Revista de informática médica y de salud

Background: The prompt spread and advancements of mobile technologies has come to address health priorities in generating real time information for evidence based decisions and to improve timely response to emergencies. According to WHO’s Global Observatory for electronic Health survey; most frequently reported Mobile Health initiatives were: health call centres, emergency toll-free telephone services and mobile telemedicine. Sierra Leone was one of severely affected countries in Ebola Virus Disease outbreak 2014/15. Toll-free line, Walk-Ins and Community suspects were main case notification strategies nationally affected for identifying Ebola Virus Disease (EVD) suspected cases and deaths in the community. The main objective of this study was to assess the role of Toll-free line played in the response against Ebola Virus Disease outbreak. Method: The study was based on review of records in Ebola Virus Disease alert reports of Western Area Urban and Rural from 26th January to 28th June 2015. All Ebola Virus disease suspected case and death alert records were classified based on surveillance strategies; Toll-free telephone call, Walk-Ins and Community suspects. SPSS Version 20 was used for data analysis. One-way Analysis of Variance (ANOVA) test was applied to evaluate the difference in number of cases and deaths notified via these surveillance strategies. P-Value was calculated and P ≤ 0.05 was reported as having significant difference in generating more suspected cases and deaths by each EVD surveillance strategies. Result: The result showed that 11,303 alerts were registered in western area within 22 weeks. Out of which 7,059 (62%) of alerts were notified by Toll-free alert. One-way Analysis of Variance (ANOVA) revealed that Toll-free telephone call based surveillance was playing significantly higher; [F (2, 63)=184.76, p<0.0001] role in generating EVD suspected cases and deaths than Walk-Ins and Community suspect strategies. Conclusion: In conclusion, Toll-free telephone line has played significantly higher role in generating EVD suspected cases and deaths in the community. Lessons shall be adopted and scaled-up by all African nations and the world at large for rapid emergency responses; however, related challenges needs to be more investigated.

Optimization and experience with using EHRs may improve physician experiences. Physician opinions about EHR-related impacts, and the extent to which these impacts differ by self-reported optimized EHR use and length of experience are examined through nationally representative physician data of EHR users from the National Electronic Health Records Survey extended survey (n=1,471). Logistic regression models first estimated how physicians’ length of times using an EHR were associated with each EHR-related impact. Additionally, a similar set of models estimated the association of self-reported optimized EHR use with each EHR impact. At least 70% of physicians using EHRs continue to attribute their administrative burdens to their EHR use. Physicians with 4 or more years of EHR experience accounted for 58% of those using EHRs. About 71% of EHR users self-reported using an optimized EHR. Physicians with more EHR experience and those in practices that optimized EHR use had positive opinions about the impacts of using EHRs, compared to their counterparts. These findings suggest that longer experience with EHRs improves perceptions about EHR use; and that perceived EHR use optimization is crucial to identifying EHR-related benefits. Finding ways to reduce EHR-related administrative burden has yet to be addressed.

A feature selection technique is highly preferred preceding data classification to improve prediction performance especially in the high dimensional space. In general, filter techniques can be considered as essential or assistant selection system on account of their effortlessness, adaptability, and low computational many-sided quality. Nonetheless, a progression of inconsequential cases demonstrates that filter techniques result in less precise execution since they disregard the conditions of features. Albeit few publications have committed their regard for uncover the relationship of features by multivariate-based techniques, these strategies depict connections among elements just by linear techniques. While straightforward linear combination relationship limits the transformation in execution. In this paper, we utilized kernel method for svm-RFE with MRMR way to deal with find inalienable nonlinear connections among features and also amongst feature and target. So as to uncover the viability of our technique we played out a few analyses and thought about the outcomes between our technique and other aggressive multivariatebased features selectors. In our examination, we utilized three classifiers (support vector machine, neural system and average perceptron) on two gathering datasets, to be specific two-class and multi-class datasets (principally focused on svm). Exploratory results show that the execution of our technique is superior to anything others, particularly on three hard group datasets, to be specific Wang’s Breast Cancer, Gordon’s Lung Adenocarcinoma and Pomeroy’s Medulloblastoma. Note: Entire Implementation was developed with MS Machine learning studio.

Computer-aided detection (CAD) systems can be served as a second view for radiologist. An overview of recent development in CAD methods are presented in this paper. Abnormalities detection, abnormalities classification and content-based image retrieval (CBIR) are briefly reviewed. For the abnormalities detection, micro-calcification detection, mass detection and multi-view based detection are introduced. For the abnormalities classification, micro-calcification classification and mass classification are given.