ARCH: Large-scale Knowledge Graph via Aggregated Narrative Codified Health Records Analysis.

Objective: Electronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes, covering hundreds of thousands of clinical concepts available for research and clinical care. The complex, massive, heterogeneous, and noisy nature of EHR data imposes significant challenges for feature representation, information extraction, and uncertainty quantification. To address these challenges, we proposed an efficient Aggregated naRrative Codified Health (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features. Methods: The ARCH algorithm first derives embedding vectors from a co-occurrence matrix of all EHR concepts and then generates cosine similarities along with associated p-values to measure the strength of relatedness between clinical features with statistical certainty quantification. In the final step, ARCH performs a sparse embedding regression to remove indirect linkage between entity pairs. We validated the clinical utility of the ARCH knowledge graph, generated from 12.5 million patients in the Veterans Affairs (VA) healthcare system, through downstream tasks including detecting known relationships between entity pairs, predicting drug side effects, disease phenotyping, as well as sub-typing Alzheimer's disease patients. Results: ARCH produces high-quality clinical embeddings and KG for over 60,000 EHR concepts, as visualized in the R-shiny powered web-API (https://celehs.hms.harvard.edu/ARCH/). The ARCH embeddings attained an average area under the ROC curve (AUC) of 0.926 and 0.861 for detecting pairs of similar EHR concepts when the concepts are mapped to codified data and to NLP data; and 0.810 (codified) and 0.843 (NLP) for detecting related pairs. Based on the p-values computed by ARCH, the sensitivity of detecting similar and related entity pairs are 0.906 and 0.888 under false discovery rate (FDR) control of 5%. For detecting drug side effects, the cosine similarity based on the ARCH semantic representations achieved an AUC of 0.723 while the AUC improved to 0.826 after few-shot training via minimizing the loss function on the training data set. Incorporating NLP data substantially improved the ability to detect side effects in the EHR. For example, based on unsupervised ARCH embeddings, the power of detecting drug-side effects pairs when using codified data only was 0.15, much lower than the power of 0.51 when using both codified and NLP concepts. Compared to existing large-scale representation learning methods including PubmedBERT, BioBERT and SAPBERT, ARCH attains the most robust performance and substantially higher accuracy in detecting these relationships. Incorporating ARCH selected features in weakly supervised phenotyping algorithms can improve the robustness of algorithm performance, especially for diseases that benefit from NLP features as supporting evidence. For example, the phenotyping algorithm for depression attained an AUC of 0.927 when using ARCH selected features but only 0.857 when using codified features selected via the KESER network[1]. In addition, embeddings and knowledge graphs generated from the ARCH network were able to cluster AD patients into two subgroups, where the fast progression subgroup had a much higher mortality rate. Conclusions: The proposed ARCH algorithm generates large-scale high-quality semantic representations and knowledge graph for both codified and NLP EHR features, useful for a wide range of predictive modeling tasks.

Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization.

OBJECTIVE: The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems. METHODS: The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems. RESULTS: With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks. CONCLUSIONS: The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.

[Relationship between ectasia of the rete testis and the volume of seminal vesicle cyst in the epididymal head: an ultrasonographic study].

OBJECTIVE: To explore the correlation between ectasia of the rete testis (ERT) and the volume of seminal vesicle cyst (SVC) in the epididymal head by ultrasonography. METHODS: This study included 36 cases of ERT diagnosed by color Doppler ultrasonography and complicated with SVC in the epididymal head (case group), and another 44 SVC cases without ERT (control group), all confirmed by surgery or fine-needle aspiration. We analyzed the differences in nationality, age, volume of SVC and resistance index of the afferent artery in the diseased testis between the two groups of patients. RESULTS: No statistically significant differences were observed between Chinese Uighurs and Hans (P > 0.05), nor in the mean age between the two groups of patients (P > 0.05). There were significant differences in the mean volume of SVC between the case and control groups ([2.081 +/- 1.147] cm3 vs [1.009 +/- 0.848 ] cm3, P < 0.01), but not in the resistance index of the afferent artery in the diseased testis (0.644 +/- 0.099 vs 0.608 +/- 0.116, P > 0.05). CONCLUSION: The volume of seminal vesicle cyst in the epididymal head plays a significant role in the formation of ectasia of the rete testis.

[Experimental study on antioxidant and calcium channel blockade preventing testicular fibrosis in rats].

OBJECTIVE: To investigate the preventive effect of antioxidant and calcium channel blockade on testicular fibrosis in rats, and to explore the ideal drug for preventing it. METHODS: Eighty Wistar rats were divided into a control group (Group A, n = 10), a treatment group (Group B, n = 57) and a testicular fibrosis model group (Group C, n = 13). And the treatment group was further divided into a higher dosage group (Group a, n = 20), a medium dosage group (Group b, n =20) and a lower dosage group (Group c, n = 17). Testicular fibrosis was duplicated with altered Wang Tao's method. From the second day of the first immunization, the higher dosage group was given antioxidant vitamins 90 mg/(kg x d) and verapamil 50 mg/(kg x d), the medium dosage group antioxidant vitamins 90 mg/(kg x d) and verapamil 25 mg/(kg x d), and the lower dosage group antioxidant vitamins 90 mg/(kg x d) and verapamil 12.5 mg/(kg x d), all for 150 days. The control and the model groups received no treatment. The sperm count, sperm deformity rate, testis length and seminiferous tubule intradiameter were measured, and the changes of the testis interstitial substance and spermatogenic cells were observed by light microscope and transmission electron microscope. RESULTS: Testicular fibrosis was significantly prevented by the higher- and medium-dosage treatment in the rats. In the higher dosage group, the intradiameter of the seminiferous tubules and the thickness of the limiting membrane were almost the same as in the control. In the lower dosage group the thickness of the limiting membrane was thicker and the damage to the spermatogenic cells was heavier than in the control, but the pathological changes of the testis structure was lighter than in the model group, in which Hyperplasia and fibroblast increase in the interstitial substance were significant, interstitial mast cells and peritubular mast cells increased, the thickness of the limiting membrane of the seminiferous tubules seriously thickened, and the damage to the spermatogenic cells was severe. CONCLUSION: Testicular fibrosis in rats can be significantly prevented by antioxidant and calcium channel blockade.