Cognitive computing for hearing healthcare: An eHealth solution for the clinical management of aged people with hearing disabilities
| Autor: | Gabriella Tognola, Alessia Paglialonga, Alessandra Murri, Ruby Karmacharya, Francesco Pinciroli, Domenico Cuda |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: | |
| Zdroj: | Journal of Hearing Science 7 (2017): 39–40. info:cnr-pdr/source/autori:Gabriella Tognola, Alessia Paglialonga, Alessandra Murri, Ruby Karmacharya, Francesco Pinciroli, Domenico Cuda/titolo:Cognitive computing for hearing healthcare: An eHealth solution for the clinical management of aged people with hearing disabilities/doi:/rivista:Journal of Hearing Science (Print)/anno:2017/pagina_da:39/pagina_a:40/intervallo_pagine:39–40/volume:7 |
| Popis: | Background: A successful hearing rehabilitation plan for older people shall consider the technological factors (e.g. the type of HA or CI used) and also other aspects related to auditory disability, e.g., the perceived hearing difficulties in real life, the impact of subject's hearing disability on the quality of life, speech perception abilities in real environments. Many valuable clinical instruments exist to measure all the diverse aspects of hearing disability. Unfortunately, most physicians cannot make profit of this wealth of ever increasing information as it is dispersed in different medical documents. Also, about 80% of health data, e.g. that in medical notes, is invisible to systems because it is unstructured. Our work is the first attempt in the hearing healthcare domain, to design and develop an easy-to-use, multi-source clinical system for extracting and collating audiological information from the diversified documents of the patient health record. Material and methods: This first pilot evaluation of our system is done on a sample of medical records of elderly with CIs. The records included all the medical documents and test results generated during the time (including all the follow-up visits). The system applies eHealth technologies (cognitive computing) and leverages an ad hoc lexicon developed for the hearing healthcare. Results: Our system extracts textual narrative information (e.g. from the past medical history, current complaints, etiology, audiological diagnosis, risk factors, surgical procedure to implant the hearing devices) and numerical information (e.g. audiometric tests, technical setup of CIs, questionnaires scores, etc.). The system analyses medical notes written in plain language, understands which information is critical to the treatment pathway, and puts the extracted information into the proper textual and temporal contexts. The extracted information is then made available through a central platform to be analyzed in a tuned approach by the clinician. All these processes are directly performed on the original medical documents, as they are generated by the clinician using plain language. Conclusions: The proposed system provides clinicians with a multi-source and multi-dimensional view of patient's hearing disability. It helps clinicians to improve the ongoing treatment of chronic conditions and the proactive and preventive interventions. Grant: PNRCNR Aging Program 2012-18. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|