Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
J Biomed Inform ; 104: 103393, 2020 04.
Artigo em Inglês | MEDLINE | ID: mdl-32087296

RESUMO

BACKGROUND AND OBJECTIVE: Published models predicting health related outcomes rely on clinical, claims and social determinants of health (SDH) data. Addressing the challenge of predicting with only SDH we developed a novel framework termed Stratified Cascade Learning (SCL) and used it for predicting the risk of hospitalization (ROH). MATERIALS AND METHODS: The variable set includes 27 SDH and "age" and "sex" for a cohort of diabetic patients. The SCL model uses three sub-models: SM1 (whole training set) stratifies training set into "predictable" and "unpredictable" subsets, SM2 (built on whole training set) classifies test set patients into "predictable" and "unpredictable", and SM3 (built on only the "predictable" subset) predicts the ROH for the patients classified as "predictable" by SM2. RESULTS: The SCL model does not improve either the AUC or the NPV of the basic classifier, but materially improves accuracy and specificity measures at the expense of lowering sensitivity for the "predictable" subset. Optimization of the risk thresholds of the sub-models does not noticeably change the AUC and NPV but further improves the accuracy and specificity at the expense of further lowering sensitivity. CONCLUSION: Since the SLC model yields low sensitivity it fails to predict high risk patients. But it yields high specificity that can be useful when the objective is to eliminate low-risk patients as candidates for further testing or treatment. The use of the SCL is not limited to healthcare, it can be applied to any predictive modeling problem when reliable predictions can only be made for a fraction of incoming data.


Assuntos
Hospitalização , Aprendizado de Máquina , Estudos de Coortes , Humanos , Fatores Socioeconômicos
2.
CNS Drugs ; 21(4): 319-34, 2007.
Artigo em Inglês | MEDLINE | ID: mdl-17381185

RESUMO

OBJECTIVE: Although the clinical benefits of pharmacological treatments for insomnia have been studied, no systematic assessment of their economic value has been reported. This analysis assessed, from a broad payer and societal perspective, the cost effectiveness of long-term treatment with eszopiclone (LUNESTA, Sepracor Inc., [Marlborough, MA, USA]) for chronic primary insomnia in adults in the US. METHODS: A decision analytical model was developed based on the reanalysis of a 6-month placebo-controlled trial, which demonstrated that eszopiclone 3mg significantly improved sleep and daytime function measures versus placebo in adults with primary insomnia. Patients were classified as either having remitted or not remitted from insomnia based upon a composite index of eight sleep and daytime function measures collected during the trial. These data were supplemented with quality-of-life and healthcare and lost productivity cost data from the published literature and medical and absenteeism claims databases. RESULTS: Compared with non-remitted patients, patients classified as remitted had lower monthly healthcare and productivity costs (in 2006 dollars) [a reduction of $US242 and $US182, respectively] and higher quality-adjusted life-year (QALY) weight (a net gain of 0.0810 on a scale ranging from 0 to 1). During the study, eszopiclone-treated patients were about 2.5 times more likely to have remitted than placebo-treated patients. Six months of eszopiclone treatment reduced direct (healthcare) and indirect (productivity) costs by an estimated $US245.13 and $US184.19 per patient, respectively. Eszopiclone use was associated with a cost of $US497.15 per patient over 6 months (including drug cost, dispensing fee, physician visit and time loss to receive care). Thus, after considering the above savings and the costs associated with eszopiclone treatment over 6 months, cost increased by $US252.02 (excluding productivity gains) and $US67.83 (including productivity gains) per person. However, eszopiclone treatment was also associated with a net QALY gain of 0.006831 per patient over the same period. Consequently, the incremental cost per QALY gained associated with eszopiclone was approximately $US9930 (including productivity gains [i.e. $US67.83 / 0.006831]) and $US36 894 (excluding productivity gains [i.e. $US252.02 / 0.006831]). Sensitivity analyses using a variety of scenarios suggested that eszopiclone is generally cost effective. CONCLUSIONS: This analysis suggested that long-term eszopiclone treatment was cost effective over the 6-month study period, particularly when the impact on productivity costs is considered. Given the increasing interest in new pharmacological interventions to manage insomnia, payers and clinicians alike should carefully consider the balance of health and economic benefits that these interventions offer. Accordingly, additional research in this area is warranted.


Assuntos
Custos e Análise de Custo , Hipnóticos e Sedativos/economia , Hipnóticos e Sedativos/uso terapêutico , Piperazinas/economia , Piperazinas/uso terapêutico , Distúrbios do Início e da Manutenção do Sono/tratamento farmacológico , Adulto , Idoso , Compostos Azabicíclicos , Feminino , Humanos , Assistência de Longa Duração , Masculino , Pessoa de Meia-Idade , Anos de Vida Ajustados por Qualidade de Vida , Sensibilidade e Especificidade , Resultado do Tratamento
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...