A Predefined Rule-Based Multi-Factor Risk Stratification Is Associated With Improved Outcomes at a Rural Primary Care Practice.

This study built a predefined rule-based risk stratification paradigm using 19 factors in a primary care setting that works with rural communities. The factors include medical and nonmedical variables. The nonmedical variables represent 3 demographic attributes and one other factor represents transportation availability. Medical variables represent major clinical variables such as blood pressure and BMI. Many risk stratification models are found in the literature but few integrate medical and nonmedical variables, and to our knowledge, no such model is designed specifically for rural communities. The data used in this study contain the associated variables of all medical visits in 2021. Data from 2022 were used to evaluate the model. After our risk stratification model and several interventions were adopted in 2022, the percentage of patients with high or medium risk of deteriorating health outcomes dropped from 34.9% to 24.4%, which is a reduction of 30%. The medium-complex patient population size, which had been 29% of all patients, decreased by about 4% to 5.7%. According to the analysis, the total risk score showed a strong correlation with 3 risk factors: dual diagnoses, the number of seen providers, and PHQ9 (0.63, 0.54, and 0.45 correlation coefficients, respectively).

Innovate and Validate: Design-Led Simulation Optimization to Test Centralized Registration Feasibility in a Multispecialty Clinic.

OBJECTIVE: This study utilizes a design-led simulation-optimization process (DLSO) to refine a hybrid registration model for a free-standing outpatient clinic. The goal is to assess the viability of employing DLSO for innovation support and highlight key factors influencing resource requirements. BACKGROUND: Manual registration in healthcare causes delays, impacting patient services and resource allocation. This study addresses these challenges by optimizing a hybrid centralized registration and adopting technology for efficiency. METHOD: An iterative methodology with simulation optimization was designed to test a proof of concept. Configurations of four and five registration options within a hybrid centralized system were explored under preregistration adoption rates of 30% and 50%. Three self-service kiosks served as a baseline during concept design and test fits. RESULTS: Centralized registration accommodated a daily throughput of 2,000 people with a 30% baseline preregistration rate. Assessing preregistration impact on seating capacity showed significant reductions in demand and floor census. For four check-in stations, a 30%-50% preregistration increase led to a 32% seating demand reduction and a 26% decrease in maximum floor census. With five stations, a 50% preregistration reduced seating demand by 23% and maximum floor census by 20%. CONCLUSION: Innovating introduces complexity and uncertainties requiring buy-in from diverse stakeholders. DLSO experimentation proves beneficial for validating novel concepts during design.

Treatment of Internal Mammary Nodes is Associated With Improved Overall Survival in Breast Cancer: A Meta-Analysis.

INTRODUCTION: The role of internal mammary nodal irradiation (IMNI) as a component of regional nodal radiotherapy is a controversial issue in breast radiation oncology with conflicting results presented in recent landmark trials. We thus created a meta-analysis of available data to better ascertain the potential benefit of IMNI. We hypothesize that with the increased power available within a meta-analysis, IMNI will prove to improve overall survival (OS) in breast cancer. METHODS: Literature search was conducted for prospective studies comparing IMNI to no IMNI. Primary endpoint was OS and secondary endpoints included local recurrence, regional recurrence, disease-free survival (DFS), breast cancer mortality (BCM), distant metastasis-free survival (DMFS), grade 2+ skin toxicity, cardiac events, and pneumonitis events. Subgroup analyses were performed for tumor location (medial/central vs. lateral), and nodal status (pN+ vs. pN0). Fixed-effect model was used if there was no heterogeneity, random-effects model otherwise. RESULTS: Four studies with a total of 5258 patients (IMNI: n=2592; control: n=2666) were included in the study. Pooled results showed IMNI significantly improved OS for all-comers (hazard ratio [HR]=0.89; 95% CI 0.81-0.97; P =0.008), as well as subgroups of pN+ with medial/central tumor location (HR=0.84; 95% CI 0.73-0.96; P =0.01) and pN+ with lateral tumor location (HR=0.87; 95% CI 0.77-0.99; P =0.04). There was no significant difference in OS for subgroups of pN0 and medial/central tumor location. There was no difference in local recurrence, but regional recurrence was significantly improved ( P =0.04). Endpoints of DFS (HR 0.91, 95% CI 0.84-0.99 P =0.03), BCM (HR 0.87, 95% CI 0.77-0.98, P =0.03), and DMFS (HR=0.87; 95% CI, 0.78-0.98; P =0.02) were all improved with IMNI. Grade 2+ skin toxicity, cardiac events and pneumonitis events were not significantly different between patient in the IMNI and no IMNI groups. CONCLUSION: Inclusion of IMN irradiation improves OS, DFS, BCM, and DMFS in breast cancer. Largest effect on OS was noted in the subgroup of patients with pN+ and medial/central tumor location.

