RegEMR: a natural language processing system to automatically identify premature ovarian decline from Chinese electronic medical records.

BACKGROUND: The ovarian reserve is a reservoir for reproductive potential. In clinical practice, early detection and treatment of premature ovarian decline characterized by abnormal ovarian reserve tests is regarded as a critical measure to prevent infertility. However, the relevant data are typically stored in an unstructured format in a hospital's electronic medical record (EMR) system, and their retrieval requires tedious manual abstraction by domain experts. Computational tools are therefore needed to reduce the workload. METHODS: We presented RegEMR, an artificial intelligence tool composed of a rule-based natural language processing (NLP) extractor and a knowledge-based disease scoring model, to automatize the screening procedure of premature ovarian decline using Chinese reproductive EMRs. We used regular expressions (REs) as a text mining method and explored whether REs automatically synthesized by the genetic programming-based online platform RegexGenerator + + could be as effective as manually formulated REs. We also investigated how the representativeness of the learning corpus affected the performance of machine-generated REs. Additionally, we translated the clinical diagnostic criteria into a programmable disease diagnostic model for disease scoring and risk stratification. Four hundred outpatient medical records were collected from a Chinese fertility center. Manual review served as the gold standard, and fivefold cross-validation was used for evaluation. RESULTS: The overall F-score of manually built REs was 0.9444 (95% CI 0.9373 to 0.9515), with no significant difference (paired t test p > 0.05) compared with machine-generated REs that could be affected by training set sizes and annotation portions. The extractor performed effectively in automatically tracing the dynamic changes in hormone levels (F-score 0.9518-0.9884) and ultrasonographic measures (F-score 0.9472-0.9822). Applying the extracted information to the proposed diagnostic model, the program obtained an accuracy of 0.98 and a sensitivity of 0.93 in risk screening. For each specific disease, the automatic diagnosis in 76% of patients was consistent with that of the clinical diagnosis, and the kappa coefficient was 0.63. CONCLUSION: A Chinese NLP system named RegEMR was developed to automatically identify high risk of early ovarian aging and diagnose related diseases from Chinese reproductive EMRs. We hope that this system can aid EMR-based data collection and clinical decision support in fertility centers.

Biotransformation of Penindolone, an Influenza A Virus Inhibitor.

Penindolone (PND) is a novel broad-spectrum anti-Influenza A Virus (IAV) agent blocking hemagglutinin-mediated adsorption and membrane fusion. The goal of this work was to reveal the metabolic route of PND in rats. Ultra-high-performance liquid chromatography tandem high-resolution mass spectrometry (UHPLC-HRMS) was used for metabolite identification in rat bile, feces and urine after administration of PND. A total of 25 metabolites, including 9 phase I metabolites and 16 phase II metabolites, were characterized. The metabolic pathways were proposed, and metabolites were visualized via Global Natural Product Social Molecular Networking (GNPS). It was found that 65.24-80.44% of the PND presented in the formation of glucuronide conjugate products in bile, and more than 51% of prototype was excreted through feces. In in vitro metabolism of PND by rat, mouse and human liver microsomes (LMs) system, PND was discovered to be eliminated in LMs to different extents with significant species differences. The effects of chemical inhibitors of isozymes on the metabolism of PND in vitro indicated that CYP2E1/2C9/3A4 and UGT1A1/1A6/1A9 were the metabolic enzymes responsible for PND metabolism. PND metabolism in vivo could be blocked by UGTs inhibitor (ibrutinib) to a certain extent. These findings provided a basis for further research and development of PND.

Advanced oxidation protein products attenuate the autophagy-lysosome pathway in ovarian granulosa cells by modulating the ROS-dependent mTOR-TFEB pathway.

Oxidative stress dysfunction has recently been found to be involved in the pathogenesis of premature ovarian insufficiency (POI). Previously, we found that advanced oxidation protein products (AOPPs) in plasma were elevated in women with POI and had an adverse effect on granulosa cell proliferation. However, the mechanism underlying the effects of AOPPs on autophagy-lysosome pathway regulation in granulosa cells remains unclear. In this study, the effect of AOPPs on autophagy and lysosomal biogenesis and the underlying mechanisms were explored by a series of in vitro experiments in KGN and COV434 cell lines. AOPP-treated rat models were employed to determine the negative effect of AOPPs on the autophagy-lysosome systems in vivo. We found that increased AOPP levels activated the mammalian target of rapamycin (mTOR) pathway, and inhibited the autophagic response and lysosomal biogenesis in KGN and COV434 cells. Furthermore, scavenging of reactive oxygen species (ROS) with N-acetylcysteine and blockade of the mTOR pathway with rapamycin or via starvation alleviated the AOPP-induced inhibitory effects on autophagy and lysosomal biogenesis, suggesting that these effects of AOPPs are ROS-mTOR dependent. The protein expression and nuclear translocation of transcription factor EB (TFEB), the key regulator of lysosomal and autophagic function, were also impaired by the AOPP-activated ROS-mTOR pathway. In addition, TFEB overexpression attenuated the AOPP-induced impairment of autophagic flux and lysosomal biogenesis in KGN and COV434 cells. Chronic AOPP stimulation in vivo also impaired autophagy and lysosomal biogenesis in granulosa cells of rat ovaries. The results highlight that AOPPs lead to impairment of autophagic flux and lysosomal biogenesis via ROS-mTOR-TFEB signaling in granulosa cells and participate in the pathogenesis of POI.

Advanced Oxidation Protein Products Induce G1/G0-Phase Arrest in Ovarian Granulosa Cells via the ROS-JNK/p38 MAPK-p21 Pathway in Premature Ovarian Insufficiency.

The mechanism underlying the role of oxidative stress and advanced oxidation protein products (AOPPs) in the aetiology of premature ovarian insufficiency (POI) is poorly understood. Here, we investigated the plasma AOPP level in POI patients and the effects of AOPPs on granulosa cells both in vitro and in vivo. KGN cells were treated with different AOPP doses, and cell cycle distribution, intracellular reactive oxygen species (ROS), and protein expression levels were measured. Sprague-Dawley (SD) rats were treated daily with PBS, rat serum albumin, AOPP, or AOPP+ N-acetylcysteine (NAC) for 12 weeks to explore the effect of AOPPs on ovarian function. Plasma AOPP concentrations were significantly higher in both POI and biochemical POI patients than in controls and negatively correlated with anti-Müllerian hormone and the antral follicle count. KGN cells treated with AOPP exhibited G1/G0-phase arrest. AOPP induced G1/G0-phase arrest in KGN cells by activating the ROS-c-Jun N-terminal kinase (JNK)/p38 mitogen-activated protein kinase (MAPK)-p21 pathway. Pretreatment with NAC, SP600125, SB203580, and si-p21 blocked AOPP-induced G1/G0-phase arrest. In SD rats, AOPP treatment increased the proportion of atretic follicles, and NAC attenuated the adverse effects of AOPPs in the ovary. In conclusion, we provide mechanistic evidence that AOPPs may induce cell cycle arrest in granulosa cells via the ROS-JNK/p38 MAPK-p21 pathway and thus may be a novel biomarker of POI.