Identifying Diabetes Related-Complications in a Real-World Free-Text Electronic Medical Records in Hebrew Using Natural Language Processing Techniques.

BACKGROUND: Studies have demonstrated that 50% to 80% of patients do not receive an International Classification of Diseases (ICD) code assigned to their medical encounter or condition. For these patients, their clinical information is mostly recorded as unstructured free-text narrative data in the medical record without standardized coding or extraction of structured data elements. Leumit Health Services (LHS) in collaboration with the Israeli Ministry of Health (MoH) conducted this study using electronic medical records (EMRs) to systematically extract meaningful clinical information about people with diabetes from the unstructured free-text notes. OBJECTIVES: To develop and validate natural language processing (NLP) algorithms to identify diabetes-related complications in the free-text medical records of patients who have LHS membership. METHODS: The study data included 2.3 million records of 41 469 patients with diabetes aged 35 or older between the years 2012 and 2017. The diabetes related complications included cardiovascular disease, diabetic neuropathy, nephropathy, retinopathy, diabetic foot, cognitive impairments, mood disorders and hypoglycemia. A vocabulary list of terms was determined and adjudicated by two physicians who are experienced in diabetes care board certified diabetes specialist in endocrinology or family medicine. Two independent registered nurses with PhDs reviewed the free-text medical records. Both rule-based and machine learning techniques were used for the NLP algorithm development. Precision, recall, and F-score were calculated to compare the performance of (1) the NLP algorithm with the reviewers' comments and (2) the ICD codes with the reviewers' comments for each complication. RESULTS: The NLP algorithm versus the reviewers (gold standard) achieved an overall good performance with a mean F-score of 86%. This was better than the ICD codes which achieved a mean F-score of only 51%. CONCLUSION: NLP algorithms and machine learning processes may enable more accurate identification of diabetes complications in EMR data.

Sex-Specific Developmental Scales for Surveillance.

BACKGROUND: Developmental surveillance, conducted routinely worldwide, is fundamental for early detection of children at risk for developmental delay. We aimed to explore sex-related difference in attainment rates of developmental milestones and to evaluate the clinical need for separate sex-specific scales. METHODS: This is a cross-sectional, natiowide retrospective study, utilizing data from a national child surveillance program of ∼1000 maternal child health clinics. The main cohort, used for constructing sex-specific developmental scales, included all children born between January 2014 to September 2020, who visited maternal child health clinics from birth to 6 years of age (n = 839 574). Children with abnormal developmental potential were excluded (n = 195 616). A validation cohort included all visits between 2020 and 2021 (n = 309 181). The sex-differences in normative attainment age of 59 developmental milestones from 4 domains were evaluated. The milestones with a significant gap between males and females were identified, and the projected error rates when conducting unified versus sex-specific surveillance were calculated. RESULTS: A new sex-specific developmental scale was constructed. In total, females preceded males in most milestones of all developmental domains, mainly at older ages. Conducting routine developmental surveillance using a unified scale, compared with sex-specific scales, resulted in potential missing of females at risk for developmental delay (19.3% of failed assessments) and over-diagnosis of males not requiring further evaluation (5.9% of failed assessments). CONCLUSIONS: There are sex-related differences in the normative attainment rates of developmental milestones, indicating possible distortion of the currently used unified scales. These findings suggest that using sex-specific scales may improve the accuracy of early childhood developmental surveillance.

Assessing the Attainment Rates of Updated CDC Milestones Using a New Israeli Developmental Scale.

OBJECTIVES: Developmental milestones norms are widely used worldwide and are fundamental for early childhood developmental surveillance. We compared a new Israeli evidence-based national developmental scale with the recently updated Centers for Disease Control and Prevention (CDC) checklists. METHODS: We used a cohort of nearly 4.5 million developmental assessments of 758 300 full-term born children aged 0 to 6 years (ALL-FT cohort), who visited maternal child health clinics in Israel for routine developmental surveillance. Among the assessed milestones of 4 developmental domains (gross motor, fine motor, language, and personal-social) we identified milestones that had equivalents on the CDC checklists and assessed the attainment rates of the Israeli children at the ages recommended by the CDC, at which ≥75% of the children would be expected to achieve the milestone. The analysis was repeated on a subgroup of 658 958 children who were considered healthy, typically developing by their birth and growth characteristics (NORMAL-FT cohort). RESULTS: There were 29 milestones, across all developmental domains and assessment ages, whose definitions by both tools were compatible, and could be compared. The attainment rate at the CDC-recommended age was >90% for 22 (76%) and 23 (79%) milestones, and the median attainment rates were 95.2% and 96.3% in the ALL-FT and NORMAL-FT cohorts, respectively. CONCLUSIONS: For almost all comparable milestones of all domains and all ages, children of the Israeli cohorts achieved the milestones earlier than expected by the CDC-defined threshold age. Evidence-based analysis of milestone norms among different populations may enable adjustments of developmental scales and facilitate more personalized developmental surveillance.

Standardization of a Developmental Milestone Scale Using Data From Children in Israel.

Importance: Routine developmental screening tests for children are used worldwide for early detection of developmental delays. However, assessment of developmental milestone norms lacks strong normative data, and there are inconsistencies among different screening tools. Objective: To establish milestone norms and build an updated developmental scale. Design, Setting, and Participants: This is a cross-sectional, population-based study conducted between 2014 and 2020. Developmental assessments were conducted by trained public health nurses, documented in national maternal child health clinics, known as Tipat Halav, which serve all children in Israel. Participants included all children born between January 2014 and September 2020, who were followed at the maternal child health clinics from birth to age 6 years. Exclusion criteria were preterm birth, missing gestational age, low birth weight (<2.5 kg), abnormal weight measurement (<3% according to standardized child growth charts), abnormal head circumference measurement (<3% or >97% according to standardized child growth charts), and visits without developmental data or without the child's age. Data analysis was performed from September 2020 to June 2021. Exposures: In total, 59 milestones in 4 developmental domains were evaluated, and the achievement rate per child's age was calculated for each milestone. Main Outcomes and Measures: A contemporary developmental scale, the Tipat Halav Israel Screening (THIS) Developmental Scale, was built, presenting the 75%, 90%, and 95% achievement rates for each milestone. The THIS scale was compared with other commonly used screening tests, including the Denver Developmental Screening Test II (Denver II), the Alberta Infant Motor Scale (AIMS), and the Centers for Disease Control and Prevention (CDC) Developmental Assessment. Results: A total of 839 574 children were followed in the maternal child health clinics between January 2014 and September 2020 in Israel, and 195 616 children were excluded. A total of 3 774 517 developmental assessments were performed for the remaining 643 958 children aged 0 to 6 years (319 562 female children [49.6%]), resulting in the establishment of new developmental norms. In terms of the comparable milestones, THIS milestones had a match of 18 of 27 (67%) with the Denver II, 7 of 7 (100%) with AIMS, and 10 of 19 (53%) with the CDC Developmental Assessment. The remaining unmatched milestones were achieved earlier in the THIS scale compared with other screening tools. Conclusions and Relevance: The THIS developmental scale is based on the largest population evaluated to date for developmental performance, representing the heterogeneous, multicultural population comprising this cohort. It is recommended for further evaluation worldwide.