Integrating artificial intelligence, machine learning, and deep learning approaches into remediation of contaminated sites: A review.

The growing number of contaminated sites across the world pose a considerable threat to the environment and human health. Remediating such sites is a cumbersome process with the complexity originating from the need for extensive sampling and testing during site characterization. Selection and design of remediation technology is further complicated by the uncertainties surrounding contaminant attributes, concentration, as well as soil and groundwater properties, which influence the remediation efficiency. Additionally, challenges emerge in identifying contamination sources and monitoring the affected area. Often, these problems are overly simplified, and the data gathered is underutilized rendering the remediation process inefficient. The potential of artificial intelligence (AI), machine-learning (ML), and deep-learning (DL) to address these issues is noteworthy, as their emergence revolutionized the process of data management/analysis. Researchers across the world are increasingly leveraging AI/ML/DL to address remediation challenges. Current study aims to perform a comprehensive literature review on the integration of AI/ML/DL tools into contaminated site remediation. A brief introduction to various emerging and existing AI/ML/DL technologies is presented, followed by a comprehensive literature review. In essence, ML/DL based predictive models can facilitate a thorough understanding of contamination patterns, reducing the need for extensive soil and groundwater sampling. Additionally, AI/ML/DL algorithms can play a pivotal role in identifying optimal remediation strategies by analyzing historical data, simulating scenarios through surrogate models, parameter-optimization using nature inspired algorithms, and enhancing decision-making with AI-based tools. Overall, with supportive measures like open-data policies and data integration, AI/ML/DL possess the potential to revolutionize the practice of contaminated site remediation.

Primary hyperparathyroidism in pregnancy: observations from the Indian PHPT registry.

PURPOSE: To present the data on primary hyperparathyroidism (PHPT) in pregnancy from India obtained from a large database maintained over 15 years. METHODS: We retrieved data of all women with gestational PHPT from the Indian PHPT registry between July 2005 and January 2020, and compared their clinical, biochemical, and other characteristics with age-matched non-pregnant women with PHPT. RESULTS: Out of 386 women, eight had gestational PHPT (2.1%). The common presenting manifestations were acute pancreatitis (50%) and renal stone disease (50%); two were asymptomatic. Five women (62.5%) had a history of prior miscarriages. Seven patients (88%) had preeclampsia during the present gestation. Serum calcium and intact parathyroid hormone (iPTH) were not statistically different from the age-matched non-pregnant PHPT group. Six patients with mild-to-moderate hypercalcemia were medically managed with hydration with/without cinacalcet while one patient underwent percutaneous ethanol ablation of the parathyroid adenoma; none underwent surgery during pregnancy. Mean serum calcium maintained from treatment initiation till delivery was 10.5 ± 0.4 mg/dl. One patient had spontaneous preterm delivery at 36 weeks; the remaining patients had normal vaginal delivery at term. None had severe preeclampsia/eclampsia. Fetal outcomes included low birth weight in three newborns (37.5%); two of them had hypocalcemic seizures. CONCLUSION: The prevalence of gestational PHPT was 2.1% in this largest Indian PHPT cohort, which is higher than that reported from the West (< 1%). Gestational PHPT can lead to preeclampsia and miscarriage. Pregnant PHPT patients with mild-to-moderate hypercalcemia can be managed with hydration/cinacalcet; however, long-term safety data and large-scale randomized controlled trials are required.

Clinical efficacy of Professional Continuous Glucose Monitoring in improving glycemic control among children with Type 1 Diabetes Mellitus: An Open-label Randomized Control Trial.

Frequent self-monitoring of blood glucose (SMBG) is the only accurate method available for insulin dose titration in patients with T1DM. Professional continuous glucose monitoring (p-CGM) is blinded recording of glucose trends over 5-7 days and helps physicians to guide insulin titration to patient. This study was planned to assess efficacy of insulin dose adjustments, based on p-CGM plus SMBG in improving glycemic control compared to SMBG alone. We did an open-label, parallel design, randomized control trial among children (2-10 years) having T1DM for at least 6 months. Subjects in the intervention group were placed on p-CGM (iPRO 2™ Professional CGM, Medtronic, USA) for 3-5 days along with regular SMBG. Data from p-CGM was analyzed by physician and used to guide insulin titration along with SMBG over following 3 months. Control group had only SMBG records for titrating insulin doses. Primary outcome was change in HbA1c 3 months after intervention. A total of 68 eligible children were randomized, 34 each to either arms. Thirty children in intervention group and 33 in control group completed the study and were analyzed. It was found that there was more decreased unit change in HbA1c, percentage of low sugar records and total insulin requirement per day, after 3 months follow-up, in intervention group. However, difference was not significant except for total insulin Units/kg/day (p = 0.014). In sub-group analysis of children with baseline HbA1c >7.5%, there was a significant mean fall of HbA1c by 1.27% (p = 0.045). There were no major adverse events associated with p-CGM. We conclude that addition of p-CGM along with SMBG may help in adjusting insulin dose more effectively especially in children with higher baseline HbA1c.