ARGO 2.0: a Hybrid NLP/ML Framework for Diagnosis Standardization.

A relevant problem in medicine is the standardization of the diagnosis associated with a clinical case. Although diagnosis formulation is an intrinsically subjective and uncertain process, its standardization may take benefit from digital solutions automating the routines at the basis of such a decision. In this work, we propose ARGO 2.0: a framework for the development of decision support systems for diagnosis formulation. The framework can read free-text reports and store their clinically relevant information as personalized electronic Case Report Forms. A hybrid strategy, exploiting the synergy of Natural Language Processing and Machine Learning techniques, is used to automatically suggest a diagnosis in a standardized fashion. ARGO 2.0 has been designed to be template-independent and easily tailored to specific medical fields. We here demonstrate its feasibility in hemo lympho-pathology, by detailing its implementation, object of an ongoing validation campaign in a standing medical institute. ARGO 2.0 achieved an average Accuracy of 95.07%, an average precision of 94.85%, an average Recall of 96.31% and a F-Score of 95.32% onto the test set, outperforming both its embedded components, based on Natural Language Processing and Machine Learning.

Electronic case report forms generation from pathology reports by ARGO, automatic record generator for onco-hematology.

The unstructured nature of Real-World (RW) data from onco-hematological patients and the scarce accessibility to integrated systems restrain the use of RW information for research purposes. Natural Language Processing (NLP) might help in transposing unstructured reports into standardized electronic health records. We exploited NLP to develop an automated tool, named ARGO (Automatic Record Generator for Onco-hematology) to recognize information from pathology reports and populate electronic case report forms (eCRFs) pre-implemented by REDCap. ARGO was applied to hemo-lymphopathology reports of diffuse large B-cell, follicular, and mantle cell lymphomas, and assessed for accuracy (A), precision (P), recall (R) and F1-score (F) on internal (n = 239) and external (n = 93) report series. 326 (98.2%) reports were converted into corresponding eCRFs. Overall, ARGO showed high performance in capturing (1) identification report number (all metrics > 90%), (2) biopsy date (all metrics > 90% in both series), (3) specimen type (86.6% and 91.4% of A, 98.5% and 100.0% of P, 92.5% and 95.5% of F, and 87.2% and 91.4% of R for internal and external series, respectively), (4) diagnosis (100% of P with A, R and F of 90% in both series). We developed and validated a generalizable tool that generates structured eCRFs from real-life pathology reports.

Regulation of divalent metal transporter 1 (DMT1) non-IRE isoform by the microRNA Let-7d in erythroid cells.

BACKGROUND: Divalent metal transporter 1 (DMT1) is a widely expressed metal-iron transporter gene encoding four variant mRNA transcripts, differing for alternative promoter at 5' (DMT1 1A and 1B) and alternative splicing at 3' UTR, differing by a specific sequence either containing or lacking an iron regulatory element (+IRE and -IRE, respectively). DMT1-IRE might be the major DMT1 isoform expressed in erythroid cells, although its regulation pathways are still unknown. DESIGN AND METHODS: The microRNA (miRNA) Let-7d (miR-Let-7d) was selected by the analysis of four miRNAs, predicted to target the DMT1-IRE gene in CD34(+) hematopoietic progenitor cells, in K562 and in HEL cells induced to erythroid differentiation. Using a luciferase reporter assay we demonstrated the inhibition of DMT1-IRE by miR-Let-7d in K562 and HEL cells. The function of miR-Let-7d in erythroid cells was evaluated by the flow cytometry analysis of erythroid differentiation markers, by benzidine staining and by iron flame atomic absorption for the evaluation of iron concentration in the endosomes from K562 cells over-expressing miR-Let-7d. RESULTS: We show that in erythroid cells, DMT1-IRE expression is under the regulation of miR-Let-7d. DMT1-IRE and miR-Let-7d are inversely correlated with CD34(+) cells, K562 and HEL cells during erythroid differentiation. Moreover, overexpression of miR-Let-7d decreases the expression of DMT1-IRE at the mRNA and protein levels in K562 and HEL cells. MiR-Let-7d impairs erythroid differentiation of K562 cells by accumulation of iron in the endosomes. CONCLUSIONS: Overall, these data suggest that miR-Let-7d participates in the finely tuned regulation of iron metabolism by targeting DMT1-IRE isoform in erythroid cells.