Multi-criteria text mining model for COVID-19 testing reasons and symptoms and temporal predictive model for COVID-19 test results in rural communities.

This study is conducted to build a multi-criteria text mining model for COVID-19 testing reasons and symptoms. The model is integrated with a temporal predictive classification model for COVID-19 test results in rural underserved areas. A dataset of 6895 testing appointments and 14 features is used in this study. The text mining model classifies the notes related to the testing reasons and reported symptoms into one or more categories using look-up wordlists and a multi-criteria mapping process. The model converts an unstructured feature to a categorical feature that is used in building the temporal predictive classification model for COVID-19 test results and conducting some population analytics. The classification model is a temporal model (ordered and indexed by testing date) that uses machine learning classifiers to predict test results that are either positive or negative. Two types of classifiers and performance measures that include balanced and regular methods are used: (1) balanced random forest and (2) balanced bagged decision tree. The balanced or weighted methods are used to address and account for the biased and imbalanced dataset and to ensure correct detection of patients with COVID-19 (minority class). The model is tested in two stages using validation and testing sets to ensure robustness and reliability. The balanced classifiers outperformed regular classifiers using the balanced performance measures (balanced accuracy and G-score), which means the balanced classifiers are better at detecting patients with positive COVID-19 results. The balanced random forest achieved the best average balanced accuracy (86.1%) and G-score (86.1%) using the validation set. The balanced bagged decision tree achieved the best average balanced accuracy (83.0%) and G-score (82.8%) using the testing set. Also, it was found that the patient history, age, testing reasons, and time are the key features to classify the testing results.

Rules of incidental operation risk propagation in metro networks under fully automatic operations mode.

The frequent interruptions of network operation due to any incident suggest the necessity to study the rules of operational risk propagation in metro networks, especially under fully automatic operations mode. In this study, risk indicator computation models were developed by analyzing risk propagation processes within transfer stations and metro networks. Moreover, indicator variance rules for a transfer station and different structural networks were discussed and verified through simulation. After reviewing the simulation results, it was concluded that under the impacts of both sudden incident and peak passenger flow, the more the passengers coming from platform inlets, the longer the non-incidental line platform total train operation delay and the higher the crowding degree. However, train headway has little influence on non-incidental line platform risk development. With respect to incident risk propagation in a metro network, the propagation speed varies with network structure, wherein an annular-radial network is the fastest, a radial is moderately fast, and a grid-type network is the slowest. The conclusions are supposed to be supports for metro operation safety planning and network design.

A Systematic Review of Parkinson's Disease Cluster Analysis Research.

