High-quality Metrics Research Articles

Socioecological Determinants of Health and the Quality of Colonoscopy in Rural Alabama.

Rural patients suffer higher incidence of and mortality from colorectal cancer. Ensuring high-quality screening is essential to address these disparities. To investigate whether socioecological determinants of health are associated with colonoscopy quality in rural Alabama. Retrospective review. Data across three rural hospitals in Alabama from August 2021 to July 2023. We included adults (≥18 years) who underwent screening or diagnostic colonoscopy and completed a validated survey that measures socioecological determinants of health. Primary outcomes included bowel preparation quality, cecal intubation, and adenoma detection rate. We linked th e survey responses to these quality metrics to identify factors associated with outcomes. Analyses included the χ 2, Fisher's Exact and Kruskal-Wallis Rank sum tests, with p < 0.05 considered statistically significant. The 84 patients surveyed were 66.7% male, 50.0% Black, and had a median age of 64 years. Optimal bowel preparation was present in 88.0%, 89.3% had successful cecal intubations, and overall adenoma detection rate was 45.8%. Patients with suboptimal bowel preparation described lower rates of internet access (60.0% vs. 87.4%, p < 0.05), more difficulty understanding written information (30.0% vs. 1.4%, p < 0.05) and lacked a sense of responsibility for their health (30.0% vs. 51.4%, p < 0.05) compared to those having optimal bowel preparation. Those with unsuccessful cecal intubations had lower physician-trust (55.6% vs. 73.3%, p < 0.05), while patients with successful cecal intubations were more confident in preventing health-related problems (53.3% vs. 33.3%, p < 0.05) and had a more supportive social environment (72.0% vs. 66.7%, p < 0.05). Retrospective design and small sample size limiting multivariable analyses. In rural Alabama, health literacy, internet access, and physician-trust were associated with low-quality colonoscopy, while a higher patient sense of responsibility and a supportive social environment was associated with higher-quality metrics. These findings identify potential targets for improving colonoscopy quality in rural settings. See Video Abstract.

Performance Management, Metric Quality, and Trust: Survey Evidence from Healthcare Organizations

We examine the impact of performance management (PM) and metric quality on trust and performance in healthcare organizations. Prior research found that PM can elicit feelings of distrust, as healthcare professionals can perceive control as curbing their autonomy. We examine whether the quality of metrics (i.e., their accuracy, sensitivity, and verifiability) can help PM to enhance interpersonal trust in healthcare settings. We mobilize self-determination theory (SDT) and argue that PM using high-quality metrics can address managers' needs for competence and autonomy, which in turn can impact interpersonal trust and unit performance. Using survey data from 152 middle managers in healthcare settings, we find that metric quality moderates the relationship between PM and interpersonal trust, which is subsequently positively linked with unit performance. Also, we find that action control and cultural control are positively associated with interpersonal trust. We complement literature on the control-trust nexus by highlighting the importance of metric quality, and by showing which forms of control can be instrumental in creating a high-trust work environment.

Quality and Readability Analysis of Turbinoplasty on the Web.

This study aimed to assess the quality, credibility, and readability of online health information concerning turbinoplasty, given the increasing reliance on internet resources for health education. Using four search terms related to turbinoplasty, we analyzed 71 text-based webpages from Google.com, Bing.com, and Yahoo.com. Readability was evaluated using the Flesch-Kincaid grade level, Gunning-Fog Index, SMOG Index, and Coleman-Liau Index were utilized. Web page quality was computed through the DISCERN Instrument (DISCERN), the Journal of the American Medical Association benchmark criteria (JAMA), Novel Turbinoplasty Index (NTI), and presence of code certification by Health on The Net (HON). Seventy-one text-based web pages were assessed. Information quality was measured by an average DISCERN score of 47.4±7.40, indicating "fair" quality. The average readability was a grade level of 9.7±1.57, notably higher than AMA and NIH recommendations. Of all web pages, only 11 (15.49%) proficiently met all 4 listed JAMA criteria. Significant correlations between web page classification and average DISCERN (P=0.0042), as well as JAMA score (P<0.001) were discovered. The web pages that had HON code certification revealed significantly higher quality metrics such as DISCERN scores (P<0.001), JAMA scores (P<0.001), and NTI scores (P=0.038). Online health information for turbinoplasty is of "fair" quality, and the average readability is several grade levels above current AMA and NIH recommendations. Health care providers should aim to guide their patients on finding appropriate educational resources and should improve the readability of their patient education materials.

