Machine Learning Approach with Harmonized Multinational Datasets for Enhanced Prediction of Hypothyroidism in Patients with Type 2 Diabetes.

Type 2 diabetes (T2D) is a global health concern with increasing prevalence. Comorbid hypothyroidism (HT) exacerbates kidney, cardiac, neurological and other complications of T2D; these risks can be mitigated pharmacologically upon detecting HT. The current HT standard of care (SOC) screening in T2D is infrequent, delaying HT diagnosis and treatment. We present a first-to-date machine learning algorithm (MLA) clinical decision tool to classify patients as low vs. high risk for developing HT comorbid with T2D; the MLA was developed using readily available patient data from harmonized multinational datasets. The MLA was trained on data from NIH All of US (AoU) and UK Biobank (UKBB) (Combined dataset) and achieved a high negative predictive value (NPV) of 0.989 and an AUROC of 0.762 in the Combined dataset, exceeding AUROCs for the models trained on AoU or UKBB alone (0.666 and 0.622, respectively), indicating that increasing dataset diversity for MLA training improves performance. This high-NPV automated tool can supplement SOC screening and rule out T2D patients with low HT risk, allowing for the prioritization of lab-based testing for at-risk patients. Conversely, an MLA output that designates a patient to be at risk of developing HT allows for tailored clinical management and thereby promotes improved patient outcomes.

Family-Centric Applied Behavior Analysis Facilitates Improved Treatment Utilization and Outcomes.

Background/Objective: Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by lifelong impacts on functional social and daily living skills, and restricted, repetitive behaviors (RRBs). Applied behavior analysis (ABA), the gold-standard treatment for ASD, has been extensively validated. ABA access is hindered by limited availability of qualified professionals and logistical and financial barriers. Scientifically validated, parent-led ABA can fill the accessibility gap by overcoming treatment barriers. This retrospective cohort study examines how our ABA treatment model, utilizing parent behavior technicians (pBTs) to deliver ABA, impacts adaptive behaviors and interfering behaviors (IBs) in a cohort of children on the autism spectrum with varying ASD severity levels, and with or without clinically significant IBs. Methods: Clinical outcomes of 36 patients ages 3-15 years were assessed using longitudinal changes in Vineland-3 after 3+ months of pBT-delivered ABA treatment. Results: Within the pBT model, our patients demonstrated clinically significant improvements in Vineland-3 Composite, domain, and subdomain scores, and utilization was higher in severe ASD. pBTs utilized more prescribed ABA when children initiated treatment with clinically significant IBs, and these children also showed greater gains in their Composite scores. Study limitations include sample size, inter-rater reliability, potential assessment metric bias and schedule variability, and confounding intrinsic or extrinsic factors. Conclusion: Overall, our pBT model facilitated high treatment utilization and showed robust effectiveness, achieving improved adaptive behaviors and reduced IBs when compared to conventional ABA delivery. The pBT model is a strong contender to fill the widening treatment accessibility gap and represents a powerful tool for addressing systemic problems in ABA treatment delivery.

Increased plasma lipopolysaccharide-binding protein and altered inflammatory mediators in overweight women suggest a state of subclinical endotoxemia.

Chronic low-grade inflammation has been recognized as an underlying event linking obesity to cardiovascular disease (CVD). However, inflammatory alterations in individuals who are overweight remain understudied. To provide insight, we determined the levels of key circulating biomarkers of endotoxemia and inflammation, including lipopolysaccharide-binding protein (LBP), CRP, IL-6, leptin, and adiponectin in adult female subjects (n = 20) who were lean or overweight and had high cholesterol and/or high blood pressure - two important conventional risk factors for CVD. Plasma levels of LBP (a recognized marker of metabolic endotoxemia in obesity) were significantly higher in the overweight group compared with the lean group (P = 0.005). The levels of CRP, a general marker of inflammation, were also significantly higher in overweight subjects (P = 0.01), as were IL-6 (P = 0.02) and leptin (P = 0.002), pro-inflammatory mediators associated with cardiovascular risk. Levels of adiponectin, an adipokine with anti-inflammatory and anti-atherogenic functions, were significantly lower in the overweight group (P = 0.002). The leptin/adiponectin ratio, a preferential atherogenic marker was significantly increased in women who are overweight (P = 0.02). LBP, CRP, leptin, and adiponectin levels significantly correlated with BMI, but not with age. These results reveal the presence of subclinical endotoxemia and a pro-inflammatory state in overweight women and are of interest for further studies with the goal for improved understanding of women's cardiovascular health.

