Crowd-based requirements elicitation via pull feedback: method and case studies.

Crowd-based Requirements Engineering (CrowdRE) promotes the active involvement of a large number of stakeholders in RE activities. A prominent strand of CrowdRE research concerns the creation and use of online platforms for a crowd of stakeholders to formulate ideas, which serve as an additional input for requirements elicitation. Most of the reported case studies are of small size, and they analyze the size of the crowd, rather than the quality of the collected ideas. By means of an iterative design that includes three case studies conducted at two organizations, we present the CREUS method for crowd-based elicitation via user stories. Besides reporting the details of these case studies and quantitative results on the number of participants, ideas, votes, etc., a key contribution of this paper is a qualitative analysis of the elicited ideas. To analyze the quality of the user stories, we apply criteria from the Quality User Story framework, we calculate automated text readability metrics, and we check for the presence of vague words. We also study whether the user stories can be linked to software qualities, and the specificity of the ideas. Based on the results, we distill six key findings regarding CREUS and, more generally, for CrowdRE via pull feedback.

Combining Supervised and Unsupervised Machine Learning Methods for Phenotypic Functional Genomics Screening.

There has been an increase in the use of machine learning and artificial intelligence (AI) for the analysis of image-based cellular screens. The accuracy of these analyses, however, is greatly dependent on the quality of the training sets used for building the machine learning models. We propose that unsupervised exploratory methods should first be applied to the data set to gain a better insight into the quality of the data. This improves the selection and labeling of data for creating training sets before the application of machine learning. We demonstrate this using a high-content genome-wide small interfering RNA screen. We perform an unsupervised exploratory data analysis to facilitate the identification of four robust phenotypes, which we subsequently use as a training set for building a high-quality random forest machine learning model to differentiate four phenotypes with an accuracy of 91.1% and a kappa of 0.85. Our approach enhanced our ability to extract new knowledge from the screen when compared with the use of unsupervised methods alone.

HC StratoMineR: A Web-Based Tool for the Rapid Analysis of High-Content Datasets.

High-content screening (HCS) can generate large multidimensional datasets and when aligned with the appropriate data mining tools, it can yield valuable insights into the mechanism of action of bioactive molecules. However, easy-to-use data mining tools are not widely available, with the result that these datasets are frequently underutilized. Here, we present HC StratoMineR, a web-based tool for high-content data analysis. It is a decision-supportive platform that guides even non-expert users through a high-content data analysis workflow. HC StratoMineR is built by using My Structured Query Language for storage and querying, PHP: Hypertext Preprocessor as the main programming language, and jQuery for additional user interface functionality. R is used for statistical calculations, logic and data visualizations. Furthermore, C++ and graphical processor unit power is diffusely embedded in R by using the rcpp and rpud libraries for operations that are computationally highly intensive. We show that we can use HC StratoMineR for the analysis of multivariate data from a high-content siRNA knock-down screen and a small-molecule screen. It can be used to rapidly filter out undesirable data; to select relevant data; and to perform quality control, data reduction, data exploration, morphological hit picking, and data clustering. Our results demonstrate that HC StratoMineR can be used to functionally categorize HCS hits and, thus, provide valuable information for hit prioritization.

Efficiency of Clinical Decision Support Systems Improves with Experience.

Efficiency, or the resources spent while performing a specific task, is widely regarded as one the determinants of usability. In this study, the authors hypothesize that having a group of users perform a similar task over a prolonged period of time will lead to improvements in efficiency of that task. This study was performed in the domain of decision-supported medication reviews. Data was gathered during a randomized controlled trial. Three expert teams consisting of an independent physician and an independent pharmacist conducted 150 computerized medication reviews on patients in 13 general practices located in Amsterdam, the Netherlands. Results were analyzed with a linear mixed model. A fixed effects test on the linear mixed model showed a significant difference in the time required to conduct medication reviews over time; F(31.145) = 14.043, p < .001. The average time in minutes required to conduct medication reviews up to the first quartile was M = 20.42 (SD = 9.00), while the time from the third quartile up was M = 9.81 (SD = 6.13). This leads the authors to conclude that the amount of time users needed to perform similar tasks decreased significantly as they gained experience over time.