Intelligent IoT-based Control System of the UAV for Meteorological Measurements

This study focuses on the creation and examination of an intelligent automated control system for UAVs utilized in meteorological measurements based on the Internet of Things (IoT) and mobile technologies. The proposed system enables the achievement of commendable flight control standards for UAVs during meteorological data gathering, thereby markedly enhancing the overall effectiveness of meteorological stations. Notably, this system is constructed on the foundation of three integrated principles: (a) a hierarchical two-level approach for control and data collection based on IoT and mobile technologies, (b) a straightforward and dependable fuzzy logic control characterized by high performance, and (c) the effective optimization of fuzzy control components through the application of bio-inspired multi-agent computing techniques. To assess the performance of the suggested intelligent system, this study involves the creation and bioinspired optimization of the climb speed fuzzy controller. Subsequent simulation experiments are conducted to evaluate the automatic control of UAV’s flight processes under different modes. The analysis of the simulation results indicates that the developed system, utilizing fuzzy control, exhibits superior efficiency and higher quality metrics when compared to existing counterparts, especially in diverse flight scenarios such as uniform climbing, gradual approach to designated altitude levels, and smooth landing during meteorological measurements.

Effects of the Construction of Granadilla Industrial Port in Seagrass and Seaweed Habitats Using Very-High-Resolution Multispectral Satellite Imagery

Seagrass and seaweed meadows hold a very important role in coastal and marine ecosystems. However, anthropogenic impacts pose risks to these delicate habitats. This paper analyses the multitemporal impact of the construction of the largest industrial port in the Canary Islands, near the Special Area of Conservation Natura 2000, on Cymodocea nodosa seagrass meadows (sebadales) of the South of Tenerife, in the locality of Granadilla (Canary Islands, Spain). Very-high-resolution WorldView-2 multispectral satellite data were used for the analysis. Specifically, three images were selected before, during, and after the construction of the port (2011, 2014, and 2022, correspondingly). Initially, advanced pre-processing of the images was performed, and then seabed maps were obtained using the machine learning K-Nearest Neighbors (KNN) supervised classification model, discriminating 12 different bottom types in Case-2 complex waters. The maps achieved high-quality metrics with Precision values of 85%, 81%, and 80%, recall of 76%, 77%, and 77%, and F1 scores of 80%, 79%, and 77% for 2011, 2014, and 2022, respectively. The results mainly show that the construction directly affected the seagrass and seaweed habitats. In particular, the impact of the port on the meadows of Cymodocea nodosa, Caulerpa prolifera, and maërl was assessed. The total maërl population was reduced by 1.9 km2 throughout the study area. However, the Cymodocea nodosa population was maintained at the cost of colonizing maërl areas. Furthermore, the port sedimented a total of 0.98 km2 of seabed, especially Cymodocea nodosa and maërl. In addition, it was observed that Caulerpa prolifera was established as a meadow at the entrance of the port, replacing part of the Cymodocea nodosa and maërl areas. As additional results, bathymetric maps were generated from satellite imagery with the Sigmoid model, and the presence of a submarine outfall was, as well, presented.

