Dataset Information

A Multi-way Multi-task Learning Approach for Multinomial Logistic Regression*. An Application in Joint Prediction of Appointment Miss-opportunities across Multiple Clinics.

ABSTRACT: 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.

SUBMITTER: Alaeddini A

PROVIDER: S-EPMC5831772 | biostudies-literature | 2017 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Multi-way Multi-task Learning Approach for Multinomial Logistic Regression*. An Application in Joint Prediction of Appointment Miss-opportunities across Multiple Clinics.

Alaeddini Adel A Hong Seung Hee SH

Methods of information in medicine 20170607 4

<h4>Objectives</h4>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.<h4>Methods</h4>An extension of L<sub>1</sub ...[more]

PMID: 28590498

Similar Datasets

Project description:BackgroundMultidrug resistant tuberculosis (MDR-TB) represents a major public health concern in the Republic of Moldova, with an estimated 31% of new and 56% of previously treated TB cases having MDR disease in 2022. A recent genomic epidemiology study of incident TB occurring in 2018 and 2019 found that 92% of MDR-TB was the result of transmission. The MDR phenotype was concentrated among two M. tuberculosis (Mtb) lineages: L2.2.1 (Beijing) and L4.2.1 (Ural).MethodsWe developed and applied a hierarchical Bayesian multinominal logistic regression model to Mtb genomic, spatial, and epidemiological data collected from all individuals with diagnosed TB in Moldova in 2018 and 2019 to identify locations in which specific Mtb strains are being transmitted. We then used a logistic regression model to estimate locality-level factors associated with local transmission.FindingsWe found differences in the spatial distribution and degree of local concentration of disease due to specific strains of Beijing and Ural lineage Mtb. Foci of transmission for four strains of Beijing lineage Mtb, predominantly of the MDR-TB phenotype, were located in several regions, but largely concentrated in Transnistria. In contrast, transmission of Ural lineage Mtb had less marked patterns of spatial aggregation, with a single strain (also of the MDR phenotype) spatially clustered in southern Transnistria. We found a 30% (95% credible interval 2%-80%) increase in odds of a locality being a transmission cluster for each increase of 100 persons per square kilometer, while higher local tuberculosis incidence and poverty were not associated with a locality being a transmission focus.InterpretationOur results identified localities where specific Mtb transmission networks were concentrated and quantified the association between locality-level factors and focal transmission. This analysis revealed Transnistria as the primary area where specific Mtb strains (predominantly of the MDR-TB phenotype) were locally transmitted and suggests that targeted intensified case finding in this region may be an attractive policy option.FundingFunding for this work was provided by the National Institute of Allergy and Infectious Diseases at the US National Institutes of Health.

Project description:BackgroundMore than one out of every ten married women in the world, and one out of every five women in Africa, have unmet family planning needs. Despite this, studies concerning sub-Saharan Africa as well as the community-level factors that may influence the unmet need for family planning are scarce.ObjectiveTo assess factors associated with unmet need for family planning in sub-Saharan Africa.MethodsThis study used the nineteen demographic and health surveys (DHS) conducted between 2015 and 2020 in sub-Saharan Africa. A total weighted sample of 175, 820 women of reproductive age who were married during the survey was used for this study. To assess the factors associated with unmet need for family planning, I have employed a multilevel multinomial logistic regression model. After selecting variables using the bivariable analysis, a multivariable model was fitted. Finally, an adjusted relative risk ratio with its 95% Confidence Interval was reported and variables with a p-value less than 0.05 were declared to be significant predictors of unmet need for family planning.ResultThe overall prevalence of unmet need for family planning in sub-Saharan Africa was 23.70%, of which unmet need for spacing and limiting was 15.81% and 7.90% respectively. In the multivariable multilevel multinomial model, women's age, women's education, age at cohabitation, heard about family planning through media, parity, number of under-five children, and knowledge about modern contraceptive methods were among the individual-level factors that were associated with both the unmet need for spacing and limiting. Place of residence, community level of women illiteracy, and region were among the community-level factors that were associated with both unmet needs for spacing and limiting. Household size and visiting the health facility in the last 12 months were associated with unmet need for spacing only and husband education was associated with unmet need for limiting only.ConclusionUnmet need for family planning in sub-Saharan Africa was high. Both individual and community level factors were associated with both unmet need for spacing and limiting. Therefore, it is better to consider interventions at both individual and community levels.

Dataset Information

A Multi-way Multi-task Learning Approach for Multinomial Logistic Regression*. An Application in Joint Prediction of Appointment Miss-opportunities across Multiple Clinics.

Publications

A Multi-way Multi-task Learning Approach for Multinomial Logistic Regression*. An Application in Joint Prediction of Appointment Miss-opportunities across Multiple Clinics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets