The effect of smart homes on older adults with chronic conditions: A systematic review and meta-analysis.

As populations continue to age, the prevalence of multiple chronic conditions in older adults grows. The purpose of this study was to evaluate the effect of smart homes on older patients with chronic conditions. A review and meta-analysis were conducted after searching both English and Chinese databases. Fifteen RCTs were included in the review, with six studies qualifying for the meta-analysis. The meta-analysis revealed no significant effects on measures of hospital admissions (RR =0.90, 95% CI (0.57, 6.34), P = 0.65) or emergency department admissions (RR =0.99, 95% CI (0.34, 2.91), P = 0.98). Likewise, no effects were observed for tele-monitoring on days spent in the hospital (MD =-0.90, 95% CI (-3.34, 1.55), P = 0.47) or quality of life. However, almost all participants were satisfied with the smart homes. The effect of tele-exercise on cognitive functioning was unclear. However, the smart homes did have an effect on physical functioning and depression in older adults with chronic conditions. Future studies should focus on the economic effectiveness, security, accessibility and practicality of smart homes on older adults with chronic conditions.

Model-independent evaluation of tumor markers and a logistic-tree approach to diagnostic decision support.

Sensitivity and specificity of using individual tumor markers hardly meet the clinical requirement. This challenge gave rise to many efforts, e.g., combing multiple tumor markers and employing machine learning algorithms. However, results from different studies are often inconsistent, which are partially attributed to the use of different evaluation criteria. Also, the wide use of model-dependent validation leads to high possibility of data overfitting when complex models are used for diagnosis. We propose two model-independent criteria, namely, area under the curve (AUC) and Relief to evaluate the diagnostic values of individual and multiple tumor markers, respectively. For diagnostic decision support, we propose the use of logistic-tree which combines decision tree and logistic regression. Application on a colorectal cancer dataset shows that the proposed evaluation criteria produce results that are consistent with current knowledge. Furthermore, the simple and highly interpretable logistic-tree has diagnostic performance that is competitive with other complex models.

Identifying a small set of marker genes using minimum expected cost of misclassification.

OBJECTIVES: This paper presents a model independent feature selection approach to identify a small subset of marker genes. METHODS AND MATERIAL: An evaluation measure, minimum expected cost of misclassification (MEMC), is used to estimate the discriminative power of a feature subset without building a model. The MECM measure is combined with sequential forward search for feature selection. This approach was applied to a breast cancer profiling problem, with the goal of identifying a small number of marker genes whose expression can be used to predict cancer molecular subtype (p53 gene status). Furthermore, the method was also applied to find a small set of single-nucleotide polymorphisms (SNPs) that can be used to predict molecular phenotype of a different type, namely alleles (genetic variants) of human leukocyte antigen genes that play an important roles in autoimmunity. RESULTS: Two marker genes were identified based on p53 status, which achieved a p-value of 7.53×10(-5) (vs. 6×10(-4) with 32 genes identified by previous research) in survival analysis. Six SNP loci were identified that achieved a leave-one-out cross-validation accuracy of 92.8% (vs. 90.6% and 89.5% with 18 SNPs selected using χ2 statistics and information gain, respectively). CONCLUSION: The MECM-based feature selection approach is capable of identifying a smaller subset of market genes with comparable or even better performance than that obtained using conventional filter methods.

Dimensionality reduction for knowledge discovery in medical claims database: application to antidepressant medication utilization study.

Data mining, through its capacity to discover knowledge embedded in large databases to improve organizational decision-making, has the potential to contribute to efficiencies and cost savings in the increasingly costly healthcare industry. One important aspect of the methods of mining medical databases includes reducing dimensionality through feature selection. Traditionally feature selection is accomplished through stepwise regression, which tends to produce an unnecessarily high number of "significant" variables. This paper applies a filter-based feature selection method using inconsistency rate measure and discretization, to a medical claims database to predict the adequacy of duration of antidepressant medication utilization. Compared to traditional stepwise logistic regression, which selected seven variables from a total of nine potential explanatory variables to characterize patients with inadequate antidepressant medication utilization, the filter-based method selected two variables (age and number of claims) to achieve a similar prediction accuracy. This comparison suggests it may be feasible and efficient to apply the filter-based feature selection method to reduce the dimensionality of healthcare databases.

Identification of factors predicting response to adjuvant radiation therapy in patients with positive margins after radical prostatectomy.

PURPOSE: Radical prostatectomy (RP) is a highly effective treatment for patients with prostate cancer. However, patients with positive surgical margins after radical prostatectomy have less than ideal outcomes with 5-year progression rates between 36% and 50%. Postoperative radiation therapy (RT) is often advocated for improving these outcomes. We identified predictors of response to adjuvant RT given for positive margins after RP. MATERIALS AND METHODS: We retrospectively reviewed the clinical records of men who underwent RP between 1987 and 1999 at our institution and who received adjuvant RT for positive surgical margins. Only patients in whom prostate specific antigen (PSA) was undetectable after RP as well as before the initiation of RT were included. Numerous clinicopathological variables, including pre-RP PSA, pathological stage, margin length and location, and extracapsular extension or seminal vesicle involvement, were assessed for their adverse effect on the biochemical recurrence rate after adjuvant RT. RESULTS: A total of 62 men met our inclusion criteria. Median age at surgery was 60.7 +/- 6.1 years and median PSA at presentation was 9.0 ng/ml (range 1.4 to 64.9). The median RT dose was 60.0 +/- 3.6 Gy. RT was started a median of 5.0 +/- 3.6 months after RP. The 5 and 10-year biochemical disease-free survival rates for the whole group were 90.2% and 87.9%, respectively. Of all parameters tested only Gleason score 4 + 3 or greater (p = 0.037) and pre-RP PSA greater than 10.9 ng/ml (p = 0.040) were predictive of biochemical recurrence after adjuvant RT on univariate analysis. On multivariate analysis only pre-RP PSA greater than 10.9 ng/ml remained an independent predictor (p = 0.031). CONCLUSIONS: In the setting of true adjuvant RT in patients with positive margins after RP and undetectable PSA those with predominant Gleason grade 4 or greater, or PSA greater than 10.9 ng/ml at presentation are at increased risk for recurrence after adjuvant RT.