Technical performance metrics of a security operations center

This research introduces a novel framework for creating metrics intended for security operations centers (SOCs). The framework is developed using the design science research methodology and has been validated by generating four novel metrics to assess the technical performance of a SOC. Additionally, the study examines the existing landscape of metrics for SOCs and concludes that a majority of the metrics discussed in the literature primarily focus on operational aspects rather than technical performance. The absence of adequate technical performance metrics makes it challenging to accurately evaluate the tangible impact of a SOC on overall cyber defense capabilities. The research also highlights the insufficiency of current methods in constructing metrics and frameworks tailored for measuring SOCs' technical performance. The resulting framework offers SOCs means to create high-quality metrics for performance evaluation. Furthermore, the metrics the framework was validated with offer SOCs an opportunity to enhance their ability to quantify their threat detection capabilities.

MENLI: Robust Evaluation Metrics from Natural Language Inference

AbstractRecently proposed BERT-based evaluation metrics for text generation perform well on standard benchmarks but are vulnerable to adversarial attacks, e.g., relating to information correctness. We argue that this stems (in part) from the fact that they are models of semantic similarity. In contrast, we develop evaluation metrics based on Natural Language Inference (NLI), which we deem a more appropriate modeling. We design a preference-based adversarial attack framework and show that our NLI based metrics are much more robust to the attacks than the recent BERT-based metrics. On standard benchmarks, our NLI based metrics outperform existing summarization metrics, but perform below SOTA MT metrics. However, when combining existing metrics with our NLI metrics, we obtain both higher adversarial robustness (15%–30%) and higher quality metrics as measured on standard benchmarks (+5% to 30%).

EURObservational Research Programme: a bibliometric assessment of its scientific output.

Given the lack of reliable observational data, a network of volunteer centres, and standardized methodological procedures, the European Society of Cardiology EURObservational Research Programme (EORP) was set up to provide a better understanding of real-world cardiovascular care and outcomes. We aimed to evaluate the scientific impact of EORP using a bibliometric approach. We collected data for each individual publication and for each individual journal with at least one EORP publication. Bibliometric indicators evaluating research performance were categorized into those evaluating EORP publications (publication-based indicators) and those assessing the journals where those papers were published (journal-based indicators). During the first ∼11 years since its inception, we found that EORP produced 189 publications, with most published in journals in the first quartile (60.9%) or the second quartile (33.5%) of the Web of Science Journal Citation Report. The total number of citations to EORP publications was 9630 (average citation per publication of 51, h-index of 54, and 29 EORP publications with ≥100 citations). Of EORP publications, 20 had an Altmetric Attention Score >50 and 9 had a score >100. A total of 52 EORP papers have been cited 65 times in ESC Clinical Practice Guidelines between 2013 and 2021. EORP registries have contributed to impactful scientific knowledge. The high-quality metrics highlight the relevance of the EORP international cardiovascular registries to the academic community. Efforts are needed to support this, and other programmes aimed at delivering real-world evidence from independent patient data of cardiovascular care and outcomes across multiple geographies.

Machine learning for predicting 5-year mortality risks: data from the ESSE-RF study in Primorsky Krai

