Prescription pattern analysis of Type 2 Diabetes Mellitus: a cross-sectional study in Isfahan, Iran.

BACKGROUND: Patients with Type 2 Diabetes Mellitus (T2DM) are at a higher risk of polypharmacy and more susceptible to irrational prescriptions; therefore, pharmacological therapy patterns are important to be monitored. The primary objective of this study was to highlight current prescription patterns in T2DM patients and compare them with existing Standards of Medical Care in Diabetes. The second objective was to analyze whether age and gender affect prescription patterns. METHOD: This cross-sectional study was conducted using the Iran Health Insurance Organization (IHIO) prescription database. It was mined by an Association Rule Mining (ARM) technique, FP-Growth, in order to find co-prescribed drugs with anti-diabetic medications. The algorithm was implemented at different levels of the Anatomical Therapeutic Chemical (ATC) classification system, which assigns different codes to drugs based on their anatomy, pharmacological, therapeutic, and chemical properties to provide an in-depth analysis of co-prescription patterns. RESULTS: Altogether, the prescriptions of 914,652 patients were analyzed, of whom 91,505 were found to have diabetes. According to our results, prescribing Lipid Modifying Agents (C10) (56.3%), Agents Acting on The Renin-Angiotensin System (C09) (48.9%), Antithrombotic Agents (B01) (35.7%), and Beta Blocking Agents (C07) (30.1%) were meaningfully associated with the prescription of Drugs Used in Diabetes. Our study also revealed that female diabetic patients have a higher lift for taking Thyroid Preparations, and the older the patients were, the more they were prone to take neuropathy-related medications. Additionally, the results suggest that there are gender differences in the association between aspirin and diabetes drugs, with the differences becoming less pronounced in old age. CONCLUSIONS: Almost all of the association rules found in this research were clinically meaningful, proving the potential of ARM for co-prescription pattern discovery. Moreover, implementing level-based ARM was effective in detecting difficult-to-spot rules. Additionally, the majority of drugs prescribed by physicians were consistent with the Standards of Medical Care in Diabetes.

Development of glaucoma predictive model and risk factors assessment based on supervised models.

OBJECTIVES: To develop and to propose a machine learning model for predicting glaucoma and identifying its risk factors. METHOD: Data analysis pipeline is designed for this study based on Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. The main steps of the pipeline include data sampling, preprocessing, classification and evaluation and validation. Data sampling for providing the training dataset was performed with balanced sampling based on over-sampling and under-sampling methods. Data preprocessing steps were missing value imputation and normalization. For classification step, several machine learning models were designed for predicting glaucoma including Decision Trees (DTs), K-Nearest Neighbors (K-NN), Support Vector Machines (SVM), Random Forests (RFs), Extra Trees (ETs) and Bagging Ensemble methods. Moreover, in the classification step, a novel stacking ensemble model is designed and proposed using the superior classifiers. RESULTS: The data were from Shahroud Eye Cohort Study including demographic and ophthalmology data for 5190 participants aged 40-64 living in Shahroud, northeast Iran. The main variables considered in this dataset were 67 demographics, ophthalmologic, optometric, perimetry, and biometry features for 4561 people, including 4474 non-glaucoma participants and 87 glaucoma patients. Experimental results show that DTs and RFs trained based on under-sampling of the training dataset have superior performance for predicting glaucoma than the compared single classifiers and bagging ensemble methods with the average accuracy of 87.61 and 88.87, the sensitivity of 73.80 and 72.35, specificity of 87.88 and 89.10 and area under the curve (AUC) of 91.04 and 94.53, respectively. The proposed stacking ensemble has an average accuracy of 83.56, a sensitivity of 82.21, a specificity of 81.32, and an AUC of 88.54. CONCLUSIONS: In this study, a machine learning model is proposed and developed to predict glaucoma disease among persons aged 40-64. Top predictors in this study considered features for discriminating and predicting non-glaucoma persons from glaucoma patients include the number of the visual field detect on perimetry, vertical cup to disk ratio, white to white diameter, systolic blood pressure, pupil barycenter on Y coordinate, age, and axial length.

A Generic Simulation Model of the Relative Cost-Effectiveness of ICU Versus Step-Down (IMCU) Expansion.

BACKGROUND: Many jurisdictions are facing increased demand for intensive care. There are two long-term investment options: intensive care unit (ICU) versus step-down or intermediate care unit (IMCU) capacity expansion. Relative cost-effectiveness of the two investment strategies with regard to patient lives saved has not been studied to date. METHODS: We expand a generic system dynamics simulation model of emergency patient flow in a typical hospital, populated with empirical evidence found in the medical and hospital administration literature, to estimate the long-term effects of expanding ICU versus IMCU beds on patient lives saved under a common assumption of 2.1% annual increase in hospital arrivals. Two alternative policies of expanding ICU by two beds versus introducing a two-bed IMCU are compared over a ten-year simulation period. Russel equation is used to calculate total cost of patients' hospitalization. Using two possible values for the ratio of ICU to IMCU cost per inpatient day and four possible values for the percentage of patients transferred from ICU to IMCU found in the literature, nine scenarios are compared against the baseline scenario of no capacity expansion. RESULTS: Expanding ICU capacity by two beds is demonstrated as the most cost-effective scenario with an incremental cost-effectiveness ratio of 3684 (US $) per life saved against the baseline scenario. Sensitivity analyses on the mortality rate of patients in IMCU, direct transfer of IMCU-destined patients to the ward upon completing required IMCU length of stay in the ICU, admission of IMCU patient to ICU, adding two ward beds, and changes in hospital size do not change the superiority of ICU expansion over other scenarios. CONCLUSIONS: In terms of operational costs, ICU beds are more cost effective for saving patients than IMCU beds. However, capital costs of setting up ICU versus IMCU beds should be considered for a complete economic analysis.

