Training needs assessment of hospital CEOs in a developing country: the example of Iran.

BACKGROUND: It is essential to identify the necessary competencies of hospital CEOs in order to improve the quality and efficiency of services they provide. Expert leadership skills and competencies can have a significant impact on the success of an organization, benefiting both patients and staff. This study aimed to assess the competencies and training needs of hospital CEOs in Iran public hospitals. METHODS: We conducted this cross-sectional analytical study through a self-assessment questionnaire, which was a web-based platform developed by the WHO country office in Iran, between July 2018 and September 2018. The questionnaire was completed by 180 hospital CEOs and included a core set of 81 items based on Assessing the Competency of Hospital CEO. These items were categorized into five superordinate categories: leadership, personality and quality of individual behavior, knowledge and business skills, social responsibility, and healthcare environment. In addition, we conducted focus groups with 30 hospital CEOs, supervisor assessments with 10 hospital managers, and interviews with 10 supervisors. RESULTS: Of the 180 questionnaires distributed, 78% were returned, and most respondents were medical specialists. The need for leadership competencies such as individual behavior skills and change management received the highest priority. Most respondents required training in management skills, including financial management, governance, strategic thinking, quality improvement, and disaster management. CONCLUSION: Providing needs-based education is crucial, especially in developing countries. In this study, leadership and strategic thinking were found to be the most needed competencies among hospital CEOs in Iran. These findings serve as reference points for developing countries with similar backgrounds and healthcare environments as Iran.

Assessing the effects of data drift on the performance of machine learning models used in clinical sepsis prediction.

BACKGROUND: Data drift can negatively impact the performance of machine learning algorithms (MLAs) that were trained on historical data. As such, MLAs should be continuously monitored and tuned to overcome the systematic changes that occur in the distribution of data. In this paper, we study the extent of data drift and provide insights about its characteristics for sepsis onset prediction. This study will help elucidate the nature of data drift for prediction of sepsis and similar diseases. This may aid with the development of more effective patient monitoring systems that can stratify risk for dynamic disease states in hospitals. METHODS: We devise a series of simulations that measure the effects of data drift in patients with sepsis, using electronic health records (EHR). We simulate multiple scenarios in which data drift may occur, namely the change in the distribution of the predictor variables (covariate shift), the change in the statistical relationship between the predictors and the target (concept shift), and the occurrence of a major healthcare event (major event) such as the COVID-19 pandemic. We measure the impact of data drift on model performances, identify the circumstances that necessitate model retraining, and compare the effects of different retraining methodologies and model architecture on the outcomes. We present the results for two different MLAs, eXtreme Gradient Boosting (XGB) and Recurrent Neural Network (RNN). RESULTS: Our results show that the properly retrained XGB models outperform the baseline models in all simulation scenarios, hence signifying the existence of data drift. In the major event scenario, the area under the receiver operating characteristic curve (AUROC) at the end of the simulation period is 0.811 for the baseline XGB model and 0.868 for the retrained XGB model. In the covariate shift scenario, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.853 and 0.874 respectively. In the concept shift scenario and under the mixed labeling method, the retrained XGB models perform worse than the baseline model for most simulation steps. However, under the full relabeling method, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.852 and 0.877 respectively. The results for the RNN models were mixed, suggesting that retraining based on a fixed network architecture may be inadequate for an RNN. We also present the results in the form of other performance metrics such as the ratio of observed to expected probabilities (calibration) and the normalized rate of positive predictive values (PPV) by prevalence, referred to as lift, at a sensitivity of 0.8. CONCLUSION: Our simulations reveal that retraining periods of a couple of months or using several thousand patients are likely to be adequate to monitor machine learning models that predict sepsis. This indicates that a machine learning system for sepsis prediction will probably need less infrastructure for performance monitoring and retraining compared to other applications in which data drift is more frequent and continuous. Our results also show that in the event of a concept shift, a full overhaul of the sepsis prediction model may be necessary because it indicates a discrete change in the definition of sepsis labels, and mixing the labels for the sake of incremental training may not produce the desired results.

Comparative Study of Medical Equipment Procurement in Selected Countries.

Background: Despite the fact that medical equipment is critical for providing good health services and also incurs significant expenditures for the health system, little is known about how to procure it effectively. To date, only a few comparative studies on the procurement framework for medical equipment between nations have been conducted. Thus, the purpose of this study was to examine this issue between the leading countries. Methods: To conduct this comparative study, Canada, the United Kingdom, Australia, Spain, Italy, Turkey, Thailand, and Iran were selected. Medical devices, medical equipment, procurement, purchasing, and acquisition were keywords considered to search PubMed, ProQuest, Web of Science, Scopus, Science Direct, and Google scholar databases. Also, the websites of the related organizations, such as the World Health Organization (WHO), the World Bank, and the Ministry of Health of respective countries were searched for the gray literature. Providing information about the procurement framework and availability of evidence in the English language was considered as the inclusion criteria and the lack of access to full texts, letters, and commentary article designs were the exclusion criteria. The results were summarized and reported using comparative tables. Results: Most of the countries involved in this study are trying to align procurement activities with national health care priorities. In view of this, there is a trend toward centralized procurement, especially in Italy, Spain, England, Italy, Canada, and Iran. While a range of actors participate in the procurement process, a greater role for physicians and patients is necessary to be defined to meet patient needs. Moving from price-based approaches to value-based approaches is in the agenda to consider a broader range of criteria to achieve value for money and support patient access to innovations. Conclusion: Most of the countries have reorganized the mechanism of medical equipment procurement. The price of products is the important factor, and recently the value factor has become more important in procurement. Reinforcing the role of decision-making teams and hospital committees in the procurement of medical equipment is suggested. Further studies are needed on the application of value-based approaches to evaluate their effects in hospitals.