Aim. To develop and perform comparative assessment of the accuracy of models for predicting 5-year mortality risks according to the Epidemiology of Cardiovascular Diseases and their Risk Factors in Regions of Russian Federation (ESSE-RF) study in Primorsky Krai.Material and methods. The study included 2131 people (1257 women and 874 men) aged 23-67 years with a median of 47 years (95% confidence interval [46; 48]). The study protocol included measurement of blood pressure (BP), heart rate (HR), waist circumference, hip circumference, and waist-to-hip ratio (WHR). The following blood biochemical parameters: total cholesterol (TC), low and high density lipoprotein cholesterol, triglycerides, apolipoproteins AI and B, lipoprotein(a), N-terminal pro-brain natriuretic peptide (NT-proNBP), D-dimer, fibrinogen, C-reactive protein (CRP), glucose, creatinine, uric acid. The study endpoint was 5-year all-cause death (2013-2018). The group of deceased patients during this period consisted of 42 (2%) people, while those continued the study — 2089 (98%). The χ2, Fisher and MannWhitney tests, univariate logistic regression (LR) were used for data processing and analysis. To build predictive models, we used following machine learning (ML) methods: multivariate LR, Weibull regression, and stochastic gradient boosting.Results. The prognostic models developed on the ML basis, using parameters of age, sex, smoking, systolic blood pressure (SBP) and TC level in their structure, had higher quality metrics than Systematic COronary Risk Evaluation (SCORE) system. The inclusion of CRP, glucose, NT-proNBP, and heart rate into the predictors increased the accuracy of all models with the maximum rise in quality metrics in the multivariate LR model. Predictive potential of other factors (WHR, lipid profile, fibrinogen, D-dimer, etc.) was low and did not improve the prediction quality. An analysis of the influence degree of individual predictors on the mortality rate indicated the prevailing contribution of five factors as follows: age, levels of TC, NT-proNBP, CRP, and glucose. A less noticeable effect was associated with the level of HR, SBP and smoking, while the contribution of sex was minimal.Conclusion. The use of modern ML methods increases the accuracy of predictive models and provides a higher efficiency of risk stratification, especially among individuals with a low and moderate death risk from cardiovascular diseases.

Future of food: Innovating towards sustainable healthy diets

Future of food: Innovating towards sustainable healthy diets

DE-STRESS: a user-friendly web application for the evaluation of protein designs.

De novo protein design is a rapidly growing field, and there are now many interesting and useful examples of designed proteins in the literature. However, most designs could be classed as failures when characterised in the lab, usually as a result of low expression, misfolding, aggregation or lack of function. This high attrition rate makes protein design unreliable and costly. It is possible that some of these failures could be caught earlier in the design process if it were quick and easy to generate information and a set of high-quality metrics regarding designs, which could be used to make reproducible and data-driven decisions about which designs to characterise experimentally.We present DE-STRESS (DEsigned STRucture Evaluation ServiceS), a web application for evaluating structural models of designed and engineered proteins. DE-STRESS has been designed to be simple, intuitive to use and responsive. It provides a wealth of information regarding designs, as well as tools to help contextualise the results and formally describe the properties that a design requires to be fit for purpose.

Automatic catalog of RR Lyrae from ∼14 million VVV light curves: How far can we go with traditional machine-learning?

Context. The creation of a 3D map of the bulge using RR Lyrae (RRL) is one of the main goals of the VISTA Variables in the Via Lactea Survey (VVV) and VVV(X) surveys. The overwhelming number of sources undergoing analysis undoubtedly requires the use of automatic procedures. In this context, previous studies have introduced the use of machine learning (ML) methods for the task of variable star classification. Aims. Our goal is to develop and test an entirely automatic ML-based procedure for the identification of RRLs in the VVV Survey. This automatic procedure is meant to be used to generate reliable catalogs integrated over several tiles in the survey. Methods. Following the reconstruction of light curves, we extracted a set of period- and intensity-based features, which were already defined in previous works. Also, for the first time, we put a new subset of useful color features to use. We discuss in considerable detail all the appropriate steps needed to define our fully automatic pipeline, namely: the selection of quality measurements; sampling procedures; classifier setup, and model selection. Results. As a result, we were able to construct an ensemble classifier with an average recall of 0.48 and average precision of 0.86 over 15 tiles. We also made all our processed datasets available and we published a catalog of candidate RRLs. Conclusions. Perhaps most interestingly, from a classification perspective based on photometric broad-band data, our results indicate that color is an informative feature type of the RRL objective class that should always be considered in automatic classification methods via ML. We also argue that recall and precision in both tables and curves are high-quality metrics with regard to this highly imbalanced problem. Furthermore, we show for our VVV data-set that to have good estimates, it is important to use the original distribution more abundantly than reduced samples with an artificial balance. Finally, we show that the use of ensemble classifiers helps resolve the crucial model selection step and that most errors in the identification of RRLs are related to low-quality observations of some sources or to the increased difficulty in resolving the RRL-C type given the data.