Antigen-presenting aged neutrophils induce CD4+ T cells to exacerbate inflammation in sepsis.

Extracellular cold-inducible RNA-binding protein (eCIRP) is a key mediator of severity and mortality in sepsis. We found that stimulation of mouse bone marrow-derived neutrophils (BMDNs) with eCIRP generated a distinct neutrophil subpopulation, characterized by cell surface markers of both antigen-presenting cells and aged neutrophils as well as expression of IL-12, which we named antigen-presenting aged neutrophils (APANs). The frequency of APANs was significantly increased in the blood, spleen, and lungs of WT mice subjected to cecal ligation and puncture-induced sepsis but not in CIRP-/- mice. Patients with sepsis had a significant increase in circulating APAN counts compared with healthy individuals. Compared with non-APAN-transfered mice, APAN-transferred septic mice had increased serum levels of injury and inflammatory markers, exacerbated acute lung injury (ALI), and worsened survival. APANs and CD4+ T cells colocalized in the spleen, suggesting an immune interaction between these cells. APANs cocultured with CD4+ T cells significantly induced the release of IFN-γ via IL-12. BMDNs stimulated with eCIRP and IFN-γ underwent hyper-NETosis. Stimulating human peripheral blood neutrophils with eCIRP also induced APANs, and stimulating human neutrophils with eCIRP and IFN-γ caused hyper-NETosis. Thus, eCIRP released during sepsis induced APANs to aggravate ALI and worsen the survival of septic animals via CD4+ T cell activation, Th1 polarization, and IFN-γ-mediated hyper-NETosis.

Increased plasma lipopolysaccharide-binding protein and altered inflammatory mediators in overweight women suggest a state of subclinical endotoxemia.

Chronic low-grade inflammation has been recognized as an underlying event linking obesity to cardiovascular disease (CVD). However, inflammatory alterations in individuals who are overweight remain understudied. To provide insight, we determined the levels of key circulating biomarkers of endotoxemia and inflammation, including lipopolysaccharide-binding protein (LBP), CRP, IL-6, leptin, and adiponectin in adult female subjects (n=40) who were lean or overweight and had high cholesterol and/or high blood pressure - two important conventional risk factors for CVD. Plasma levels of LBP were significantly higher in the overweight group compared with the lean group (P=0.005). The levels of CRP were also significantly higher in overweight subjects (P=0.01), as were IL-6 (P=0.02) and leptin (P=0.002), pro-inflammatory mediators associated with cardiovascular risk. Levels of adiponectin, an adipokine with anti-inflammatory and anti-atherogenic functions, were significantly lower in the overweight group (P=0.002). The leptin/adiponectin ratio, a preferential atherogenic marker was significantly increased in women who are overweight (P=0.02). LBP, CRP, leptin, and adiponectin levels significantly correlated with BMI, but not with age and there was a significant correlation between LBP and IL-6 levels. These results reveal the presence of subclinical endotoxemia and a pro-inflammatory state in overweight women and are of interest for further studies with the goal for improved understanding of cardiovascular health risks in women.

Machine Learning Approach for Improved Longitudinal Prediction of Progression from Mild Cognitive Impairment to Alzheimer's Disease.

