Artificial intelligence processing electronic health records to identify commonalities and comorbidities cluster at Immuno Center Humanitas

Abstract

Background Comorbidities are common in chronic inflammatory conditions, requiring multidisciplinary treatment approach. Understanding the link between a single disease and its comorbidities is important for appropriate treatment and management. We evaluate the ability of an NLP‐based process for knowledge discovery to detect information about pathologies, patients' phenotype, doctors' prescriptions and commonalities in electronic medical records, by extracting information from free narrative text written by clinicians during medical visits, resulting in the extraction of valuable information and enriching real world evidence data from a multidisciplinary setting. Methods We collected clinical notes from the Allergy Department of Humanitas Research Hospital written in the last 3 years and used it to look for diseases that cluster together as comorbidities associated to the main pathology of our patients, and for the extent of prescription of systemic corticosteroids, thus evaluating the ability of NLP‐based tools for knowledge discovery to extract structured information from free text. Results We found that the 3 most frequent comorbidities to appear in our clusters were asthma, rhinitis, and urticaria, and that 991 (of 2057) patients suffered from at least one of these comorbidities. The clusters which co‐occur particularly often are oral allergy syndrome and urticaria (131 patients), angioedema and urticaria (105 patients), rhinitis and asthma (227 patients). With regards to systemic corticosteroid prescription volume by our clinicians, we found it was lower when compared to the therapy the patients followed before coming to our attention, with the exception of two diseases: Chronic obstructive pulmonary disease and Angioedema. Conclusions This analysis seems to be valid and is confirmed by the data from the literature. This means that NLP tools could have significant role in many other research fields of medicine, as it may help identify other important, and possibly previously neglected clusters of patients with comorbidities and commonalities. Another potential benefit of this approach lies in its potential ability to foster a multidisciplinary approach, using the same drugs to treat pathologies normally treated by physicians in different branches of medicine, thus saving resources and improving the pharmacological management of patients.

The DERMACLEAR study: Verification results of a natural language processing system in dermatology

“…NLP systems have the potential to improve epidemiology disease awareness; NLP has been utilized in previous studies to extract information from unstructured clinical notes, including the dermatology setting 16–18,24 . Morandini et al 16 used NLP to assess clinical notes to identify diseases that present together as comorbidities.…”

“…NLP systems have the potential to improve epidemiology disease awareness; NLP has been utilized in previous studies to extract information from unstructured clinical notes, including the dermatology setting. [16][17][18]24 Morandini et al 16 used NLP to assess clinical notes to identify diseases that present together as comorbidities. Through NLP, they reported that, of 2057 patient records, the most common conditions that occur together were oral allergy syndrome and urticaria, angioedema and urticaria, and rhinitis and asthma.…”

“…Data were gathered, anonymized and stored on the servers of the hospitals for optimal security; IOMED's cloud servers will be used to analyse the EHRs. To select and include eligible patients, and to collect and organize data, EHRs will be processed by a data analytics platform which includes an NLP system [16][17][18] developed by IOMED. This medical NLP system was retrained for this study by IOMED, updating existing NLP models, and designing and training new models via data annotation performed by physicians.…”

“…[12][13][14][15] NLP can extract large amounts of data from EHRs with unprecedented efficiency by reducing the time spent on manual searching. 5 NLP technology has been utilized in previous studies to extract information from unstructured clinical notes [16][17][18] ; for example, to identify cases of psoriatic arthritis from a large volume of EHRs. 19 However, the real-world application of AI tools, including NLP, pose several challenges in terms of accuracy and reliability.…”

La gestione del paziente con rinosinusite cronica e poliposi nasale in Italia: expert opinion sul percorso diagnostico-terapeutico

“…Nell'esperienza clinica reallife sono comuni le situazioni complesse, con pazienti con una storia di patologia di lunga durata, sottoposti a trattamenti diversi anche per le comorbilità presenti, per i quali la decisione terapeutica risulta complicata e non chiaramente definita dalle Linee Guida. Per questi pazienti l'intervento multidisciplinare è determinante; l'introduzione di approcci innovativi come l'utilizzo dell'intelligenza artificiale può rappresentare un supporto nell'identificazione di migliori strategie terapeutiche, in relazione all'elevato numero di possibili comorbilità (20).…”