Multitask Learning With Recurrent Neural Networks for Acute Respiratory Distress Syndrome Prediction Using Only Electronic Health Record Data: Model Development and Validation Study.

BACKGROUND: Acute respiratory distress syndrome (ARDS) is a condition that is often considered to have broad and subjective diagnostic criteria and is associated with significant mortality and morbidity. Early and accurate prediction of ARDS and related conditions such as hypoxemia and sepsis could allow timely administration of therapies, leading to improved patient outcomes. OBJECTIVE: The aim of this study is to perform an exploration of how multilabel classification in the clinical setting can take advantage of the underlying dependencies between ARDS and related conditions to improve early prediction of ARDS in patients. METHODS: The electronic health record data set included 40,703 patient encounters from 7 hospitals from April 20, 2018, to March 17, 2021. A recurrent neural network (RNN) was trained using data from 5 hospitals, and external validation was conducted on data from 2 hospitals. In addition to ARDS, 12 target labels for related conditions such as sepsis, hypoxemia, and COVID-19 were used to train the model to classify a total of 13 outputs. As a comparator, XGBoost models were developed for each of the 13 target labels. Model performance was assessed using the area under the receiver operating characteristic curve. Heat maps to visualize attention scores were generated to provide interpretability to the neural networks. Finally, cluster analysis was performed to identify potential phenotypic subgroups of patients with ARDS. RESULTS: The single RNN model trained to classify 13 outputs outperformed the individual XGBoost models for ARDS prediction, achieving an area under the receiver operating characteristic curve of 0.842 on the external test sets. Models trained on an increasing number of tasks resulted in improved performance. Earlier prediction of ARDS nearly doubled the rate of in-hospital survival. Cluster analysis revealed distinct ARDS subgroups, some of which had similar mortality rates but different clinical presentations. CONCLUSIONS: The RNN model presented in this paper can be used as an early warning system to stratify patients who are at risk of developing one of the multiple risk outcomes, hence providing practitioners with the means to take early action.

Assessing the effects of data drift on the performance of machine learning models used in clinical sepsis prediction.

Background: Data drift can negatively impact the performance of machine learning algorithms (MLAs) that were trained on historical data. As such, MLAs should be continuously monitored and tuned to overcome the systematic changes that occur in the distribution of data. In this paper, we study the extent of data drift and provide insights about its characteristics for sepsis onset prediction. This study will help elucidate the nature of data drift for prediction of sepsis and similar diseases. This may aid with the development of more effective patient monitoring systems that can stratify risk for dynamic disease states in hospitals. Methods: We devise a series of simulations that measure the effects of data drift in patients with sepsis. We simulate multiple scenarios in which data drift may occur, namely the change in the distribution of the predictor variables (covariate shift), the change in the statistical relationship between the predictors and the target (concept shift), and the occurrence of a major healthcare event (major event) such as the COVID-19 pandemic. We measure the impact of data drift on model performances, identify the circumstances that necessitate model retraining, and compare the effects of different retraining methodologies and model architecture on the outcomes. We present the results for two different MLAs, eXtreme Gradient Boosting (XGB) and Recurrent Neural Network (RNN). Results: Our results show that the properly retrained XGB models outperform the baseline models in all simulation scenarios, hence signifying the existence of data drift. In the major event scenario, the area under the receiver operating characteristic curve (AUROC) at the end of the simulation period is 0.811 for the baseline XGB model and 0.868 for the retrained XGB model. In the covariate shift scenario, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.853 and 0.874 respectively. In the concept shift scenario and under the mixed labeling method, the retrained XGB models perform worse than the baseline model for most simulation steps. However, under the full relabeling method, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.852 and 0.877 respectively. The results for the RNN models were mixed, suggesting that retraining based on a fixed network architecture may be inadequate for an RNN. We also present the results in the form of other performance metrics such as the ratio of observed to expected probabilities (calibration) and the normalized rate of positive predictive values (PPV) by prevalence, referred to as lift, at a sensitivity of 0.8. Conclusion: Our simulations reveal that retraining periods of a couple of months or using several thousand patients are likely to be adequate to monitor machine learning models that predict sepsis. This indicates that a machine learning system for sepsis prediction will probably need less infrastructure for performance monitoring and retraining compared to other applications in which data drift is more frequent and continuous. Our results also show that in the event of a concept shift, a full overhaul of the sepsis prediction model may be necessary because it indicates a discrete change in the definition of sepsis labels, and mixing the labels for the sake of incremental training may not produce the desired results.

