Health Care Analytics With Time-Invariant and Time-Variant Feature Importance to Predict Hospital-Acquired Acute Kidney Injury: Observational Longitudinal Study.

BACKGROUND: Acute kidney injury (AKI) develops in 4% of hospitalized patients and is a marker of clinical deterioration and nephrotoxicity. AKI onset is highly variable in hospitals, which makes it difficult to time biomarker assessment in all patients for preemptive care. OBJECTIVE: The study sought to apply machine learning techniques to electronic health records and predict hospital-acquired AKI by a 48-hour lead time, with the aim to create an AKI surveillance algorithm that is deployable in real time. METHODS: The data were sourced from 20,732 case admissions in 16,288 patients over 1 year in our institution. We enhanced the bidirectional recurrent neural network model with a novel time-invariant and time-variant aggregated module to capture important clinical features temporal to AKI in every patient. Time-series features included laboratory parameters that preceded a 48-hour prediction window before AKI onset; the latter's corresponding reference was the final in-hospital serum creatinine performed in case admissions without AKI episodes. RESULTS: The cohort was of mean age 53 (SD 25) years, of whom 29%, 12%, 12%, and 53% had diabetes, ischemic heart disease, cancers, and baseline eGFR <90 mL/min/1.73 m2, respectively. There were 911 AKI episodes in 869 patients. We derived and validated an algorithm in the testing dataset with an AUROC of 0.81 (0.78-0.85) for predicting AKI. At a 15% prediction threshold, our model generated 699 AKI alerts with 2 false positives for every true AKI and predicted 26% of AKIs. A lowered 5% prediction threshold improved the recall to 60% but generated 3746 AKI alerts with 6 false positives for every true AKI. Representative interpretation results produced by our model alluded to the top-ranked features that predicted AKI that could be categorized in association with sepsis, acute coronary syndrome, nephrotoxicity, or multiorgan injury, specific to every case at risk. CONCLUSIONS: We generated an accurate algorithm from electronic health records through machine learning that predicted AKI by a lead time of at least 48 hours. The prediction threshold could be adjusted during deployment to optimize recall and minimize alert fatigue, while its precision could potentially be augmented by targeted AKI biomarker assessment in the high-risk cohort identified.

Particulate matter 2.5 regulates lipid synthesis and inflammatory cytokine production in human SZ95 sebocytes.

A large body of evidence indicates that particulate matter (PM)2.5 is associated with various negative effects on human health. However, the impact and molecular mechanism of PM2.5 on the skin have not been elucidated. Therefore, the present study aimed to investigate the effects of two types of PM2.5 [water-soluble extracts (W-PM2.5) and non-water-soluble extracts (NW-PM2.5)] on cell proliferation, cell cycle progression, lipid synthesis, and inflammatory cytokine production of human SZ95 sebocytes. The results demonstrated that NW-PM2.5 and W-PM2.5 exposure dose-dependently inhibited SZ95 sebocyte proliferation by inducing G1 cell arrest. Furthermore, NW-PM2.5 and W-PM2.5 significantly reduced sebaceous lipid synthesis and markedly promoted the production of inflammatory cytokines, including interleukin-1α (IL-1α), IL-6 and IL-8 in SZ95 sebocytes. Additionally, the expression of aryl hydrocarbon (Ah) receptor (AhR), AhR nuclear translocator protein (ARNT), as well as cytochrome P450 1A1 were significantly increased following PM2.5 exposure. Thus, these findings indicate that PM2.5 exerts inhibitory effects on cell proliferation and lipid synthesis, and stimulatory effects on inflammatory cytokine production and AhR signaling activation in human SZ95 sebocytes.

A novel truncating mutation of PTCH1 in a Chinese family with Gorlin syndrome.

Gorlin syndrome, a rare autosomal dominant disease, is characterized by numerous basal cell carcinomas, multiple jaw cysts, palmar and plantar pits and embryological deformities. Mutations in the PTCH1 gene are the most common molecular defects associated with Gorlin syndrome. We detected a duplication of thymine after nucleotide position 2927 in exon 18 of the PTCH1 gene (c.2927 dupT) in a fifty-year-old male proband with peri-anal basal cell carcinoma and his brother. The mutation creates a frameshift and leads to a premature stop codon (p.Tyr977 Leufs* 16) lacking 5 of the 12 transmembrane-spanning domains. However, the functional significance of truncation of the N terminal regions remains currently unknown and to be further investigated. The current findings indicate that genetic testing of PTCH1 gene mutational status may aid in the early diagnosis of Gorlin syndrome in which multiple complex abnormalities are present, hampering prompt diagnosis and treatment.