Machine Learning of Plasma Proteomics Classifies Diagnosis of Interstitial Lung Disease.

Rationale: Distinguishing connective tissue disease-associated interstitial lung disease (CTD-ILD) from idiopathic pulmonary fibrosis (IPF) can be clinically challenging. Objectives: To identify proteins that separate and classify patients with CTD-ILD and those with IPF. Methods: Four registries with 1,247 patients with IPF and 352 patients with CTD-ILD were included in analyses. Plasma samples were subjected to high-throughput proteomics assays. Protein features were prioritized using recursive feature elimination to construct a proteomic classifier. Multiple machine learning models, including support vector machine, LASSO (least absolute shrinkage and selection operator) regression, random forest, and imbalanced Random Forest, were trained and tested in independent cohorts. The validated models were used to classify each case iteratively in external datasets. Measurements and Main Results: A classifier with 37 proteins (proteomic classifier 37 [PC37]) was enriched in the biological process of bronchiole development and smooth muscle proliferation and immune responses. Four machine learning models used PC37 with sex and age score to generate continuous classification values. Receiver operating characteristic curve analyses of these scores demonstrated consistent areas under the curve of 0.85-0.90 in the test cohort and 0.94-0.96 in the single-sample dataset. Binary classification demonstrated 78.6-80.4% sensitivity and 76-84.4% specificity in the test cohort and 93.5-96.1% sensitivity and 69.5-77.6% specificity in the single-sample classification dataset. Composite analysis of all machine learning models confirmed 78.2% (194 of 248) accuracy in the test cohort and 82.9% (208 of 251) in the single-sample classification dataset. Conclusions: Multiple machine learning models trained with large cohort proteomic datasets consistently distinguished CTD-ILD from IPF. Many of the identified proteins are involved in immune pathways. We further developed a novel approach for single-sample classification, which could facilitate honing the differential diagnosis of ILD in challenging cases and improve clinical decision making.

Development and initial validation of a disease-specific instrument to measure health-related quality of life in hypersensitivity pneumonitis.

Rationale and objective: Disease-specific health-related quality of life (HRQOL) instruments enable us to capture domains that are most relevant to specific patient populations and are useful when a more individualised approach to patient assessment is desired. In this study, we assessed the validity and reliability of the first instrument specifically developed to measure HRQOL in hypersensitivity pneumonitis (HP). Methods: A 39-item HP-HRQOL instrument and several anchors were collected from a cohort of patients with HP. Exploratory factor analysis and item reduction were utilised to construct a shortened version of the instrument. Several validity and reliability analyses were conducted on this version of the HP-HRQOL. Measurements and main results: 59 patients with HP completed the study. The revised HP-HRQOL instrument comprises 15 items composing two factors (domains): 1) impacts on daily life; and 2) mental wellbeing. Internal consistency reliability was strong for Factor 1 (Cronbach's α=0.94, 95% CI 0.92-0.96) and Factor 2 (Cronbach's α=0.89, 95% CI 0.85-0.94). Test-retest reliability was strong (ICC 0.94, 95% CI 0.89-0.97). The HP-HRQOL strongly correlated with other validated patient-reported outcome measures and moderately correlated with % predicted forced vital capacity. The HP-HRQOL distinguished between those with different severities of HP as determined by lung function and supplemental oxygen use. Conclusions: The HP-HRQOL, the first patient-reported outcome instrument specific to adults with HP, possesses strong validity and reliability characteristics for measuring disease-specific HRQOL and distinguishes among patients with different severities of disease.

Solid-State Fluorescent Selenium Quantum Dots by a Solvothermal-Assisted Sol-Gel Route for Curcumin Sensing.

Toward the need for solid-state fluorescent quantum dots, resistant to self-quenching, we describe a solvothermal-assisted sol-gel method to synthesize Se quantum dots. Morphological and crystalline characterizations reveal that Se quantum dots (average size 3-8 nm) have a trigonal crystal structure. The presence of planar defects (dislocations, stacking faults, twins, and grain boundaries) suggests formation of Se nanocrystallites through aggregation-based crystal growth mechanisms. Under ultraviolet excitation, the quantum dots exhibit an excitation wavelength-dependent solid-state blue emission with an average lifetime of 1.96 ns. Depending on fluorescence quenching by curcumin, selenium quantum dots act as ideal candidates for inner filter effect-based curcumin sensing.

Early postnatal iron repletion overcomes lasting effects of gestational iron deficiency in rats.

Iron deficiency anemia in early childhood causes developmental delays and, very likely, irreversible alterations in neurological functioning. One primary goal for the present study was to determine whether the effects of late gestational iron deficiency on brain monoamine metabolism, iron content, and behavioral phenotypes could be repaired with iron intervention in early lactation. Young pregnant rats were provided iron-deficient or control diets from mid-gestation (G15). At postnatal d 4 (P4), pups from iron-deficient dams were out-fostered either to other ID dams or control dams while pups of control dams were similarly fostered to other control dams. Dietary treatments continued to adulthood (P65) when brain iron and regional monoamines were evaluated. P4 iron repletion normalized body iron status, brain iron concentrations, monoamine concentrations, and monoamine transporter and receptor densities in most brain regions. Dopamine transporter densities in caudate and substantia nigra were lower in ID rats but were normalized with iron repletion. Serotonin transporter levels in most brain regions and open-field exploration were also normalized with iron repletion. The success of this approach of early postnatal iron intervention following iron deficiency in utero contrasts to a relative lack of success when the intervention is performed at weaning. These data suggest that a window of opportunity exists for reversing the detrimental effects of iron deficiency in utero in rats and provides strong support of intervention approaches in humans with iron deficiency during pregnancy.

Early iron deficiency alters sensorimotor development and brain monoamines in rats.

Iron deficiency in human infancy reportedly leads to developmental delays and changes in neurobiology that may be irreversible. Using a rodent model, the present study examined whether dietary iron deficiency late in pregnancy and during lactation alters sensorimotor development and brain monoaminergic systems. Rats were assigned to 1 of 4 dietary treatments during gestation and lactation: 1) iron sufficient control; 2) prenatal iron deficiency beginning on gestational d 15 (G15); 3) postnatal iron deficiency beginning on postnatal d 4 (P4); 4) iron deficiency beginning on G15 followed by an iron sufficient diet on P4. Developmental milestones, open field behavior, brain iron and proteins, monoamines, and their transporters were evaluated between P6 and P21. Only G15 iron deficient rats had greater dopaminergic activity than controls as indicated by increased tyrosine hydroxylase levels, phosphorylated tyrosine hydroxylase levels, and cellular dopamine in prefrontal cortex and striatum at P15. These rats also showed delayed eye opening, ear development, and reduced locomotor activity. Iron repletion at P4 returned most measures to control levels by the time of weaning. Postnatal iron deficiency reduced striatal and ventral midbrain iron as well as cellular dopamine levels in prefrontal cortex and striatum at P21. Developmental delays in ear development and achievement in bar holding and surface righting also resulted from postnatal iron deficiency. These results indicate that iron deficiency begun at G15 affects early dopamine neurobiology, the development of specific developmental milestones, and behavior in preweaned rats.