An electronic record system in nursing education: evaluation and utilization

The main objective of the present work is to analyze the results of the utilization and evaluation of the LORETO Record System (LRS), providing improvement areas in the teaching-learning process and technology, in second year nursing students. A descriptive, prospective, cross sectional study using inferential statics has been carried out on all electronic records reported by 55 nursing students during clinical internships (April 1º-June 26º, 2013). Electronic record average rated 7.22 points (s=0.6; CV=0.083), with differences based on the clinical practice units (p<0,05). Three items assessed did not exceed the quality threshold set at 0.7 (p<0.05). Record Rate exceeds the quality threshold set at 80% for the overall sample, with differences based on the practice units. Only two clinical practice units rated above the minimum threshold (p <0.05). Record of care provision every 3 days did not reach the estimated quality threshold (p <0.05). There is a dichotomy between qualitative and quantitative results of LRS. Improvement areas in theoretical education have been identified. The LRS seems an appropriate learning and assessment tool, although the development of a new APP version and the application of principles of gamification should be explored.

A metasynthesis of qualitative studies regarding opinions and perceptions about barriers and determinants of health services’ accessibility in economic migrants

Background: Access to health services is an important health determinant. New research in health equity is required, especially amongst economic migrants from developing countries. Studies conducted on the use of health services by migrant populations highlight existing gaps in understanding which factors affect access to these services from a qualitative perspective. We aim to describe the views of the migrants regarding barriers and determinants of access to health services in the international literature (1997–2011). Methods: A systematic review was conducted for Qualitative research papers (English/Spanish) published in 13 electronic databases. A selection of articles that accomplished the inclusion criteria and a quality evaluation of the studies were carried out. The findings of the selected studies were synthesised by means of metasynthesis using different analysis categories according to Andersen’s conceptual framework of access and use of health services and by incorporating other emergent categories. Results: We located 3,025 titles, 36 studies achieved the inclusion criteria. After quality evaluation, 28 articles were definitively synthesised. 12 studies (46.2%) were carried out in the U.S and 11 studies (42.3%) dealt with primary care services. The participating population varied depending mainly on type of host country. Barriers were described, such as the lack of communication between health services providers and migrants, due to idiomatic difficulties and cultural differences. Other barriers were linked to the economic system, the health service characteristics and the legislation in each country. This situation has consequences for the lack of health control by migrants and their social vulnerability. Conclusions: Economic migrants faced individual and structural barriers to the health services in host countries, especially those with undocumented situation and those experimented idiomatic difficulties. Strategies to improve the structures of health systems and social policies are needed.

The aid of machine learning to overcome the classification of real health discharge reports written in Spanish

Hospitals attached to the Spanish Ministry of Health are currently using the International Classification of Diseases 9 Clinical Modification (ICD9-CM) to classify health discharge records. Nowadays, this work is manually done by experts. This paper tackles the automatic classification of real Discharge Records in Spanish following the ICD9-CM standard. The challenge is that the Discharge Records are written in spontaneous language. We explore several machine learning techniques to deal with the classification problem. Random Forest resulted in the most competitive one, achieving an F-measure of 0.876.