatal intensive care unit: advancement towards a better critical care unit.

We report the design and implementation of an affordable bedside device, Neo is capable of acquiring vital data in real time by integrating with diverse devices connected to newborns in neonatal intensive care units (NICUs). NICUs are equipped with multiple vital sign monitoring devices that are connected to the premature newborn and acquire a few gigabytes of data every day. The continuous vital data from these devices are manually documented every hour. This introduces errors and loses a large amount of high-resolution data. The intermittent documentation of physiological data also makes it difficult for clinicians to visualize and detect the trends of diagnostic utility. Neo is built on an affordable Internet of Things platform that aggregates and sends the real-time data to a cloud-based big data platform called integrated NICU. Apart from minimizing documentation errors, the device enables data acquisition at sufficiently real-time rates as to indicate the current status of all the patients at the NICU. Neo automates immediate vital sign status and past trends as graphs or charts that the doctor and nurses can view from anywhere through the Internet. Physiological signal and clinical parameters from Neo is used to score different diseases like sepsis, respiratory distress syndrome, necrotizing enterocolitis, and retinopathy of prematurity. This score predicts the physiological health of the newborn and aid clinicians in decision-making ensuring timely intervention.

Neo-Bedside Monitoring Device for Integrated Neonatal Intensive Care Unit (iNICU)

Limbus-derived stromal/mesenchymal stem cells (LMSCs) are vital for corneal homeostasis and wound healing. However, despite multiple pre-clinical and clinical studies reporting the potency of LMSCs in avoiding inflammation and scarring during corneal wound healing, the molecular basis for the ability of LMSCs remains unknown. This study aimed to uncover the factors and pathways involved in LMSC-mediated corneal wound healing by employing RNA-Sequencing (RNA-Seq) in human LMSCs for the first time. We characterized the cultured LMSCs at the stages of initiation (LMSC−P0) and pure population (LMSC−P3) and subjected them to RNA-Seq to identify the differentially expressed genes (DEGs) in comparison to native limbus and cornea, and scleral tissues. Of the 28,000 genes detected, 7800 DEGs were subjected to pathway-specific enrichment Gene Ontology (GO) analysis. These DEGs were involved in Wnt, TGF-β signaling pathways, and 16 other biological processes, including apoptosis, cell motility, tissue remodeling, and stem cell maintenance, etc. Two hundred fifty-four genes were related to wound healing pathways. COL5A1 (11.81 ± 0.48) and TIMP1 (20.44 ± 0.94) genes were exclusively up-regulated in LMSC−P3. Our findings provide new insights involved in LMSC-mediated corneal wound healing.

/pdf/transcriptomic-profiling-of-human-limbus-derived-stromal-2cr5rqzh.pdf

Transcriptomic Profiling of Human Limbus-Derived Stromal/Mesenchymal Stem Cells—Novel Mechanistic Insights into the Pathways Involved in Corneal Wound Healing

Abhilash Gangadharan

Papers

Neo-Bedside Monitoring Device for Integrated Neonatal Intensive Care Unit (iNICU)

Transcriptomic Profiling of Human Limbus-Derived Stromal/Mesenchymal Stem Cells—Novel Mechanistic Insights into the Pathways Involved in Corneal Wound Healing