Computerized Decision Support Improves Medication Review Effectiveness: An Experiment Evaluating the STRIP Assistant's Usability.

BACKGROUND: Polypharmacy poses threats to patients' health. The Systematic Tool to Reduce Inappropriate Prescribing (STRIP) is a drug optimization process for conducting medication reviews in primary care. To effectively and efficiently incorporate this method into daily practice, the STRIP Assistant--a decision support system that aims to assist physicians with the pharmacotherapeutic analysis of patients' medical records--has been developed. It generates context-specific advice based on clinical guidelines. OBJECTIVE: The aim of this study was to validate the STRIP Assistant's usability as a tool for physicians to optimize medical records for polypharmacy patients. METHODS: In an online experiment, 42 physicians were asked to optimize medical records for two comparable polypharmacy patients, one in their usual manner and one using the STRIP Assistant. Changes in effectiveness were measured by comparing respondents' optimized medicine prescriptions with medication prepared by an expert panel of two geriatrician-pharmacologists. Efficiency was operationalized by recording the time the respondents took to optimize the two cases. User satisfaction was measured with the System Usability Scale (SUS). Independent and paired t tests were used for analysis. RESULTS: Medication optimization significantly improved with the STRIP Assistant. Appropriate decisions increased from 58% without the STRIP Assistant to 76% with it (p < 0.0001). Inappropriate decisions decreased from 42% without the STRIP Assistant to 24% with it (p < 0.0001). Participants spent significantly more time optimizing medication with the STRIP Assistant (24 min) than without it (13 min; p < 0.0001). They assigned it a below-average SUS score of 63.25. CONCLUSION: The STRIP Assistant improves the effectiveness of medication reviews for polypharmacy patients.

General practitioners' attitudes towards decision-supported prescribing: an analysis of the Dutch primary care sector.

The use of multiple drugs by patients increases the risk of medical problems. Clinical decision support could assist general practitioners with prescribing but is underused. This article aims to investigate the attitudes of general practitioners towards using decision support systems. A survey was distributed among 500 Dutch general practitioners. Virtually all 184 respondents indicated having a clinical information system, while only 21 percent indicated having a decision support plug-in; this correlated with their use of medical formularies. Only use of one of the medical formularies correlated with the number of recognized underprescription problems. General practitioners' attitudes toward a newly proposed system aiding them with polypharmacy prescribing were mainly positive (57%); the perceived usefulness correlated with output quality (p = .000), time investment (p = .000), and financial stimuli (payability: p = .000 and reimbursement: p = .015) but not with job relevance. Dutch general practitioners are thus likely to adopt the proposed system under the conditions that it improves prescription quality and does not require extensive investments of time or money.

A situational alignment framework for PACS.

This paper reports the outcomes of a study on an integrated situational alignment framework for picture archiving and communication systems (PACS) labeled as PISA. Following the design research cycle, complementary validation methods and pilot cases were used to assess the proposed framework and its operationalized survey. In this paper, the authors outline (a) the process of the framework' development, (b) the validation process with its underlying iterative steps, (c) the outcomes of pilot cases, and (d) improvement opportunities to refine and further validate the PISA framework. Results of this study support empirical application of the framework to hospital enterprises in order to gain insights into their PACS maturity and alignment. We argue that the framework can be applied as a valuable tool for assessments, monitoring and benchmarking purposes and strategic PACS planning.

AmI in good care? Developing design principles for ambient intelligent domotics for elderly.

The combination of ambient intelligence (AmI) and domotics has the potential to respond to elderly people's desire to live independent from extensive forms of care. Their slow adoption of technological aids shows reluctance, though. This article investigates their motivations to adopt ambient intelligent domotics, and proposes design principles specifically based on their preferences and experiences. Respondents appeared to be more acceptive of tangible problems they expected with AmI domotics than intangible ones. In addition, their opinions seemed to be profoundly influenced by the way they perceived their psychological quality of life, while their physical conditions did not seem to have noticeable impacts.