Predicting Provider Workload Using Predicted Patient Risk Score and Social Determinants of Health in Primary Care Setting.

BACKGROUND: Provider burnout due to workload is a significant concern in primary care settings. Workload for primary care providers encompasses both scheduled visit care and non-visit care interactions. These interactions are highly influenced by patients' health conditions or acuity, which can be measured by the Adjusted Clinical Group (ACG) score. However, new patients typically have minimal health information beyond social determinants of health (SDOH) to determine ACG score. OBJECTIVES: This study aims to assess new patient workload by first predicting the ACG score using SDOH, age, and gender and then using this information to estimate the number of appointments (scheduled visit care) and non-visit care interactions. METHODS: Two years of appointment data were collected for patients who had initial appointment requests in the first year and had the ACG score, appointment, and non-visit care counts in the subsequent year. State-of-art machine learning algorithms were employed to predict ACG scores and compared with current baseline estimation. Linear regression models were then used to predict appointments and non-visit care interactions, integrating demographic data, SDOH, and predicted ACG scores. RESULTS: The machine learning methods showed promising results in predicting ACG scores. Besides the decision tree, all other methods performed at least 9% better in accuracy than the baseline approach which had an accuracy of 78%. Incorporating SDOH and predicted ACG scores also significantly improved the prediction for both appointments and non-visit care interactions. The R 2 values increased by 95.2 and 93.8%, respectively. Furthermore, age, smoking tobacco, family history, gender, usage of injection birth control, and ACG were significant factors for determining appointments. SDOH factors such as tobacco usage, physical exercise, education level, and group activities were strongly correlated with non-visit care interactions. CONCLUSION: The study highlights the importance of SDOH and predicted ACG scores in predicting provider workload in primary care settings.

Convolutional Neural Networks for Classifying Cervical Cancer Types Using Histological Images.

Cervical cancer is the most common cancer among women worldwide. The diagnosis and classification of cancer are extremely important, as it influences the optimal treatment and length of survival. The objective was to develop and validate a diagnosis system based on convolutional neural networks (CNN) that identifies cervical malignancies and provides diagnostic interpretability. A total of 8496 labeled histology images were extracted from 229 cervical specimens (cervical squamous cell carcinoma, SCC, n = 37; cervical adenocarcinoma, AC, n = 8; nonmalignant cervical tissues, n = 184). AlexNet, VGG-19, Xception, and ResNet-50 with five-fold cross-validation were constructed to distinguish cervical cancer images from nonmalignant images. The performance of CNNs was quantified in terms of accuracy, precision, recall, and the area under the receiver operating curve (AUC). Six pathologists were recruited to make a comparison with the performance of CNNs. Guided Backpropagation and Gradient-weighted Class Activation Mapping (Grad-CAM) were deployed to highlight the area of high malignant probability. The Xception model had excellent performance in identifying cervical SCC and AC in test sets. For cervical SCC, AUC was 0.98 (internal validation) and 0.974 (external validation). For cervical AC, AUC was 0.966 (internal validation) and 0.958 (external validation). The performance of CNNs falls between experienced and inexperienced pathologists. Grad-CAM and Guided Gard-CAM ensured diagnoses interpretability by highlighting morphological features of malignant changes. CNN is efficient for histological image classification tasks of distinguishing cervical malignancies from benign tissues and could highlight the specific areas of concern. All these findings suggest that CNNs could serve as a diagnostic tool to aid pathologic diagnosis.

Coordination of Intraoperative Neurophysiologic Monitoring Technologist and Surgery Schedules.

Resource coordination in surgical scheduling remains challenging in health care delivery systems. This is especially the case in highly-specialized settings such as coordinating Intraoperative Neurophysiologic Monitoring (IONM) resources. Inefficient coordination yields higher costs, limited access to care, and creates constraints to surgical quality and outcomes. To maximize utilization of IONM resources, optimization-based algorithms are proposed to effectively schedule IONM surgical cases and technologists and evaluate staffing needs. Data with 10 days of case volumes, their surgery durations, and technologist staffing was used to demonstrate method effectiveness. An iterative optimization-based model that determines both optimal surgery and technologist start time (operational scenario 4) was built in an Excel spreadsheet along with Excel's Solver settings. It was compared with current practice (operational scenario 1) and optimization solution on only surgery start time (operational scenario 2) or technologist start time (operational scenario 3). Comparisons are made with respect to technologist overtime and under-utilization time. The results conclude that scenario 4 significantly reduces overtime by 74% and under-utilization time by 86% as well as technologist needs by 10%. For practices that do not have flexibility to alter surgeon preference on surgery start time or IONM technologist staffing levels, both scenarios 2 and 3 also result in substantial reductions in technologist overtime and under-utilization. Moreover, IONM technologist staffing options are discussed to accommodate technologist preferences and set constraints for surgical case scheduling. All optimization-based approaches presented in this paper are able to improve utilization of IONM resources and ultimately improve the coordination and efficiency of highly-specialized resources.

