Vesa Komssi

Objective: In recent years research has identified important predictors for nursing home admission (NHA). However, as far as we know, the previous risk models use complex variable sets from many sources and the output is a single risk value. The objective of this study was to develop an NHA risk model with
a variable set from single data source and richer output information.

Methods: In this study, we developed a model selecting variables only from the RAI-HC (Resident Assessment… Näytä lisää

Objective: In recent years research has identified important predictors for nursing home admission (NHA). However, as far as we know, the previous risk models use complex variable sets from many sources and the output is a single risk value. The objective of this study was to develop an NHA risk model with
a variable set from single data source and richer output information.

Methods: In this study, we developed a model selecting variables only from the RAI-HC (Resident Assessment Instrument – Home Care) system. Furthermore, we used principal component analysis and K-means clustering to target proper interventions for high-risk clients.

Results: The performance of the model was close to the complex previous model (recall :442 vs. :486 and specificity :879 vs. :884). For the risk clients, three intervention clusters (deficiency in physical functionality, deficiency in cognitive functionality and depression and mood disorders) were found.

Conclusion: The NHA risk model and intervention clusters are important because they enable the identification of proper interventions for the right clients. The fact that the model with RAI-HC data alone was accurate enough simplifies the integration of the NHA risk model into practice because it uses data from one system and the algorithm can be integrated easily into the source system. Näytä vähemmän

In previous years a substantial number of studies have identified statistically important predictors of nursing home admission (NHA). However, as far as we know, the analyses have been done at the population-level. No prior research has analysed the prediction accuracy of a NHA model for individuals.

This study is an analysis of 3056 longer-term home care customers in the city of Tampere, Finland.
The logistic regression and Gaussian naive Bayes classifiers achieved 78% accuracy for… Näytä lisää

In previous years a substantial number of studies have identified statistically important predictors of nursing home admission (NHA). However, as far as we know, the analyses have been done at the population-level. No prior research has analysed the prediction accuracy of a NHA model for individuals.

This study is an analysis of 3056 longer-term home care customers in the city of Tampere, Finland.
The logistic regression and Gaussian naive Bayes classifiers achieved 78% accuracy for predicting NHA. The most important variables were RAI MAPLE (Method for Assigning Priority Levels), functional impairment (RAI IADL, Activities of Daily Living), cognitive impairment (RAI CPS, Cognitive Performance Scale), memory disorders (diagnoses G30-G32 and F00-F03) and the use of community-based health-service and prior hospital use (emergency visits and periods of care).

The accuracy of the classifier for individuals was high enough to convince the officials of the city of
Tampere to integrate the predictive model based on the findings of this study as a part of home care information system. Further work need to be done to evaluate variables that are modifiable and responsive to interventions. Näytä vähemmän

In order to slow down the increase of social and healthcare costs on the level of society as a whole, improving the coordination of services for those in need of a lot of services, on the one hand, and prevention of the increased need for services on the other become crucial. The problems related to multiple sources of funding may be exacerbated within the segment of the population who are most in need of services, who need funding for medical and travel expenses, rehabilitation services and… Näytä lisää

In order to slow down the increase of social and healthcare costs on the level of society as a whole, improving the coordination of services for those in need of a lot of services, on the one hand, and prevention of the increased need for services on the other become crucial. The problems related to multiple sources of funding may be exacerbated within the segment of the population who are most in need of services, who need funding for medical and travel expenses, rehabilitation services and disability benefits in addition to the social and healthcare services provided by the municipality. What makes the coordination of the services complicated today is the dispersed decision making and the lack of information across funding sources. The reform of the social and healthcare system should aim at supporting the comprehensive planning and coordination of services and benefits for those most in need of them. Näytä vähemmän

Each year, the 15% of patients who used the most services accrued 70% of the total expenditure billed by the hospital district. Patients using services from more than one specialty accounted for 41% of the total cost of these patients. When the patients who were among the top 15% during two consecutive years were analyzed, the share of total costs incurred by patients who had used more than one specialty increased to 53%.The majority of patients who were among the top 15% during two consecutive… Näytä lisää

Each year, the 15% of patients who used the most services accrued 70% of the total expenditure billed by the hospital district. Patients using services from more than one specialty accounted for 41% of the total cost of these patients. When the patients who were among the top 15% during two consecutive years were analyzed, the share of total costs incurred by patients who had used more than one specialty increased to 53%.The majority of patients who were among the top 15% during two consecutive years had one or more of a small number of diagnoses. In addition to these diagnoses, they had as many as six or more other primary diagnoses during the two year period. Näytä vähemmän

A roadmap for improving the productivity and efficacy of home care organizations (in Finnish)

The most expensive 10% of the population cause 81% of the costs of social and health care services funded by the city of Oulu. Of the costs of the most expensive 10% of the population, 62% are caused by people who are customers of at least one social service and 38% by people using only health care services. The most expensive 10% of the population use on average four different service types whereas the remaining 90% of the population use on average one type of service. The most expensive 10%… Näytä lisää

The most expensive 10% of the population cause 81% of the costs of social and health care services funded by the city of Oulu. Of the costs of the most expensive 10% of the population, 62% are caused by people who are customers of at least one social service and 38% by people using only health care services. The most expensive 10% of the population use on average four different service types whereas the remaining 90% of the population use on average one type of service. The most expensive 10% of the population are the main users of primary care ward services, psychiatric care services, and
secondary and tertiary health care services while the costs of other health care services (primary care outpatient services, emergency care and dental care services) are mainly caused by the remaining 90% of the population.

Because a small portion of the population causes the majority of the costs, the structure of the health care system and the service network should focus on the management of this group and the prevention of becoming a member of the group. The current system based on separate organizations for each service serves well the 90% of the population who use at most one type of service. However, it cannot respond to the needs of the high-cost 10% of the population. Because the expensive customers use many different services, the service combination should be individually planned, and there should be one party responsible for the coordination. Patient information should flow to and from the coordinator and between service providers. Näytä vähemmän