BIG DATA in geriatric oncology: How could we assess effective working time?

• Published in: Journal of clinical oncology Vol. 37; no. 15_suppl; p. e18073
• Main Authors: Lopez De San Vicente, Borja, Jaureguibeitia, Paula, Zumarraga, Ane, López Santillan, Maria, Pikabea, Fernando, Galve, Elena, Nuño, Maitane, Novas, Patricia, Abad, Teresa, Arango, Juan Fernando, Perez-Hoyos, Maria Teresa, Sande, Laura, Sala, Angeles, Legaspi, Jairo, Azcuna, Josune, Martínez, Maria Purificacion
• Format: Journal Article
• Language: English
• Published: 20.05.2019
• ISSN: 0732-183X; 1527-7755
• DOI: 10.1200/JCO.2019.37.15_suppl.e18073

Abstract only e18073 Background: Electronic Medical Records (EMR) were born as a result of medicine digitalization. Healthcare information systems (HIS) hold great value to the workflow management and patient care. New technologies not only allow us work with a faster and more reliable medical history, but also understand how health professionals think and work. Time consumption is one of the biggest issues that geriatric assessment (GA) has to deal with. Hurria et al. developed a brief tool which requires minimal resources and time spent (≈30 mins) by healthcare providers. On the other hand, patients´ medical history review, writing reports or tumor board discussions are often underestimated on daily time schedule. The aim of this study is to analyse the effective working time (EWT) invested in geriatric assessment in our centre by Big Data analytics. Methods: From 1 March 2018 to 31 december 2018, > 70 years-old patients were prospectively recruited from the outpatient oncology practices at Basurto University Hospital. Nurse-guided geriatric assessment was scheduled 45 mins before oncologist’s first visit, and functional status, comorbidity, cognitive function, psychological state, social support, polypharmacy, nutritional status, and nurse interventions were measured. Patterns of nurse and medical behaviors from EMRs were tracked. The model to figure out active behaviour in HIS was defined as > 23 events/hour. EWT was established as time spent between first and last access to HIS. Isolated events and interventions by users other than oncologists and nurses were excluded. Results: 280 patients were enrolled, 54.3% men. Geriatric assessment detected: cognitive impairment 17 pts (6.9%), mental health alteration 78 pts (27.8%), Poor social support 10 pts (3,7%), polypharmacy 239 pts (89,28%), and severe malnutrition 34 pts (13.2%). Nurse specific intervention was made in 90 pts (32,6%). The median EWT by nurses for a GA was 39 minutes (SD 0:21), and 46 mins (SD 0:17) by oncologists´global evaluation. Nurses started in average 3 mins (SD 0:27) before scheduled visit, and oncologists 9 mins (SD 0:28) after. Conclusions: Big data analytics show an assumable effective working time for a geriatric assessment in our patients. HIS users behavior analysis could help in the management of our healthcare systems.