Politecnico di Torino (logo)

Data-Driven Analysis to Improve Oncological Processes in Hospital

Manuel Scurti

Data-Driven Analysis to Improve Oncological Processes in Hospital.

Rel. Silvia Anna Chiusano, Ernestina Menasalvas Ruiz. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2019

PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview

Big Data technologies are becoming a pervasive technology in day-to-day life. Marketing, financial, automotive are some examples of sectors in which already we can see examples of how big data technologies can have a fundamental impact on society. The Healthcare sector, however, still has not benefitted from the wide scale use of Big Data technologies. This is because, the sector has been traditionally slow in adopting ICT and until recently, most clinical data was not stored digitally but on paper. Clinical decision making for specific diseases cannot be made using current hospital IT systems as information is either not structured or has been collected for operational purposes without having in mind to reuse them for further analysis. Thus, there is an unmet need for smart analytics capabilities to help report and measure key quality indicators. Cancer is the uncontrolled growth and spread of cells that arises from a change in one single cell. With more than 3.7 million new cases and 1.9 million deaths each year, cancer represents the second most important cause of death and morbidity in Europe. In this thesis, we focus on lung cancer from which we count with the data of the anonymized data of patients being diagnosed of a lung cancer in the last 10 year and we present a data-driven approach to help clinicians measuring two key performance indicators: i) length of stay and ii) patients at risk of developing lung cancer. The main challenge is to deal with unstructured informations in order to extract the knowledge. In order to achieve the goal this thesis presents a method to be able, first of all, to extract processes of the patient from unstructured data sets. To structure the project and make it replicable, CRISP-DM has been adopted as a methodology to fulfill the goals. The thesis also presents methods to analyze, clean and prepare data to obtain structured datasets from which the mentioned KPIs can be measured. The thesis also presents results that have been already discussed with the healthcare professionals.

Relators: Silvia Anna Chiusano, Ernestina Menasalvas Ruiz
Academic year: 2019/20
Publication type: Electronic
Number of Pages: 111
Corso di laurea: Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering)
Classe di laurea: New organization > Master science > LM-32 - COMPUTER SYSTEMS ENGINEERING
Aziende collaboratrici: UNSPECIFIED
URI: http://webthesis.biblio.polito.it/id/eprint/12442
Modify record (reserved for operators) Modify record (reserved for operators)