Sustaining critical care: using evidence-based simulation to evaluate ICU management policies.

Intensive Care Units (ICU) are costly yet critical hospital departments that should be available to care for patients needing highly specialized critical care. Shortage of ICU beds in many regions of the world and the constant fire-fighting to make these beds available through various ICU management policies motivated this study. The paper discusses the application of a generic system dynamics model of emergency patient flow in a typical hospital, populated with empirical evidence found in the medical and hospital administration literature, to explore the dynamics of intended and unintended consequences of such ICU management policies under a natural disaster crisis scenario. ICU management policies that can be implemented by a single hospital on short notice, namely premature transfer from ICU, boarding in ward, and general ward admission control, along with their possible combinations, are modeled and their impact on managerial and health outcome measures are investigated. The main insight out of the study is that the general ward admission control policy outperforms the rest of ICU management policies under such crisis scenarios with regards to reducing total mortality, which is counter intuitive for hospital administrators as this policy is not very effective at alleviating the symptoms of the problem, namely high ED and ICU occupancy rates that are closely monitored by hospital management particularly in times of crisis. A multivariate sensitivity analysis on parameters with diverse range of values in the literature found the superiority of the general ward admission control to hold true in every scenario.

Can hospitals compete on quality? Hospital competition.

In this paper, we consider two hospitals with different perceived quality of care competing to capture a fraction of the total market demand. Patients select the hospital that provides the highest utility, which is a function of price and the patient's perceived quality of life during their life expectancy. We consider a market with a single class of patients and show that depending on the market demand and perceived quality of care of the hospitals, patients may enjoy a positive utility. Moreover, hospitals share the market demand based on their perceived quality of care and capacity. We also show that in a monopoly market (a market with a single hospital) the optimal demand captured by the hospital is independent of the perceived quality of care. We investigate the effects of different parameters including the market demand, hospitals' capacities, and perceived quality of care on the fraction of the demand that each hospital captures using some numerical examples.

Strategic analytics: towards fully embedding evidence in healthcare decision-making.

Cancer Care Ontario (CCO) has implemented multiple information technology solutions and collected health-system data to support its programs. There is now an opportunity to leverage these data and perform advanced end-to-end analytics that inform decisions around improving health-system performance. In 2014, CCO engaged in an extensive assessment of its current data capacity and capability, with the intent to drive increased use of data for evidence-based decision-making. The breadth and volume of data at CCO uniquely places the organization to contribute to not only system-wide operational reporting, but more advanced modelling of current and future state system management and planning. In 2012, CCO established a strategic analytics practice to assist the agency's programs contextualize and inform key business decisions and to provide support through innovative predictive analytics solutions. This paper describes the organizational structure, services and supporting operations that have enabled progress to date, and discusses the next steps towards the vision of embedding evidence fully into healthcare decision-making.

Theory of constraints for publicly funded health systems.

Originally developed in the context of publicly traded for-profit companies, theory of constraints (TOC) improves system performance through leveraging the constraint(s). While the theory seems to be a natural fit for resource-constrained publicly funded health systems, there is a lack of literature addressing the modifications required to adopt TOC and define the goal and performance measures. This paper develops a system dynamics representation of the classical TOC's system-wide goal and performance measures for publicly traded for-profit companies, which forms the basis for developing a similar model for publicly funded health systems. The model is then expanded to include some of the factors that affect system performance, providing a framework to apply TOC's process of ongoing improvement in publicly funded health systems. Future research is required to more accurately define the factors affecting system performance and populate the model with evidence-based estimates for various parameters in order to use the model to guide TOC's process of ongoing improvement.

Cost-effectiveness analysis of medical documentation alternatives.

OBJECTIVES: The delay between patient discharge and the completion of the final discharge note have prompted hospitals to consider new information technologies. This study compared the relative cost-effectiveness of an automated medical documentation system to the current system in place at a Canadian hospital. There are significant expenditures associated with the choice of medical documentation system, yet the benefit to the patient population has not been studied. METHODS: A systematic review of the literature was carried out. Cost data for the current documentation system were obtained from the study hospital. The costs of purchasing the automated system were obtained from the manufacturer. Other resource cost implications of the automated system were estimated based on information obtained from the Centre for Applied Health Informatics at the study hospital. The outcome was determined to be the average time (days) between patient discharge and note completion. A cost-effectiveness analysis was conducted. Sensitivity analyses were used to determine the robustness of the results. RESULTS: The automated documentation system was associated with higher costs but better outcomes than the current system. The incremental cost-effectiveness ratio used for comparing the automated medical documentation system with the traditional system indicated that the incremental daily cost for decreasing a day in average note completion time per discharge note was 0.331 Canadian $/day over the study period (4 years). CONCLUSIONS: Although the automated documentation system was more expensive than the current system, it also provided qualitative benefits that were not considered in the cost-effectiveness analysis.