Older adults’ understanding of hypothetical community pharmacy quality report cards

BackgroundQuality ratings for health plans and health services have become increasingly available to patients. ObjectiveWe sought to explore older adults’ understanding of hypothetical community pharmacy report cards and the information they valued on the report card. MethodsWe recruited participants aged 50 years or older to complete a 59-question telephone survey. The participants reviewed 3 different pairs of report cards, which represented a hypothetical pharmacy, and each pair contained different quality metrics. The participants identified which pharmacy of the pair they preferred, and this served as the primary outcome. We asked the participants to rate the level of importance (4-point unidirectional scale, not at all to very important) of the star ratings, source of information, and quality metrics. We also gathered information about the participants personal experiences with medications and pharmacy services, their self-reported health, health literacy, health numeracy, and demographics. The frequency that the pharmacy with higher quality metrics was selected was reported. We used logistic regression to examine factors associated with correctly identifying the highest quality pharmacy for all 3 sets of report cards. ResultsMost participants (n = 152) correctly identified all 3 (n = 120, 79.0%) report cards for pharmacies with higher quality metrics. The source of the information, individual quality metrics, and star ratings were all perceived as moderately or very important by most participants. Ratings of importance were strongly correlated (r, 0.70–1.00). ConclusionMore than 75% were able to correctly identify all 3 report cards with higher quality ratings. Most participants believed that the source of the information, the individual quality metrics, and the star rating were all important. Research is needed to explore to what extent patients would use these types of quality metric report cards to make decisions about where to obtain their medications.

Aquatic macroinvertebrate richness and diversity associated with native submerged aquatic vegetation plantings increases in longer-managed and wetland-channeled effluent constructed urban wetlands

Macroinvertebrate community structure and assemblages associated with the planted, native submerged aquatic vegetation (SAV) species Heteranthera dubia (Jacq.) MacMillan and Potamogeton nodosus Poiret were examined in a series of constructed urban floodway wetlands, the Dallas Floodway Extension Lower Chain of Wetlands, Dallas, TX, USA. Macroinvertebrate community metrics, including abundance, richness, diversity, and evenness associated with SAV and three different wetlands of varying construction completion dates, water sources (direct or wetland-channeled wastewater effluent), and ecosystem management stage (established/reference or developing) were compared and analyzed. Assemblages at sampling sites were also classified and related to vegetation and wetland physicochemical parameters. Plant species affected only macroinvertebrate abundance, with the less-dissected P. nodosus supporting higher counts than H. dubia. Wetland age and water-effluent type had the most substantial effect on macroinvertebrate communities. The older, longer-managed wetland and wetland-channeled effluent habitat consistently demonstrated higher quality metrics and biodiversity than newly constructed, direct effluent wetland habitat. Increased vegetation cover and wetland age, coupled with moderate water temperature, pH, and DO levels were characteristics of more rich and diverse macroinvertebrate communities, including pollutant-sensitive taxa, such as Ephemeroptera and Trichoptera.

An adaptive minimum-maximum value-based weighted median filter for removing high density salt and pepper noise in medical images

This paper presents an adaptive minimum-maximum value-based weighted median (AMMWM) filter that effectively restores noisy pixel in medical images at high noise density. The proposed filter computes two highly correlated groups of noise-free pixels using minimum and maximum value of the current window. Further, weighted medians of these groups determine the estimated value of candidate noisy pixel. If the current window fails to provide any noise-free pixels, its size is increased by one. The maximum size of window considered is 7 × 7 to minimise blurring. The proposed AMMWM filter is evaluated on various medical images where it provides higher quality metrics while preserving image features even at higher noise density. The simulation results using X-ray images show on an average 0.3 dB and 3.56 dB higher value of PSNR for wide (10%-90%) and very high (91%-98%) noise density ranges respectively.

Attenuated total reflection Fourier-transform infrared spectral discrimination in human bodily fluids of oesophageal transformation to adenocarcinoma.

