Regional Language Support for Patient-inclusive Decision Making in Breast Cancer Pathology Domain
G. Johanna Johnsi Rani1, Gladis D.2, Joy John Mammen3

1G. Johanna Johnsi Rani, Department of Computer Science, Madras Christian College (Autonomous), University of Madras, Chennai, India.
2Gladis D, Principal, Bharathi Women’s College (Autonomous), University of Madras, Chennai, India.
3Joy John Mammen, Professor and Head, Department of Transfusion Medicine & Immunohaematology, Christian Medical College, Vellore, India.

Manuscript received on 04 August 2019. | Revised Manuscript received on 11 August 2019. | Manuscript published on 30 September 2019. | PP: 8392-8399 | Volume-8 Issue-3 September 2019 | Retrieval Number: C6518098319/2019©BEIESP | DOI: 10.35940/ijrte.C6518.098319

Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: A Clinical Decision Support system (CDSS) is an application that analyzes data to help healthcare providers to make decisions and improve patient care. Clinicians use the CDSS to perform their routine tasks with computer-assistance. In the past, decision-making using CDSS was primarily oriented towards Clinicians but in recent times, shared decision-making with the patient is advocated. Shared decision-making focuses on encouraging patients to become informed and involved about their health-concerns and make right choices in discussion with expert Clinicians. In India, Breast cancer is the number one killer disease among women. The fast-growing breast cancer patient population demands development of a CDSS for the domain with patient-inclusive features. Medical documents generated in English by Medical practitioners may be understood only by patients with adequate medical knowledge and proficiency in English language. To benefit the regional-language patient population, a CDSS was developed with patient-inclusive features such as Risk assessment questionnaires and Pathology reports presented in Tamil to benefit the regional language-literate patients in the state of Tamilnadu. Translation resources for the domain such as Lexicon and Bilingual Dictionary are generated and used in Machine Translation (MT) of the reports in the CDSS. Translation of Pathology reports is performed by applying Natural Language Processing methods and Phrase-based translation approach and is refined using Synsets. The machine-translation by the CDSS was evaluated by comparing the CDSS output with output from a translation tool Anuvadaksh developed by Department of Information Technology, Government of India, and Google Translate. The outputs were also scrutinized by regional language experts and medical experts. The developed CDSS prototype is a pioneering effort to compile medical language resources for breast cancer pathology domain, and to present details to the patient in a language familiar to her. The regional language support would improve co-operation between the Clinician and patients for shared decision-making and enhance understanding in patients who would otherwise be passive due to the English language barrier. The CDSS with regional language could be used in hospitals in Tamilnadu and the implementation could be extended to other regional languages of India in the future.
Keywords: Clinical Decision Support System, Breast cancer, Machine Translation, Natural Language Processing, Shared Decision-Making

Scope of the Article:
Natural Language Processing