Management and outcomes in secondary diabetes among pediatric patients hospitalized with hemophagocytic lymphohistiocytosis.

OBJECTIVES: Hemophagocytic lymphohistiocytosis (HLH) is a life-threatening disorder marked by massive cytokine release from macrophage and T-cell activation. Hallmarks include fever, splenomegaly, cytopenias, hypertriglyceridemia, hypofibrinogemia, and elevations in ferritin and soluble IL-2 receptor. Given the association of HLH with inflammation and glucocorticoid therapy, the development of hyperglycemia is not unexpected. Descriptions of the prevalence of secondary diabetes in youth diagnosed with HLH are lacking. METHODS: Retrospective review from 2010 through 2019 of hospitalized youth 0-21 years diagnosed with HLH. The primary outcome of interest was the development of secondary diabetes, defined as a serum glucose 200 mg/dL or higher necessitating insulin therapy. RESULTS: Of 28 patients with HLH, 36 % (n=10) developed secondary diabetes. The only risk factor associated with secondary diabetes was an infectious cause of HLH (60 % vs. 27.8 %, p 0.041). Intravenous regular insulin was used in 80 % of patients with a mean duration of 9.5 days (2-24 days). Most (70 %) needed insulin within 5 days of starting steroids. Stays in the ICU were longer (median 20 vs. 3 days, p 0.007) and intubation more likely (90 vs. 45 %, p 0.041) among those with secondary diabetes. Mortality was high (16-30 %) regardless of insulin use (p 0.634). CONCLUSIONS: One-third of hospitalized pediatric patients with HLH developed secondary diabetes requiring insulin therapy. Insulin is typically started within 5 days of initiating steroids, limited to IV infusions, and often is not needed by discharge. Secondary diabetes was associated with longer ICU stays and heightened risk of intubation.

An "All-Data-on-Hand" Deep Learning Model to Predict Hospitalization for Diabetic Ketoacidosis in Youth With Type 1 Diabetes: Development and Validation Study.

BACKGROUND: Although prior research has identified multiple risk factors for diabetic ketoacidosis (DKA), clinicians continue to lack clinic-ready models to predict dangerous and costly episodes of DKA. We asked whether we could apply deep learning, specifically the use of a long short-term memory (LSTM) model, to accurately predict the 180-day risk of DKA-related hospitalization for youth with type 1 diabetes (T1D). OBJECTIVE: We aimed to describe the development of an LSTM model to predict the 180-day risk of DKA-related hospitalization for youth with T1D. METHODS: We used 17 consecutive calendar quarters of clinical data (January 10, 2016, to March 18, 2020) for 1745 youths aged 8 to 18 years with T1D from a pediatric diabetes clinic network in the Midwestern United States. The input data included demographics, discrete clinical observations (laboratory results, vital signs, anthropometric measures, diagnosis, and procedure codes), medications, visit counts by type of encounter, number of historic DKA episodes, number of days since last DKA admission, patient-reported outcomes (answers to clinic intake questions), and data features derived from diabetes- and nondiabetes-related clinical notes via natural language processing. We trained the model using input data from quarters 1 to 7 (n=1377), validated it using input from quarters 3 to 9 in a partial out-of-sample (OOS-P; n=1505) cohort, and further validated it in a full out-of-sample (OOS-F; n=354) cohort with input from quarters 10 to 15. RESULTS: DKA admissions occurred at a rate of 5% per 180-days in both out-of-sample cohorts. In the OOS-P and OOS-F cohorts, the median age was 13.7 (IQR 11.3-15.8) years and 13.1 (IQR 10.7-15.5) years; median glycated hemoglobin levels at enrollment were 8.6% (IQR 7.6%-9.8%) and 8.1% (IQR 6.9%-9.5%); recall was 33% (26/80) and 50% (9/18) for the top-ranked 5% of youth with T1D; and 14.15% (213/1505) and 12.7% (45/354) had prior DKA admissions (after the T1D diagnosis), respectively. For lists rank ordered by the probability of hospitalization, precision increased from 33% to 56% to 100% for positions 1 to 80, 1 to 25, and 1 to 10 in the OOS-P cohort and from 50% to 60% to 80% for positions 1 to 18, 1 to 10, and 1 to 5 in the OOS-F cohort, respectively. CONCLUSIONS: The proposed LSTM model for predicting 180-day DKA-related hospitalization was valid in this sample. Future research should evaluate model validity in multiple populations and settings to account for health inequities that may be present in different segments of the population (eg, racially or socioeconomically diverse cohorts). Rank ordering youth by probability of DKA-related hospitalization will allow clinics to identify the most at-risk youth. The clinical implication of this is that clinics may then create and evaluate novel preventive interventions based on available resources.

Gender diversity in adolescents with polycystic ovary syndrome.

OBJECTIVES: The objective of our study was to describe the prevalence of gender diverse (GD) youth  among adolescents with polycystic ovary syndrome (PCOS). METHODS: We conducted a retrospective chart review on patients who met NIH criteria for PCOS in our Multidisciplinary Adolescent PCOS Program (MAPP). We compared those with PCOS to MAPP patients who did not meet PCOS criteria as well as to non-PCOS patients from the Adolescent Specialty Clinic (ASC). Variables analyzed included gender identity, androgen levels, hirsutism scores, and mood disorders. We used chi-square, Fisher's exact, t-tests, and Wilcoxon rank sum tests to compare groups.  Gender identities self-reported as male, fluid/both or nonbinary  were pooled into the GD category. RESULTS: Within the MAPP, 7.6% (n=12) of PCOS youth self-identified as GD compared to 1.8% (n=3) of non PCOS youth (p=0.01, chi-square). When compared to non-PCOS GD adolescents from ASC (4.4%; n=3), the difference to PCOS youth was no longer significant (p=0.56). Among MAPP patients, gender diversity was associated with higher hirsutism scores (p<0.01), but not higher androgen levels. In PCOS, depression/anxiety was higher in GD vs cisgender youth (100% vs. 37.6%, p<0.01 and 77.8% vs. 35.8%, p=0.03 respectively). CONCLUSIONS: Gender diversity was observed more commonly in those meeting PCOS criteria. PCOS GD youth were more hirsute and reported more depression/anxiety. Routine screening for differences in gender identity in comprehensive adolescent PCOS programs could benefit these patients, as alternate treatment approaches may be desired to support a transmasculine identity.