Using Machine Learning Classifiers to Assist Healthcare-Related Decisions: Classification of Electronic Patient Records

Surveillance Levels (SLs) are categories for medical patients (used in Brazil) that represent different types of medical recommendations. SLs are defined according to risk factors and the medical and developmental history of patients. Each SL is associated with specific educational and clinical measures. The objective of the present paper was to verify computer-aided, automatic assignment of SLs. The present paper proposes a computer-aided approach for automatic recommendation of SLs. The approach is based on the classification of information from patient electronic records. For this purpose, a software architecture composed of three layers was developed. The architecture is formed by a classification layer that includes a linguistic module and machine learning classification modules. The classification layer allows for the use of different classification methods, including the use of preprocessed, normalized language data drawn from the linguistic module. We report the verification and validation of the software architecture in a Brazilian pediatric healthcare institution. The results indicate that selection of attributes can have a great effect on the performance of the system. Nonetheless, our automatic recommendation of surveillance level can still benefit from improvements in processing procedures when the linguistic module is applied prior to classification. Results from our efforts can be applied to different types of medical systems. The results of systems supported by the framework presented in this paper may be used by healthcare and governmental institutions to improve healthcare services in terms of establishing preventive measures and alerting authorities about the possibility of an epidemic.

Factors associated with maternal intrapartum transfers from a freestanding birth centre in Sao Paulo, Brazil: A case control study

Objectives: to identify factors associated with maternal intrapartum transfer from a freestanding birth centre to hospital. Design: case-control study with retrospective data collection. Participants and settings: cases included all 111 women transferred from a freestanding birth centre in Sao Paulo to the referral hospital, from March 2002 to December 2009. The controls were 456 women who gave birth in the birth centre during the same period who were not transferred, randomly selected with four controls for each case. Methods: data were obtained from maternal records. Factors associated with maternal intrapartum transfers were initially analysed using a chi(2) test of association. Variables with p < 0.20 were then included in multivariate analyses. A multiple logistic regression model was built using stepwise forward selection; variables which reached statistical significance at p < 0.05 were considered to be independently associated with maternal transfer. Findings: during the study data collection period, 111(4%) of 2,736 women admitted to the centre were transferred intrapartum. Variables identified as independently associated factors for intrapartum transfer included nulliparity (OR 5.1, 95% CI 2.7-9.8), maternal age >= 35 years (OR 5.4, 95% CI 2.1-13.4), not having a partner (OR 2.8, 95% CI 1.5-5.3), cervical dilation <= 3 cm on admission to the birth centre (OR 1.9, 95% CI 1.1-3.2) and between 5 and 12 antenatal appointments at the birth centre (OR 3.8, 95% CI 1.9-7.5). In contrast, a low correlation between fundal height and pregnancy gestation (OR 0.3, 95% CI 0.2-0.6) appeared to be protective against transfer. Conclusions and implications for practice: identifying factors associated with maternal intrapartum transfer could support decision making by women considering options for place of birth, and support the content of appropriate information about criteria for admission to a birth centre. Findings add to the evidence base to support identification of women in early labour who may experience later complications and could support timely implementation of appropriate interventions associated with reducing transfer rates. (C) 2012 Elsevier Ltd. All rights reserved.