Dataset Information

Predicting GP visits: A multinomial logistic regression investigating GP visits amongst a cohort of UK patients living with Myalgic encephalomyelitis.

ABSTRACT: BACKGROUND:Myalgic Encephalomyelitis (ME) is a chronic condition whose status within medicine is the subject of on-going debate. Some medical professionals regard it as a contentious illness. Others report a lack of confidence with diagnosis and management of the condition. The genesis of this paper was a complaint, made by an ME patient, about their treatment by a general practitioner. In response to the complaint, Healthwatch Trafford ran a patient experience-gathering project. METHOD:Data was collected from 476 participants (411 women and 65 men), living with ME from across the UK. Multinomial logistic regression investigated the predictive utility of length of time with ME; geographic location (i.e. Manchester vs. rest of UK); trust in GP; whether the patient had received a formal diagnosis; time taken to diagnosis; and gender. The outcome variable was number of GP visits per year. RESULTS:All variables, with the exception of whether the patient had received a formal diagnosis, were significant predictors. CONCLUSIONS:Relationships between ME patients and their GPs are discussed and argued to be key to the effective delivery of care to this patient cohort. Identifying potential barriers to doctor patient interactions in the context of ME is crucial.

SUBMITTER: Walsh RS

PROVIDER: S-EPMC7285543 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting GP visits: A multinomial logistic regression investigating GP visits amongst a cohort of UK patients living with Myalgic encephalomyelitis.

Walsh R Stephen RS Denovan Andrew A Drinkwater Kenneth K Reddington Sean S Dagnall Neil N

BMC family practice 20200610 1

<h4>Background</h4>Myalgic Encephalomyelitis (ME) is a chronic condition whose status within medicine is the subject of on-going debate. Some medical professionals regard it as a contentious illness. Others report a lack of confidence with diagnosis and management of the condition. The genesis of this paper was a complaint, made by an ME patient, about their treatment by a general practitioner. In response to the complaint, Healthwatch Trafford ran a patient experience-gathering project.<h4>Meth ...[more]

PMID: 32522264

Similar Datasets

Project description:Background:Unmet need for family planning is high (30%) in Ghana. Reducing unmet need for family planning will reduce the high levels of unintended pregnancies, unsafe abortions, maternal and neonatal morbidity and mortality. The purpose of this study was to examine factors that are associated with unmet need for family planning to help scale up the uptake of family planning services in Ghana. Methods:This cross sectional descriptive and inferential study involved secondary data analysis of women in the reproductive age (15-49?years) from the Ghana Demographic and Health Survey 2014 data. The outcome variable was unmet need for family planning which was categorized into three as no unmet need, unmet need for limiting and unmet need for spacing. Chi-squared test statistic and bivariate multilevel multinomial mixed effects logistic regression model were used to determine significant variables which were included for the multivariable multilevel multinomial mixed effects logistic regression model. All significant variables (p?<?0.05) based on the bivariate analysis were included in the multinomial mixed effects logistic regression model via model building approach. Results:Women who fear contraceptive side effects were about 2.94 (95% CI, 2.28, 3.80) and 2.58 (95% CI, 2.05, 3.24) times more likely to have an unmet need for limiting and spacing respectively compared to those who do not fear side effects. Respondents' age was a very significant predictor of unmet need for family planning. There was very high predictive probability among 45-49?year group (0.86) compared to the 15-19?year group (0.02) for limiting. The marginal predictive probability for spacing changed significantly from 0.74 to 0.04 as age changed from 15 to 19 to 45-49?years. Infrequent sexual intercourse, opposition from partners, socio-economic (wealth index, respondents educational level, respondents and partner's occupation) and cultural (religion and ethnicity) were all significant determinants of both unmet need for limiting and spacing. Conclusions:This study reveals that fear of side effect, infrequent sex, age, ethnicity, partner's education and region were the most highly significant predictors of both limiting and spacing. These factors must be considered in trying to meet the unmet need for family planning.

Project description:Whether they have been engineered for it or not, most healthcare systems experience a variety of unexpected events such as appointment miss-opportunities that can have significant impact on their revenue, cost and resource utilization. In this paper, a multi-way multi-task learning model based on multinomial logistic regression is proposed to jointly predict the occurrence of different types of miss-opportunities at multiple clinics.An extension of L1?/?L2 regularization is proposed to enable transfer of information among various types of miss-opportunities as well as different clinics. A proximal algorithm is developed to transform the convex but non-smooth likelihood function of the multi-way multi-task learning model into a convex and smooth optimization problem solvable using gradient descent algorithm.A dataset of real attendance records of patients at four different clinics of a VA medical center is used to verify the performance of the proposed multi-task learning approach. Additionally, a simulation study, investigating more general data situations is provided to highlight the specific aspects of the proposed approach. Various individual and integrated multinomial logistic regression models with/without LASSO penalty along with a number of other common classification algorithms are fitted and compared against the proposed multi-way multi-task learning approach. Fivefold cross validation is used to estimate comparing models parameters and their predictive accuracy. The multi-way multi-task learning framework enables the proposed approach to achieve a considerable rate of parameter shrinkage and superior prediction accuracy across various types of miss-opportunities and clinics.The proposed approach provides an integrated structure to effectively transfer knowledge among different miss-opportunities and clinics to reduce model size, increase estimation efficacy, and more importantly improve predictions results. The proposed framework can be effectively applied to medical centers with multiple clinics, especially those suffering from information scarcity on some type of disruptions and/or clinics.

Dataset Information

Predicting GP visits: A multinomial logistic regression investigating GP visits amongst a cohort of UK patients living with Myalgic encephalomyelitis.

Publications

Predicting GP visits: A multinomial logistic regression investigating GP visits amongst a cohort of UK patients living with Myalgic encephalomyelitis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets