Mining Electronic Health Records: Challenges and Impact

Big data applications in the Healthcare Sector can provide a high potential for improving the overall efficiency and quality of care delivery. In the health care sector though, big data analytics has still to address several technical requirements, being unstructured data analysis one of them. Unstructured data represents a powerful untapped resource-one that has the potential to provide deeper insights into data and ultimately help drive competitive advantage. In this talk some of the most common challenges of processing such data to extract useful knowledge will be analyzed. In particular, we will deal with the following challenges: i) clinical narratives preprocessing using NLP, ii) name entity recognition, iii) semantic enrichment, iv) integration of the results. We will focus on the real use cases in which we are working in the frame of a European H2020 project called IASIS. In fact, we will analyze the challenges of analyzing reports and notes of patients suffering from Alzheimer's disease disease and lung cancer to extract patterns (survival, treatment, antecedents,...) that can help physicians to get insights for better management of the disease.

[1]  S Morin-Ben Abdallah,et al.  Brain metastases in non-small-cell lung cancer: are tyrosine kinase inhibitors and checkpoint inhibitors now viable options? , 2018, Current oncology.

[2]  Gang Chen,et al.  CEP72‐ROS1: A novel ROS1 oncogenic fusion variant in lung adenocarcinoma identified by next‐generation sequencing , 2018, Thoracic cancer.

[3]  Geoffrey R. Oxnard,et al.  Structural, Biochemical, and Clinical Characterization of Epidermal Growth Factor Receptor (EGFR) Exon 20 Insertion Mutations in Lung Cancer , 2013, Science Translational Medicine.

[4]  J. Engelman,et al.  ALK in lung cancer: past, present, and future. , 2013, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[5]  T. Arakawa,et al.  Molecular characterization of ALK, a receptor tyrosine kinase expressed specifically in the nervous system , 1997, Oncogene.

[6]  Olivier Bodenreider,et al.  The Unified Medical Language System (UMLS): integrating biomedical terminology , 2004, Nucleic Acids Res..

[7]  J. Shih,et al.  Management of acquired resistance to EGFR TKI–targeted therapy in advanced non-small cell lung cancer , 2018, Molecular Cancer.

[8]  M. Tamburini,et al.  Karnofsky and ECOG performance status scoring in lung cancer: a prospective, longitudinal study of 536 patients from a single institution. , 1996, European journal of cancer.

[9]  Yoshihiko Hayashi,et al.  Anaplastic lymphoma kinase-negative uterine inflammatory myofibroblastic tumor containing the ETV6-NTRK3 fusion gene: a case report , 2018, The Journal of international medical research.

[10]  L. Sobin,et al.  TNM Classification of Malignant Tumours , 1987, UICC International Union Against Cancer.

[11]  David A. Ferrucci,et al.  UIMA: an architectural approach to unstructured information processing in the corporate research environment , 2004, Natural Language Engineering.

[12]  E. McFadden,et al.  Toxicity and response criteria of the Eastern Cooperative Oncology Group , 1982, American journal of clinical oncology.

[13]  N. Ridgway,et al.  Epidermal growth factor receptor (EGFR) in lung cancer: an overview and update. , 2011, Journal of thoracic disease.

[14]  Kent A. Spackman,et al.  SNOMED RT: a reference terminology for health care , 1997, AMIA.

[15]  H. Aburatani,et al.  Identification of the transforming EML4–ALK fusion gene in non-small-cell lung cancer , 2007, Nature.

[16]  B. Chan,et al.  Targeted therapy for non-small cell lung cancer: current standards and the promise of the future. , 2015, Translational lung cancer research.

[17]  L. Sequist,et al.  Transformation from non-small-cell lung cancer to small-cell lung cancer: molecular drivers and cells of origin. , 2015, The Lancet. Oncology.