One way to understand the Parkinson's disease (PD) population is to investigate the similarities and differences among patients through cluster analysis, which may lead to defined, patient subgroups for diagnosis, progression tracking and treatment planning. This paper provides a systematic review of PD patient clustering research, evaluating the variables included in clustering, the cluster methods applied, the resulting patient subgroups, and evaluation metrics. A search was conducted from 1999 to 2021 on the PubMed database, using various search terms including: Parkinson's disease, cluster, and analysis. The majority of studies included a variety of clinical scale scores for clustering, of which many provide a numerical, but ordinal, categorical value. Even though the scale scores are ordinal, these were treated as numerical values with numerical and continuous values being the focus of the clustering, with limited attention to categorical variables, such as gender and family history, which may also provide useful insights into disease diagnosis, progression, and treatment. The results pointed to two to five patient clusters, with similarities among the age of onset and disease duration. The studies lacked the use of existing clustering evaluation metrics which points to a need for a thorough, analysis framework, and consensus on the appropriate variables to include in cluster analysis. Accurate cluster analysis may assist with determining if PD patients' symptoms can be treated based on a subgroup of features, if personalized care is required, or if a mix of individualized and group-based care is the best approach.

An Investigation into the Use and Meaning of Parkinson's Disease Clinical Scale Scores.

Parkinson's disease (PD) is the second most common, neurodegenerative disorder. It is a chronic, disabling, and progressive disease, and no treatment stops its progression. Rating scales are utilized to quantify PD progression and severity. The most conventional scale is the Unified Parkinson's Disease Rating Scale (UPDRS) and its modified version, Movement Disorder Society- (MDS-) UPDRS. An analytical investigation into the use and meaning of these clinical scale scores was conducted to determine if gaps exist in quantifying disease progression and severity. A series of discrepancies were identified including confusion among patients regarding the score meaning and misuse of the scores among clinicians and researchers to define disease progression. The scales are of an ordinal type and hence the resulting scores are ordinal, not providing a quantifiable progression nor severity level, but a categorical value and survey total. The knowledge that the scores are ordinal and the scales are subjective is mentioned in very limited publications, not the focus of these papers, but a brief introduction and a thoroughly researched, analytical investigation into the scales and scores have not been found. Therefore, the continuous misunderstanding and misuse of these scales and resulting scores warrant a comprehensive assessment and evaluation of these scales and scores to identify the gaps.

G-Forest: An ensemble method for cost-sensitive feature selection in gene expression microarrays.

Microarray gene expression profiling has emerged as an efficient technique for cancer diagnosis, prognosis, and treatment. One of the major drawbacks of gene expression microarrays is the "curse of dimensionality", which hinders the usefulness of information in datasets and leads to computational instability. In recent years, feature selection techniques have emerged as effective tools to identify disease biomarkers to aid in medical screening and diagnosis. However, the existing feature selection techniques, first, do not suit the rare variance exists in genomic data; and second, do not consider the feature cost (i.e. gene cost). Because ignoring features' costs may result in high cost gene profiling, this study proposes a new algorithm, called G-Forest, for cost-sensitive feature selection in gene expression microarrays. G-Forest is an ensemble cost-sensitive feature selection algorithm that develops a population of biases for a Random Forest induction algorithm. The G-Forest embeds the feature cost in the feature selection process and allows for simultaneous selection of low-cost and most informative features. In particular, when constructing the initial population, the feature is randomly selected with a probability inversely proportional to its associated cost. The G-Forest was compared with multiple state-of-the-art algorithms. Experimental results showed the effectiveness and robustness of the G-Forest in selecting the least cost and most informative genes. The G-Forest improved accuracy up to 14 % and decreased costs up to 56 % - on average - when compared with the other approaches tested in this article.

Advancing evidence-based healthcare facility design: a systematic literature review.

