Dataset Information

Predicting patterns of service utilization within children's mental health agencies.

ABSTRACT:

Background

Some children with mental health (MH) problems have been found to receive ongoing care, either continuously or episodically. We sought to replicate patterns of MH service use over extended time periods, and test predictors of these patterns.

Methods

Latent class analyses were applied to 4?years of visit data from five MH agencies and nearly 6000 children, 4- to 13-years-old at their first visit.

Results

Five patterns of service use were identified, replicating previous findings. Overall, 14% of cases had two or more episodes of care and 23% were involved for more than 2?years. Most children (53%) were seen for just a few visits within a few months. Two patterns represented cases with two or more episodes of care spanning multiple years. In the two remaining patterns, children tended to have just one episode of care, but the number of sessions and length of involvement varied. Using discriminant function analyses, we were able to predict with just over 50% accuracy children's pattern of service use. Severe externalizing behaviors, high impairment, and high family burden predicted service use patterns with long durations of involvement and frequent visits.

Conclusions

Optimal treatment approaches for children seen for repeated episodes of care or for care lasting multiple years need to be developed. Children with the highest level of need (severe pathology, impairment, and burden) are probably best served by providing high intensity services at the start of care.

SUBMITTER: Reid GJ

PROVIDER: S-EPMC6929287 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting patterns of service utilization within children's mental health agencies.

Reid Graham J GJ Stewart Shannon L SL Barwick Melanie M Carter Jeffrey J Leschied Alan A Neufeld Richard W J RWJ St Pierre Jeff J Tobon Juliana I JI Vingilis Evelyn E Zaric Gregory S GS

BMC health services research 20191223 1

<h4>Background</h4>Some children with mental health (MH) problems have been found to receive ongoing care, either continuously or episodically. We sought to replicate patterns of MH service use over extended time periods, and test predictors of these patterns.<h4>Methods</h4>Latent class analyses were applied to 4 years of visit data from five MH agencies and nearly 6000 children, 4- to 13-years-old at their first visit.<h4>Results</h4>Five patterns of service use were identified, replicating pr ...[more]

PMID: 31870372

Similar Datasets

Project description:BACKGROUND:The utilization of oral health services in children remains at a relatively low level in China. However, little is known about the utilization patterns and related factors. The objective of this study was to explore the patterns of oral health service utilization and to determine the related factors among preschool children in Beijing, China, based on the Andersen behavioral model. METHODS:A cross-sectional study of 1425 preschool children aged 2 to 6 years was carried out in five kindergartens in Beijing, China. A questionnaire investigation of parents/caregivers was performed to collect information on oral health service utilization. Oral health needs were evaluated through oral health examinations. Chi-square tests, t-tests, multivariate logistic regression and negative binomial regression were used in this study to identify the variables associated with oral health service utilization. RESULTS:In total, 648 (45.5%) children had utilized oral health services in the past 12 months, while 24.3% had utilized preventive oral health services. Routine checkups and receiving preventive measures accounted for 63.2% of the children who utilized oral health services in the past 12 months. Children were more likely to have utilized oral health services in the past 12 months if they attended kindergartens with regular oral health care resources, if their oral health status as perceived by their parents/parents was "fair" or "poor", if they had more decayed, missing and filled teeth (dmft) and if they had experienced more dental pain. In addition, children with more dental pain and more access to oral health services, whose oral health status was perceived by parents/caregivers as worse tended to have utilized oral health services more frequently in the past 12 months. CONCLUSIONS:In conclusion, we found a strong association between access to regular oral health care resources and oral health service utilization among preschool children. Children whose oral health status was perceived by parents/caregivers as worse and who had more dental pain were more likely to have utilized oral health services in China.

Project description:BACKGROUND:Chronic spinal pain conditions affect millions of US adults and carry a high healthcare cost burden, both direct and indirect. Conservative interventions for spinal pain conditions, including chiropractic care, have been associated with lower healthcare costs and improvements in pain status in different clinical populations, including veterans. Little is currently known about predicting healthcare service utilization in the domain of conservative interventions for spinal pain conditions, including the frequency of use of chiropractic services. The purpose of this retrospective cohort study was to explore the use of supervised machine learning approaches to predicting one-year chiropractic service utilization by veterans receiving VA chiropractic care. METHODS:We included 19,946 veterans who entered the Musculoskeletal Diagnosis Cohort between October 1, 2003 and September 30, 2013 and utilized VA chiropractic services within one year of cohort entry. The primary outcome was one-year chiropractic service utilization following index chiropractic visit, split into quartiles represented by the following classes: 1 visit, 2 to 3 visits, 4 to 6 visits, and 7 or greater visits. We compared the performance of four multiclass classification algorithms (gradient boosted classifier, stochastic gradient descent classifier, support vector classifier, and artificial neural network) in predicting visit quartile using 158 sociodemographic and clinical features. RESULTS:The selected algorithms demonstrated poor prediction capabilities. Subset accuracy was 42.1% for the gradient boosted classifier, 38.6% for the stochastic gradient descent classifier, 41.4% for the support vector classifier, and 40.3% for the artificial neural network. The micro-averaged area under the precision-recall curve for each one-versus-rest classifier was 0.43 for the gradient boosted classifier, 0.38 for the stochastic gradient descent classifier, 0.43 for the support vector classifier, and 0.42 for the artificial neural network. Performance of each model yielded only a small positive shift in prediction probability (approximately 15%) compared to naïve classification. CONCLUSIONS:Using supervised machine learning to predict chiropractic service utilization remains challenging, with only a small shift in predictive probability over naïve classification and limited clinical utility. Future work should examine mechanisms to improve model performance.

Project description:BackgroundMental disorders are likely to be elevated in the Libyan population during the post-conflict period. We estimated cases of severe PTSD and depression and related health service requirements using modelling from existing epidemiological data and current recommended mental health service targets in low and middle income countries (LMIC's).MethodsPost-conflict prevalence estimates were derived from models based on a previously conducted systematic review and meta-regression analysis of mental health among populations living in conflict. Political terror ratings and intensity of exposure to traumatic events were used in predictive models. Prevalence of severe cases was applied to chosen populations along with uncertainty ranges. Six populations deemed to be affected by the conflict were chosen for modelling: Misrata (population of 444,812), Benghazi (pop. 674,094), Zintan (pop. 40,000), displaced people within Tripoli/Zlitan (pop. 49,000), displaced people within Misrata (pop. 25,000) and Ras Jdir camps (pop. 3,700). Proposed targets for service coverage, resource utilisation and full-time equivalent staffing for management of severe cases of major depression and post-traumatic stress disorder (PTSD) are based on a published model for LMIC's.FindingsSevere PTSD prevalence in populations exposed to a high level of political terror and traumatic events was estimated at 12.4% (95%CI 8.5-16.7) and was 19.8% (95%CI 14.0-26.3) for severe depression. Across all six populations (total population 1,236,600), the conflict could be associated with 123,200 (71,600-182,400) cases of severe PTSD and 228,100 (134,000-344,200) cases of severe depression; 50% of PTSD cases were estimated to co-occur with severe depression. Based upon service coverage targets, approximately 154 full-time equivalent staff would be required to respond to these cases sufficiently which is substantially below the current level of resource estimates for these regions.DiscussionThis is the first attempt to predict the mental health burden and consequent service response needs of such a conflict, and is crucially timed for Libya.

Dataset Information

Predicting patterns of service utilization within children's mental health agencies.

Background

Methods

Results

Conclusions

Publications

Predicting patterns of service utilization within children's mental health agencies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets