Medical Information Extraction With NLP-Powered QABots: A Real-World Scenario.

The advent of computerized medical recording systems in healthcare facilities has made data retrieval tasks easier, compared to manual recording. Nevertheless, the potential of the information contained within medical records remains largely untapped, mostly due to the time and effort required to extract data from unstructured documents. Natural Language Processing (NLP) represents a promising solution to this challenge, as it enables the use of automated text-mining tools for clinical practitioners. In this work, we present the architecture of the Virtual Dementia Institute (IVD), a consortium of sixteen Italian hospitals, using the NLP Extraction and Management Tool (NEMT), a (semi-) automated end-to-end pipeline that extracts relevant information from clinical documents and stores it in a centralized REDCap database. After defining a common Case Report Form (CRF) across the IVD hospitals, we implemented NEMT, the core of which is a Question Answering Bot (QABot) based on a modern NLP model. This QABot is fine-tuned on thousands of examples from IVD centers. Detailed descriptions of the process to define a common minimum dataset, Inter-Annotator Agreement calculated on clinical documents, and NEMT results are provided. The best QABot performance show an Exact Match score (EM) of 78.1%, a F1-score of 84.7%, a Lenient Accuracy (LAcc) of 0.834, and a Mean Reciprocal Rank (MRR) of 0.810. EM and F1 scores outperform the same metrics obtained with ChatGPTv3.5 (68.9% and 52.5%, respectively). With NEMT the IVD has been able to populate a database that will contain data from thousands of Italian patients, all screened with the same procedure. NEMT represents an efficient tool that paves the way for medical information extraction and exploitation for new research studies.

Characterization of novel progranulin gene variants in Italian patients with neurodegenerative diseases.

Loss-of-function mutations in the gene encoding for the protein progranulin (PGRN), GRN, are one of the major genetic abnormalities involved in frontotemporal lobar degeneration. However, genetic variations, mainly missense, in GRN have also been linked to other neurodegenerative diseases. We found 12 different pathogenic/likely pathogenic variants in 21 patients identified in a cohort of Italian patients affected by various neurodegenerative disorders. We detected the p.Thr272SerfsTer10 as the most frequent, followed by the c.1179+3A>G variant. We characterized the clinical phenotype of 12 patients from 3 pedigrees carrying the c.1179+3A>G variant, demonstrated the pathogenicity of this mutation, and detected other rarer variants causing haploinsufficiency (p.Met1?, c.709-2A>T, p.Gly79AspfsTer39). Finally, by applying bioinformatics, neuropathological, and biochemical studies, we characterized 6 missense/synonymous variants (p.Asp94His, p.Gly117Asp, p.Ala266Pro, p.Val279Val, p.Arg298His, p.Ala505Gly), including 4 previously unreported. The designation of variants is crucial for genetic counseling and the enrollment of patients in clinical studies.