Diagnostic tools for the detection of early-stage oesophageal adenocarcinoma (OAC) are urgently needed. Our aim was to develop an accurate and inexpensive method using biofluids (plasma, serum, saliva or urine) for detecting oesophageal stages through to OAC (squamous; inflammatory; Barrett's; low-grade dysplasia; high-grade dysplasia; OAC) using attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy. ATR-FTIR spectroscopy coupled with variable selection methods, with successive projections or genetic algorithms (GA) combined with quadratic discriminant analysis (QDA) were employed to identify spectral biomarkers in biofluids for accurate diagnosis in a hospital setting of different stages through to OAC. Quality metrics (Accuracy, Sensitivity, Specificity and F-score) and biomarkers of disease were computed for each model. For plasma, GA-QDA models using 15 wavenumbers achieved 100% classification for four classes. For saliva, PCA-QDA models achieved 100% for the inflammatory stage and high-quality metrics for other classes. For serum, GA-QDA models achieved 100% performance for the OAC stage using 13 wavenumbers. For urine, PCA-QDA models achieved 100% performance for all classes. Selected wavenumbers using a Student's t-test (95% confidence interval) identified a differentiation of the stages on each biofluid: plasma (929 cm-1 to 1431 cm-1, associated with DNA/RNA and proteins); saliva (1000 cm-1 to 1150 cm-1, associated with DNA/RNA region); serum (1435 cm-1 to 1573 cm-1, associated with methyl groups of proteins and Amide II absorption); and, urine (1681 cm-1 to 1777 cm-1, associated with a high frequency vibration of an antiparallel β-sheet of Amide I and stretching vibration of lipids). Our methods have demonstrated excellent efficacy for a rapid, cost-effective method of diagnosis for specific stages to OAC. These findings suggest a potential diagnostic tool for oesophageal cancer and could be translated into clinical practice.

Lessons learned from the Canadian cancer registry experience.

Health leaders and caregivers are focused on evidence-based data to drive care delivery and practice. Ensuring the health system is functioning effectively and efficiently and that patient outcomes are reaching expected targets are topics that permeate conversations at the local, provincial, and national levels. However, as many leaders have come to understand in recent years, healthcare data collection and producing meaningful, high-quality metrics is a complex set of tasks, requiring its own level of attention and dedicated resources. In the healthcare data realm, there are opportunities to learn from experience. One of these opportunities is the population-based cancer registry, which is one of the oldest examples of standardized data collection in the Canadian health system.

Abstract 2923: Label-free enrichment and integrated full-length mRNA transcriptome analysis of single live circulating tumor cells from breast cancer patients

