Your browser doesn't support javascript.
loading
Dense Annotation of Free-Text Critical Care Discharge Summaries from an Indian Hospital and Associated Performance of a Clinical NLP Annotator.
Ramanan, S V; Radhakrishna, Kedar; Waghmare, Abijeet; Raj, Tony; Nathan, Senthil P; Sreerama, Sai Madhukar; Sampath, Sriram.
Afiliación
  • Ramanan SV; RelAgent Technologies (P) Limited, IIT Madras Research Park, #14, 1st Floor, Taramani, Chennai, 600113, India. ramanan@relagent.com.
  • Radhakrishna K; Division of Medical Informatics, St. John's Research Institute, 100 Feet Road, Koramangala, Bangalore, 560034, India. kedar.angirus@gmail.com.
  • Waghmare A; Division of Medical Informatics, St. John's Research Institute, 100 Feet Road, Koramangala, Bangalore, 560034, India.
  • Raj T; Division of Medical Informatics, St. John's Research Institute, 100 Feet Road, Koramangala, Bangalore, 560034, India.
  • Nathan SP; RelAgent Technologies (P) Limited, IIT Madras Research Park, #14, 1st Floor, Taramani, Chennai, 600113, India.
  • Sreerama SM; Division of Medical Informatics, St. John's Research Institute, 100 Feet Road, Koramangala, Bangalore, 560034, India.
  • Sampath S; Department of Critical Care Medicine, St. John's Medical College, Bangalore, India.
J Med Syst ; 40(8): 187, 2016 Aug.
Article en En | MEDLINE | ID: mdl-27342107
Electronic Health Record (EHR) use in India is generally poor, and structured clinical information is mostly lacking. This work is the first attempt aimed at evaluating unstructured text mining for extracting relevant clinical information from Indian clinical records. We annotated a corpus of 250 discharge summaries from an Intensive Care Unit (ICU) in India, with markups for diseases, procedures, and lab parameters, their attributes, as well as key demographic information and administrative variables such as patient outcomes. In this process, we have constructed guidelines for an annotation scheme useful to clinicians in the Indian context. We evaluated the performance of an NLP engine, Cocoa, on a cohort of these Indian clinical records. We have produced an annotated corpus of roughly 90 thousand words, which to our knowledge is the first tagged clinical corpus from India. Cocoa was evaluated on a test corpus of 50 documents. The overlap F-scores across the major categories, namely disease/symptoms, procedures, laboratory parameters and outcomes, are 0.856, 0.834, 0.961 and 0.872 respectively. These results are competitive with results from recent shared tasks based on US records. The annotated corpus and associated results from the Cocoa engine indicate that unstructured text mining is a viable method for cohort analysis in the Indian clinical context, where structured EHR records are largely absent.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Alta del Paciente / Procesamiento de Lenguaje Natural / Cuidados Críticos / Registros Electrónicos de Salud / Minería de Datos Tipo de estudio: Diagnostic_studies / Guideline / Observational_studies / Risk_factors_studies Aspecto: Equity_inequality Límite: Humans País/Región como asunto: Asia Idioma: En Revista: J Med Syst Año: 2016 Tipo del documento: Article País de afiliación: India Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Alta del Paciente / Procesamiento de Lenguaje Natural / Cuidados Críticos / Registros Electrónicos de Salud / Minería de Datos Tipo de estudio: Diagnostic_studies / Guideline / Observational_studies / Risk_factors_studies Aspecto: Equity_inequality Límite: Humans País/Región como asunto: Asia Idioma: En Revista: J Med Syst Año: 2016 Tipo del documento: Article País de afiliación: India Pais de publicación: Estados Unidos