Search NASA⌕ Search

Engineering topics

Shi, Xu

Publications and source records attributed to Shi, Xu.

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.

Zhou, Doudou↗

Controlled synthesis of hierarchical ZSM-5 for catalytic fast pyrolysis of cellulose to aromatics

Zeolite materials play a significant role throughout the oil refining and petrochemical industry. Microporous ZSM-5 has a high degree of crystallinity but low mass transfer, while hierarchical ZSM-5 shows a low degree of crystallinity as well as acidity. Here, we first report the synthesis of ZSM-5 with a new morphological structure, which has nanocrystalline ZSM-5 particles on the surface of an intact ZSM-5 zeolite. This not only improved the mass transfer in microporosity but also overcame disadvantages of hierarchical ZSM-5 including low degrees of crystallinity and acidity. This new and very efficient structure with both intracrystal microporosity and intercrystal macroporosity, formed by secondary crystallization after the intact ZSM-5 zeolite was synthesized, was verified by transmission electronic microscopy, N 2 adsorption and desorption, and X-ray diffraction. Lastly, the obtained ZSM-5 zeolite showed a uniform size (~200 nm), high crystallinity acidity, and a suitable hierarchical structure that exhibited excellent properties in the catalytic fast pyrolysis of cellulose to produce aromatics.

36 MATERIALS SCIENCE↗