Reduce Patient Treatment wait time in a Proton Beam Facility - A Gatekeeper Approach.

Patient wait time can negatively impact treatment quality in a proton therapy center, where multiple treatment rooms share one proton beam. Wait time increases patient discomfort that can lead to patient motion, dissatisfaction, and longer treatment delay. This study was to develop a patient call-back model that reduced patient wait while efficiently utilizing the proton beam. A "Gatekeeper" logic allowing therapists to adjust the time of a patient's call-back to the treatment room was developed. It uses a two-pronged approach to minimize overlap of long treatment and the possibility of excessive wait in the queue to receive the proton beam. The goal was to reduce the maximum wait time to less than eight minutes per field for a four-room facility. The effectiveness of this logic was evaluated through simulation, and five scenarios were compared. Four scenarios implementing various levels of gatekeeper logic were compared with the original scenario without the logic. The best performing model provided a reduction of the maximum field wait by 26% and met the predefined goal. Adjusting call-back extended the treatment day length by an average of 6 min and a maximum of 12 min in total. The use of this gatekeeper logic significantly reduces patient field wait with minimal impact on treatment day length for a four-room proton facility. A sample interface that adopts this logic for therapists to make informed decision on patient call-back time is demonstrated.

Chemotherapy scheduling template development using an optimization approach.

PURPOSE: The purpose of this paper is to develop a chemotherapy scheduling template that accounts for nurse resource availability and patient treatment needs to alleviate the mid-day patient load and provide quality services for patients. DESIGN/METHODOLOGY/APPROACH: Owing to treatment complexity in chemotherapy administration, nurses are required at the beginning, end and during treatment. When nurses are not available to continue treatment, the service is compromised, and the resource constraint is violated, which leads to inevitable delay that risks service quality. Consequently, an optimization method is used to create a scheduling template that minimizes the violation between resource assignment and treatment requirements, while leveling patient load throughout a day. A case study from a typical clinic day is presented to understand current scheduling issues, describe nursing resource constraints, and develop a constraint-based optimization model and leveling algorithm for the final template. FINDINGS: The approach is expected to reduce the variation in the system by 24 percent and result in five fewer chemo chairs used during peak hours. Adjusting staffing levels could further reduce resource constraint violations and more savings on chair occupancy. The actual implementation results indicate a 33 percent reduction on resource constraint violations and positive feedback from nursing staff for workload. RESEARCH LIMITATIONS/IMPLICATIONS: Other delays, including laboratory test, physician visit and treatment assignment, are potential research areas. ORIGINALITY/VALUE: The study demonstrates significant improvement in mid-day patient load and meeting treatment needs using optimization with a unique objective.

Alternative Outpatient Chemotherapy Scheduling Method to Improve Patient Service Quality and Nurse Satisfaction.

INTRODUCTION: Optimal scheduling and calendar management in an outpatient chemotherapy unit is a complex process that is driven by a need to focus on safety while accommodating a high degree of variability. Primary constraints are infusion times, staffing resources, chair availability, and unit hours. METHODS: We undertook a process to analyze our existing management models across multiple practice settings in our health care system, then developed a model to optimize safety and efficiency. The model was tested in one of the community chemotherapy units. We assessed staffing violations as measured by nurse-to-patient ratios throughout the workday and at key points during treatment. Staffing violations were tracked before and after the implementation of the new model. RESULTS: The new model reduced staffing violations by nearly 50% and required fewer chairs to treat the same number of patients for the selected clinic day. Actual implementation results indicated that the new model leveled the distribution of patients across the workday with an 18% reduction in maximum chair utilization and a 27% reduction in staffing violations. Subsequently, a positive impact on peak pharmacy workload reduced delays by as much as 35 minutes. Nursing staff satisfaction with the new model was positive. CONCLUSION: We conclude that the proposed optimization approach with regard to nursing resource assignment and workload balance throughout a day effectively improves patient service quality and staff satisfaction.

Prevalence, quantification, and typing of human adenoviruses detected in river water in Taiwan.

The prevalence of human adenoviruses (HAdV) in river waters was investigated in this study. Water samples were collected from 13 rivers in Taiwan, concentrated, and assessed for the presence of HAdVs using nested polymerase chain reaction (PCR). Human AdV positive samples were then subjected to real-time PCR (qPCR) to quantify the viral genomes and further subjected to primer-based genotyping to identify the various serotypes present. For each water sample, several water quality parameters were evaluated, including heterotrophic plate count, total coliform, Escherichia coli, water temperature, pH, conductivity, and dissolved oxygen. Among the 13 rivers examined, four rivers (30.8 %) were found to contain HAdVs. The major genotype was F species HAdV serotype 41. The mean HAdVs concentrations ranged from 6.10 × 10(2) to 8.51 × 10(2) copies/L. No significant differences were observed between the presence of HAdVs, and all of the water quality parameters evaluated (heterotrophic plate count, total coliform, E. coli, water temperature, pH, conductivity, and dissolved oxygen). Given the potential health risks posed by the presence of enteric viruses in environmental waters, further assessment is desirable with respect to possible sources, virus transport, and survival of viruses in the aquatic environment.