Mild cognitive impairment (MCI) is cognitive decline that can indicate future risk of Alzheimer's disease (AD). We developed and validated a machine learning algorithm (MLA), based on a gradient-boosted tree ensemble method, to analyze phenotypic data for individuals 55-88 years old (n = 493) diagnosed with MCI. Data were analyzed within multiple prediction windows and averaged to predict progression to AD within 24-48 months. The MLA outperformed the mini-mental state examination (MMSE) and three comparison models at all prediction windows on most metrics. Exceptions include sensitivity at 18 months (MLA and MMSE each achieved 0.600); and sensitivity at 30 and 42 months (MMSE marginally better). For all prediction windows, the MLA achieved AUROC ≥ 0.857 and NPV ≥ 0.800. With averaged data for the 24-48-month lookahead timeframe, the MLA outperformed MMSE on all metrics. This study demonstrates that machine learning may provide a more accurate risk assessment than the standard of care. This may facilitate care coordination, decrease healthcare expenditures, and maintain quality of life for patients at risk of progressing from MCI to AD.

Single-cell analysis of menstrual endometrial tissues defines phenotypes associated with endometriosis.

BACKGROUND: Endometriosis is a common, complex disorder which is underrecognized and subject to prolonged delays in diagnosis. It is accompanied by significant changes in the eutopic endometrial lining. METHODS: We have undertaken the first single-cell RNA-sequencing (scRNA-Seq) comparison of endometrial tissues in freshly collected menstrual effluent (ME) from 33 subjects, including confirmed endometriosis patients (cases) and controls as well as symptomatic subjects (who have chronic symptoms suggestive of endometriosis but have not been diagnosed). RESULTS: We identify a unique subcluster of proliferating uterine natural killer (uNK) cells in ME-tissues from controls that is almost absent from endometriosis cases, along with a striking reduction of total uNK cells in the ME of cases (p < 10-16). In addition, an IGFBP1+ decidualized subset of endometrial stromal cells are abundant in the shed endometrium of controls when compared to cases (p < 10-16) confirming findings of compromised decidualization of cultured stromal cells from cases. By contrast, endometrial stromal cells from cases are enriched in cells expressing pro-inflammatory and senescent phenotypes. An enrichment of B cells in the cases (p = 5.8 × 10-6) raises the possibility that some may have chronic endometritis, a disorder which predisposes to endometriosis. CONCLUSIONS: We propose that characterization of endometrial tissues in ME will provide an effective screening tool for identifying endometriosis in patients with chronic symptoms suggestive of this disorder. This constitutes a major advance, since delayed diagnosis for many years is a major clinical problem in the evaluation of these patients. Comprehensive analysis of ME is expected to lead to new diagnostic and therapeutic approaches to endometriosis and other associated reproductive disorders such as female infertility.

Specification of fetal liver endothelial progenitors to functional zonated adult sinusoids requires c-Maf induction.

The liver vascular network is patterned by sinusoidal and hepatocyte co-zonation. How intra-liver vessels acquire their hierarchical specialized functions is unknown. We study heterogeneity of hepatic vascular cells during mouse development through functional and single-cell RNA-sequencing. The acquisition of sinusoidal endothelial cell identity is initiated during early development and completed postnatally, originating from a pool of undifferentiated vascular progenitors at E12. The peri-natal induction of the transcription factor c-Maf is a critical switch for the sinusoidal identity determination. Endothelium-restricted deletion of c-Maf disrupts liver sinusoidal development, aberrantly expands postnatal liver hematopoiesis, promotes excessive postnatal sinusoidal proliferation, and aggravates liver pro-fibrotic sensitivity to chemical insult. Enforced c-Maf overexpression in generic human endothelial cells switches on a liver sinusoidal transcriptional program that maintains hepatocyte function. c-Maf represents an inducible intra-organotypic and niche-responsive molecular determinant of hepatic sinusoidal cell identity and lays the foundation for the strategies for vasculature-driven liver repair.

Morphological characterization of Etv2 vascular explants using fractal analysis and atomic force microscopy.