Abstract Background Label-free methods for isolating circulating tumor cells (CTCs) are attractive because they provide an opportunity to analyze a larger set of CTCs that may otherwise be missed due to variable or no expression of protein (label) markers. Understanding genetic and functional heterogeneity in CTCs allows us to gain insight into the mechanisms underscoring metastasis, drug resistance, and tumor aggressiveness. Currently, a simple workflow for isolation and molecular characterization of single CTCs by mRNA sequencing is lacking. In order to address this challenge, we developed a label-free workflow to isolate CTCs from breast cancer patients for full-length mRNA sequencing analysis by integrating the ClearCell® FX System with the Polaris™ system. The ClearCell FX system processes blood samples from cancer patients and enriches for CTCs in a label-free antibody-independent manner. The low level of nonspecifically isolated white blood cells from ClearCell FX is further depleted on the Polaris system by negative enrichment of viable CTCs. This unique integration of systems will enable researchers to perturb single CTCs in a controlled environment, monitor and measure the response due to perturbation, and link these response measurements to downstream genomic and transcriptomic analysis. Method and Results CTCs from 7.5 mL of peripheral blood sample from breast cancer patients were enriched using ClearCell FX. To differentiate larger blood cells from putative CTCs, we stained the enriched cells with Alexa Fluor® 647-conjugated CD45 and CD31 to identify leukocytes and endothelial cells, respectively. Calcein AM (live cell marker) and CellTracker™ Orange (universal cell marker) were added to identify live cells. Single CTCs were selected on Polaris (Fluidigm) system, lysed and reverse-transcribed, and cDNA were preamplified on the Polaris integrated fluidic circuit (IFC). Sequencing libraries were generated using the Nextera® kit and sequenced on Illumina® MiSeq™ and NextSeq™ systems. We successfully processed blood samples from four patients. Sequenced data showed high-quality metrics, with read depth of up to 2.5 million reads (MiSeq) or 60 million reads (NextSeq), with a low percentage of mapped reads to ribosomal RNA and mitochondrial RNA. Unsupervised hierarchical clustering of gene expression data showed clustering by patient, but considerable heterogeneity was also observed among the CTCs from the same patient. We will provide insights into full-length mRNA transcriptome of single CTCs from triple negative breast cancer patient. Conclusion We present the feasibility of integrating two microfluidics platforms to capture single CTCs for transcriptome and functional study. Our data suggests that the heterogeneity of tumor sample and characterization of metastatic processes can be elucidated from single-cell mRNA sequencing of CTCs. Citation Format: Naveen Ramalingam, Yi Fang Lee, Lukasz Szpankowski, Anne Leyrat, Brian Fowler, Jovina Tan, Chong Tracy Lu, Ninez Delos Angeles, Chad Sanada, Cassandra Greene, Kyle Hukari, Andrew Wu, Yoon-Sim Yap, Jay West, Ali Asgar Bhagat. Label-free enrichment and integrated full-length mRNA transcriptome analysis of single live circulating tumor cells from breast cancer patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr 2923. doi:10.1158/1538-7445.AM2017-2923

A Case Study of Visit-Driven Preventive Care Screening Using Clinical Decision Support: The Need to Redesign Preventive Care Screening.

Introduction:In the traditional model of care, an annual visit was dedicated to the task of assessing and delivering preventive care. With the move away from annual physicals, primary care physicians are addressing preventive services at every clinic visit often aided by electronic clinical decision support (CDS) systems.Methods:We conducted a case study of a visit-driven CDS system in use at a primary care clinic. Steady-state performance was assessed via control charts of quality metrics, data regarding completion of recommendations, and an analysis of screening intervals achieved with patient visits.Results:Under this visit-driven CDS system, quality metric performance was poor and declining. Almost half of the patients were not screened (46.5%), and the other half were overscreened the majority of the time (83.3%). Recommended preventive services were ordered less than half the time (42.6%), despite CDS reminders.Discussion:Various barriers and systematic inefficiencies combined to produce ineffective screening in this visit-driven CDS preventive service delivery system. As a result, we conclude a visit-driven system cannot produce optimal results. In order to improve performance, preventive services should be delivered separately from clinical visits, perhaps by a “preventive service ranger” (PSR) utilizing the CDS system to review each patient once annually. Under such a system, patients would receive preventive services in an organized and efficient fashion, potentially leading to better continuity, higher quality metrics that are mathematically predictable, and improved satisfaction.

Constraining and summarizing association rules in medical data

Association rules are a data mining technique used to discover frequent patterns in a data set. In this work, association rules are used in the medical domain, where data sets are generally high dimensional and small. The chief disadvantage about mining association rules in a high dimensional data set is the huge number of patterns that are discovered, most of which are irrelevant or redundant. Several constraints are proposed for filtering purposes, since our aim is to discover only significant association rules and accelerate the search process. A greedy algorithm is introduced to compute rule covers in order to summarize rules having the same consequent. The significance of association rules is evaluated using three metrics: support, confidence and lift. Experiments focus on discovering association rules on a real data set to predict absence or existence of heart disease. Constraints are shown to significantly reduce the number of discovered rules and improve running time. Rule covers summarize a large number of rules by producing a succinct set of rules with high-quality metrics.