Application of passive sampling on assessment of concentration distribution and health risk of volatile organic compounds at a high-tech science park.

The objectives of this study are to investigate the volatile organic compound (VOC) distribution using passive samplers and to assess the resulting health risks in a high-tech science industrial park. With the advantages of passive sampling techniques, long-term and wide-area samples are collected. The results show TVOC concentrations in summer, fall, winter, and spring are 7.14 ± 5.66 ppb, 18.17 ± 5.81 ppb, 10.30 ± 3.54 ppb, and 14.56 ± 4.53 ppb, respectively; those on weekdays and weekends are 14.36 ± 6.80 ppb and 9.87 ± 4.86 ppb, respectively; and those in industrial and residential zones are 12.97 ± 0.39 ppb and 11.13 ± 0.68 ppb, respectively. Based on concentration variations, and benzene, toluene, ethylbenzene, and xylene ratios, we can resolve the source origins. Health risks are assessed based on the resulting concentrations. In the case of non-cancer chronic effects, long-term exposure to these concentrations does not support there is a risk of adverse health effects. However, potential cancer risks of exposure to these concentrations may occur, especially to carbon tetrachloride and benzene. By applying this study's procedures, information on VOC concentration distribution, source identification, and health assessment can be obtained and they are applicable to similar studies.

Bone marrow stromal cell transplantation combined with angiotensin-converting enzyme inhibitor treatment in rat with acute myocardial infarction and the role of insulin-like growth factor-1.

BACKGROUND AIMS: We investigated bone marrow stromal cell (BMSC) transplantation combined with angiotensin-converting enzyme inhibitor (ACEI) treatment in acute myocardial infarction (AMI) and the role of insulin-like growth factor-1 (IGF-1). METHODS: AMI models were established in Sprague-Dawley rats by ligation of the left anterior descending coronary artery and grouped into blank control (BC), ACEI treatment (ACEI), BMSC transplantation (BMSC) and BMSC transplantation plus ACEI (combined). Perindopril (2.5 mg/kg) was administered by gavage to ACEI and combined groups from the day after AMI. BMSC (2 × 10(8)) were injected into the border of the MI area a week later in the BMSC and combined groups. RESULTS: After 4 weeks, hemodynamics in the BMSC and combined groups were significantly improved (P < 0.05 versus BC), with the greatest improvement in the combined group (P < 0.05). In addition, an increased number of BMSC survived in the combined group (P < 0.05 versus BMSC). A proportion of BMSC was positive for troponin T, as detected by immunofluorescence. The number of apoptotic cardiomyocytes was decreased in the BMSC and ACEI groups, and even further in the combined group (P < 0.05). IGF-1 expression was up-regulated in the BMSC and combined groups (P < 0.05 versus BC), but not in the ACEI group. B cell lymphoma-2 (Bcl-2) expression was up-regulated in the ACEI, BMSC and combined groups, with the highest expression in the combined group (P < 0.05). CONCLUSIONS: Our results show that BMSC engrafted in AMI can survive well and secrete IGF-1 and preserve cardiac function significantly. These data suggest that BMSC transplantation inhibits apoptosis of cardiomyocytes by up-regulation of Bcl-2 expression in the myocardium, and this effect might be sensitized by ACEI.

Effects of insulin-like growth factor-1 on the properties of mesenchymal stem cells in vitro.

OBJECTIVE: To explore the effects of insulin-like growth factor-1 (IGF-1) on migration, proliferation and differentiation of mesenchymal stem cells (MSCs). METHODS: MSCs were obtained from Sprague-Dawley rats by a combination of gradient centrifugation and cell culture techniques and treated with IGF-1 at concentrations of 5-20 ng/ml. Proliferation of MSCs was determined as the mean doubling time. Expression of CXC chemokine receptor 4 (CXCR4) and migration property were determined by flow cytometry and transwell migration essay, respectively. mRNA expression of GATA-4 and collagen II was determined by reverse transcription-polymerase chain reaction (RT-PCR). RESULTS: The mean doubling time of MSC proliferation was decreased, and the expression of CXCR4 on MSCs and migration of MSCs were increased by IGF-1, all in a dose-dependent manner, while the optimal concentration of IGF-1 on proliferation and migration was different. IGF-1 did not affect the expression of GATA-4 or collagen II mRNA. CONCLUSIONS: IGF-1 dose-dependently stimulated the proliferation of MSCs, upregulated the expression of CXCR4, and accelerated migration. There was no apparent differentiation of MSCs to cardiomyocytes or chondrocytes after culturing with IGF-1 alone.