The rapid engraftment of vascular networks is critical for functional incorporation of tissue explants. However, existing methods for inducing angiogenesis utilize approaches that yield vasculature with poor temporal stability or inadequate mechanical integrity, which reduce their robustness in vivo. The transcription factor Ets variant 2 (Etv2) specifies embryonic hematopoietic and vascular endothelial cell (EC) development, and is transiently reactivated during postnatal vascular regeneration and tumor angiogenesis. This study investigates the role for Etv2 upregulation in forming stable vascular beds both in vitro and in vivo. Control and Etv2+ prototypical fetal-derived human umbilical vein ECs (HUVECs) and adult ECs were angiogenically grown into vascular beds. These vessel beds were characterized using fractal dimension and lacunarity, to quantify their branching complexity and space-filling homogeneity, respectively. Atomic force microscopy (AFM) was used to explore whether greater complexity and homogeneity lead to more mechanically stable vessels. Additionally, markers of EC integrity were used to probe for mechanistic clues. Etv2+ HUVECs exhibit greater branching, vessel density, and structural homogeneity, and decreased stiffness in vitro and in vivo, indicating a greater propensity for stable vessel formation. When co-cultured with colon tumor organoid tissue, Etv2+ HUVECs had decreased fractal dimension and lacunarity compared to Etv2+ HUVECs cultured alone, indicating that vessel density and homogeneity of vessel spacing increased due to the presence of Etv2. This study sets forth the novel concept that fractal dimension, lacunarity, and AFM are as informative as conventional angiogenic measurements, including vessel branching and density, to assess vascular perfusion and stability.

Greater effect of polygenic risk score for Alzheimer's disease among younger cases who are apolipoprotein E-ε4 carriers.

To evaluate how age and apolipoprotein E-ε4 (APOE4) status interact with APOE-independent polygenic risk score (PRSnon-APOE), we estimated PRSnon-APOE in superagers (age ≥ 90 years, N = 346), 89- controls (age 60-89, N = 2930), and Alzheimer's disease (AD) cases (N = 1760). Using superagers, we see a nearly 5 times greater odds ratio (OR) for AD comparing the top PRSnon-APOE decile to the lowest decile (OR = 4.82, p = 2.5 × 10-6), which is twice the OR as using 89- controls (OR = 2.38, p = 4.6 × 10-9). Thus PRSnon-APOE is correlated with age, which in turn is associated with APOE. Further exploring these relationships, we find that PRSnon-APOE modifies age at onset among APOE4 carriers, but not among noncarriers. More specifically, PRSnon-APOE in the top decile predicts an age at onset 5 years earlier compared with the lowest decile (70.1 vs. 75.0 years; t-test p = 2.4 × 10-5) among APOE4 carriers. This disproportionally large PRSnon-APOE among younger APOE4-positive cases is reflected in a significant statistical interaction between APOE4 status and age at onset (ß = -0.02, p = 4.8 × 10-3) as a predictor of PRSnon-APOE. Thus, the known AD risk variants are particularly detrimental in young APOE4 carriers.

Empirical design of a variant quality control pipeline for whole genome sequencing data using replicate discordance.

The success of next-generation sequencing depends on the accuracy of variant calls. Few objective protocols exist for QC following variant calling from whole genome sequencing (WGS) data. After applying QC filtering based on Genome Analysis Tool Kit (GATK) best practices, we used genotype discordance of eight samples that were sequenced twice each to evaluate the proportion of potentially inaccurate variant calls. We designed a QC pipeline involving hard filters to improve replicate genotype concordance, which indicates improved accuracy of genotype calls. Our pipeline analyzes the efficacy of each filtering step. We initially applied this strategy to well-characterized variants from the ClinVar database, and subsequently to the full WGS dataset. The genome-wide biallelic pipeline removed 82.11% of discordant and 14.89% of concordant genotypes, and improved the concordance rate from 98.53% to 99.69%. The variant-level read depth filter most improved the genome-wide biallelic concordance rate. We also adapted this pipeline for triallelic sites, given the increasing proportion of multiallelic sites as sample sizes increase. For triallelic sites containing only SNVs, the concordance rate improved from 97.68% to 99.80%. Our QC pipeline removes many potentially false positive calls that pass in GATK, and may inform future WGS studies prior to variant effect analysis.