Healthcare facility design is a complex process that brings together diverse stakeholders and ideally aligns operational, environmental, experiential, clinical, and organizational objectives. The challenges inherent in facility design arise from the dynamic and complex nature of healthcare itself, and the growing accountability to the quadruple aims of enhancing patient experience, improving population health, reducing costs, and improving staff work life. Many healthcare systems and design practitioners are adopting an evidence-based approach to facility design, defined broadly as basing decisions about the built environment on credible and rigorous research and linking facility design to quality outcomes. Studies focused on architectural options and concepts in the evidence-based design literature have largely employed observation, surveys, post-occupancy study, space syntax analysis, or have been retrospective in nature. Fewer studies have explored layout optimization frameworks, healthcare layout modeling, applications of artificial intelligence, and layout robustness. These operations research/operations management approaches are highly valuable methods to inform healthcare facility design process in its earliest stages and measure performance in quantitative terms, yet they are currently underutilized. A primary objective of this paper is to begin to bridge this gap. This systematic review summarizes 65 evidence-based research studies related to facility layout and planning concepts published from 2008 through 2018, and categorizes them by methodology, area of focus, typology, and metrics of interest. The review identifies gaps in the existing literature and proposes solutions to advance evidence-based healthcare facility design. This work is the first of its kind to review the facility design literature across the disciplines of evidence-based healthcare design research, healthcare systems engineering, and operations research/operations management. The review suggests areas for future study that will enhance evidence-based healthcare facility designs through the integration of operations research and management science methods.

Post-Operative Infection Prediction and Risk Factor Analysis in Colorectal Surgery Using Data Mining Techniques: A Pilot Study.

Background: Post-operative infections have many negative consequences for patients' health and the healthcare system. Among other things, they increase the recovery time and the risk of re-admission. Also, infection results in penalties for hospitals and decreases the quality performance measures. Surgeons can take preventive actions if they can identify high-risk patients. The purpose of this study was to develop a model to help predict those patients at risk for post-operative infection. Methods: A retrospective analysis was conducted on patients with colorectal post-operative infections. Univariable analysis was used to identify the features associated with post-operative infection. Then, a support vector classification-based method was employed to select the right features and build prediction models. Decision tree, support vector machine (SVM), logistic regression, naïve Bayes, neural network, and random forest algorithms were implemented and compared to determine the performance algorithm that best predicted high-risk patients. Results: From 2016 to the first quarter of 2017, 208 patients who underwent colorectal resection were analyzed. The factors with a statistically significant association (p < 0.05) with post-operative infections were elective surgery, origin status, steroid or immunosuppressant use, >10% loss of body weight in the prior six months, serum creatinine concentration, length of stay, unplanned return to the operating room, administration of steroids or immunosuppressants for inflammatory bowel disease, use of a mechanical bowel preparation, various Current Procedural Terminology (CPT) codes, and discharge destination. However, accurate prediction models can be developed with seven factors: age, serum sodium concentration, blood urea nitrogen, hematocrit, platelet count, surgical procedure time, and length of stay. Logistic regression and SVM were stable models for predicting infections. Conclusion: The models developed using the pre-operative features along with the full list of features helped us interpret the results and determine the significant factors contributing to infections. These factors present opportunities for proper interventions to mitigate infection risks and their consequences.

An ergonomic comparison of firearm safety mechanisms.

As with most machines, the integral safety mechanism on firearms is vital to injury or fatality free operation. Presently, there is little or no standardisation in the design of these mechanisms. In this investigation, five existing designs found on both military and commercial rifles were evaluated ergonomically to determine the most effective characteristics for incorporation into future designs. The designs were evaluated experimentally on ease of use, visual effectiveness and operational impact. Three groups, representing a total of 30 subjects with widely varying experience, were selected. Results strongly suggest that safeties whose actuators are mounted within easy reach of the trigger finger are preferred and have the least operational impact. Subjects also preferred and were more adept at recognising safety status when the indicator was located on the receiver/barrel along the normal line of sight. Subjects more often correctly identified safety status when the indicator utilised colouring, was clearly marked and/or was in the normal line of sight. The results of this research prove that ergonomics can contribute to the understanding of firearm safety dynamics. The two essential components of safety mechanism design identified in this investigation, unambiguous status visibility and impact-free operation, are also likely to have implications in non-firearm safety mechanism design. This is particularly true for devices whose inadvertent operation can cause injury, as well as systems in which operational effectiveness can be jeopardised when attentiveness or operational control are lost in the process of actuating a poorly designed safety mechanism.