An Affordable phototherapy intensity meter using machine learning to improve the quality of care system for Hyperbilirubinemia in Indonesia.

Hyperbilirubinemia is more frequently seen in low and middle-income countries like Indonesia. One of the contributing factors is a substandard dose of Phototherapy irradiance. This research aims to design a phototherapy intensity meter called PhotoInMeter using readily available low-cost components. PhotoInMeter is designed by using a microcontroller, light sensor, color sensor, and an ND (neutral-density) filter. We use machine learning to create a mathematical model that converts the emission from the color sensor and light sensor into light intensity measurements that are close to Ohmeda Biliblanket's measurements. Our prototype collects sensor reading data and pairs them with Ohmeda Biliblanket Light Meter to create a training set for our machine learning algorithm. We create a multivariate linear regression, random forest, and XGBoost model based on our training set to convert sensor readings to Ohmeda Biliblanket Light Meter measurement. We successfully devised a prototype that costs 20 times less to produce compared to our reference intensity meter while still having high accuracy. Compared to Ohmeda Biliblanket Light Meter, our PhotoInMeter has a Mean Absolute Error (MAE) of 0.83 and achieves more than a 0.99 correlation score in all six different devices for intensity in the range of 0-90 µW/cm2/nm. Our prototypes show consistent reading between PhotoInMeter devices, having an average difference of 0.435 among all six devices.

Association between glial fibrillary acidic protein, glial-derived neurotrophic factor, and fatty acid-binding protein-2 at birth in the incidence of necrotizing enterocolitis in preterm infants.

Background: This study aimed to analyze the relationship between glial fibrillary acidic protein (GFAP), glial-derived neurotrophic factor (GDNF), and fatty acid-binding protein-2 (FABP-2) in preterm infants on the incidence of NEC. Methods: Preterm infants with a birth weight <1,500 g and gestational age <34 weeks were included in this study. Biomarker examination was performed using the umbilical vein blood at birth (first sample). Biomarker examination was repeated if the infant developed symptoms of NEC using peripheral vein blood (second sample). Infants were observed for 14 days. If NEC did not exist, a biomarker examination was performed at 14 days. Results: This study included 30 preterm infants, nine infants experienced NEC. The values of GFAP, GDNF, and FABP-2 (median and range) in the group with NEC were higher than those in the group without NEC in both the first samples {GFAP [1.40 (0.20-6.50) vs. 0.30 (0.10-1.30) P = 0.014], GDNF [2.84 (1.05-14.11) vs. 1.56 (1.07-3.48) P = 0.050], and FABP-2 [621.70 (278.40-2,207.00) vs. 294.20 (211.40-597.50) P = 0.002]} and second samples {GFAP [2.40 (0.30-3.10) vs. 0.30 (0.10-0.60) P = 0.003], GDNF [2.99 (0.56-10.30) vs. 1.46 (0.85-2.24) P = 0.019], and FABP-2 [646.8 (179.20-1,571.00) vs. 314.90 (184.70-521.60) P = 0.040]}. In infants with NEC, the median values of GFAP [2.40 (0.30-3.10) vs. 1.40 (0.20-6.50) P = 0.767], GDNF [2.99 (0.56-10.30) vs. 2.84 (1.05-14.11) P = 0.859], and FABP-2 [646.80 (179.20-1,571.00) vs. 621.70 (278.40-2,207.00) P = 0.953] in the second sample were higher than those in the first sample. Logistic regression demonstrated that GFAP at birth (Odds Ratio [OR] = 15.629, 95% Confidence Interval [CI] = 1.697-143.906, P = 0.015) and FABP-2 levels at birth (OR = 1.008, 95% CI = 1.001-1.015, P = 0.033) were significantly associated with an increased risk of NEC. Conclusion: Increased GFAP, GDNF, and FABP-2 at birth are associated with NEC occurrence within two weeks of birth. These findings suggest that early-onset NEC is associated with intestinal injury that occurs during the perinatal or even prenatal period.

A review of existing neonatal hyperbilirubinemia guidelines in Indonesia.

Background: Neonatal hyperbilirubinemia is one of the most common conditions for neonate inpatients. Indonesia faces a major challenge in which different guidelines regarding the management of this condition were present. This study aimed to compare the existing guidelines regarding prevention, diagnosis, treatment and monitoring in order to create the best recommendation for a new hyperbilirubinemia guideline in Indonesia. Methods: Through an earlier survey regarding adherence to the neonatal hyperbilirubinemia guideline, we identified that three main guidelines are being used in Indonesia. These were developed by the Indonesian Pediatric Society (IPS), the Ministry of Health (MoH), and World Health Organization (WHO). In this study, we compared factors such as prevention, monitoring, methods for identifying, risk factors in the development of neonatal jaundice, risk factors that increase brain damage, and intervention treatment threshold in the existing guidelines to determine the best recommendations for a new guideline. Results: The MoH and WHO guidelines allow screening and treatment of hyperbilirubinemia based on visual examination (VE) only. Compared with the MoH and WHO guidelines, risk assessment is comprehensively discussed in the IPS guideline. The MoH guideline recommends further examination of an icteric baby to ensure that the mother has enough milk without measuring the bilirubin level. The MoH guideline recommends referring the baby when it looks yellow on the soles and palms. The WHO and IPS guidelines recommend combining VE with an objective measurement of transcutaneous or serum bilirubin. The threshold to begin phototherapy in the WHO guideline is lower than the IPS guideline while the exchange transfusion threshold in both guidelines are comparably equal. Conclusions: The MoH guideline is outdated. MoH and IPS guidelines are causing differences in approaches to the management hyperbilirubinemia. A new, uniform guideline is required.

Comparison of complication rates between umbilical and peripherally inserted central venous catheters in newborns.

OBJECTIVE: To compare the complication rates between umbilical central venous catheters and peripherally inserted central venous catheters in newborns and to investigate whether other variables might increase complication rates. DESIGN: A retrospective observational study. SETTING: A Level III neonatal intensive care unit (NICU). PARTICIPANTS AND SETTING: Newborns (gestational age 24-42 weeks). METHODS: All central venous catheter-related complications were retrospectively analyzed in newborns. The differences in survival rates between the two types of central venous catheters were evaluated using a Kaplan-Meier survival analysis with removal because of complications as the event of interest. RESULTS: In total, 140 umbilical venous catheters and 63 peripherally inserted central catheters were included. There were no significant differences in removals due to complications between the two catheters. The central line-associated bloodstream infections had the highest complication incidence, followed by obstruction, dislocation, leakage, and extravasation. There were no influences of gestational age, birth weight, and the use of subsequent catheters on the complication incidence. CONCLUSION: A high complication incidence resulted in removal of the catheters, but it was not significantly different between the two catheters. The prevention of complications should be an important goal in the daily care of infants in the NICU.