Early prediction of central line associated bloodstream infection using machine learning.

BACKGROUND: Central line-associated bloodstream infections (CLABSIs) are associated with significant morbidity, mortality, and increased healthcare costs. Despite the high prevalence of CLABSIs in the U.S., there are currently no tools to stratify a patient's risk of developing an infection as the result of central line placement. To this end, we have developed and validated a machine learning algorithm (MLA) that can predict a patient's likelihood of developing CLABSI using only electronic health record data in order to provide clinical decision support. METHODS: We created three machine learning models to retrospectively analyze electronic health record data from 27,619 patient encounters. The models were trained and validated using an 80:20 split for the train and test data. Patients designated as having a central line procedure based on International Statistical Classification of Diseases and Related Health Problems 10 codes were included. RESULTS: XGBoost was the highest performing MLA out of the three models, obtaining an AUROC of 0.762 for CLABSI risk prediction at 48 hours after the recorded time for central line placement. CONCLUSIONS: Our results demonstrate that MLAs may be effective clinical decision support tools for assessment of CLABSI risk and should be explored further for this purpose.

New financial management system for Iran public health sector: A qualitative study.

BACKGROUND: Financial management system acts as a driving force and the first important principle of health sector reform. This study aimed to prepare a framework for new financial management system in Iran health sector. MATERIALS AND METHODS: This qualitative study was conducted by content analysis approach and 15 key informant participants selected through purposive sampling consisted of three minsters of Ministry of Health and Medical Education (MOHME), three vice-chancellors in the Center of Resource Development and Management, Two members of the Health Assembly of the Islamic Consultative, four Medical Sciences university's presidents, and three managers in Budgeting and performance Monitoring Center of MOHME in 2017. Data were collected through semi-structured interviews and they were analyzed using Atlas T6 software. RESULTS: Six main themes were emerged as follow: "legal reform," "removing barriers to set up accrual accounting," "cost price calculation," "operational planning and budgeting," "human resources' organization, recruitment, and moderation," and "financial system output utilization (management accounting techniques) as the base for evidence-based policymaking and decision-making practices." CONCLUSION: Any efforts for improving the current situation and reducing of mentioned limitations could be useful in providing required space for future phases of reforms and calculation of unit cost, operational budgeting, and management of cost and productivity. This can be achieved through an integrated system of recording and producing standard and accrual financial information. Furthermore, changing the accounting process and the financial system that complies with one single encoding in the country is a key issue.

Predicting ventilator-associated pneumonia with machine learning.

ABSTRACT: Ventilator-associated pneumonia (VAP) is the most common and fatal nosocomial infection in intensive care units (ICUs). Existing methods for identifying VAP display low accuracy, and their use may delay antimicrobial therapy. VAP diagnostics derived from machine learning (ML) methods that utilize electronic health record (EHR) data have not yet been explored. The objective of this study is to compare the performance of a variety of ML models trained to predict whether VAP will be diagnosed during the patient stay.A retrospective study examined data from 6126 adult ICU encounters lasting at least 48 hours following the initiation of mechanical ventilation. The gold standard was the presence of a diagnostic code for VAP. Five different ML models were trained to predict VAP 48 hours after initiation of mechanical ventilation. Model performance was evaluated with regard to the area under the receiver operating characteristic (AUROC) curve on a 20% hold-out test set. Feature importance was measured in terms of Shapley values.The highest performing model achieved an AUROC value of 0.854. The most important features for the best-performing model were the length of time on mechanical ventilation, the presence of antibiotics, sputum test frequency, and the most recent Glasgow Coma Scale assessment.Supervised ML using patient EHR data is promising for VAP diagnosis and warrants further validation. This tool has the potential to aid the timely diagnosis of VAP.

Value-Based procurement for medical devices: A scoping review.

Background: Despite this seemingly simple definition of value in different perspectives, the definition of value-based procurement for medical devices is still unclear. This study aimed to delineate the definition of value-based procurement for medical devices and its characteristics. Methods: According to the systematic method for scoping review described by Arksey and O'Malley, we reviewed related literature through target databases (PUBMED, ProQuest, Web of Science, Scopus, and Science Direct) during 2004-2020. The publications that focused on the procurement of medical devices and address the issue of value in procurement were selected. The publications whose full-text was not available and were not in English were excluded. By using data charting tables, selected articles were reviewed and concepts and definitions were extracted. Results: According to the eligibility criteria and reference checking, 24 documents were selected. There are different definition and understanding for value-based procurement (VBP). Identified characteristics of VBP are information, actors Collaboration, patient experience, value analysis team, ability to evaluate alternatives, value proposition, competitive dialogue, and weighing evaluation criteria. Conclusion: VBP is a framework that guides the review and decision-making to procure medical devices. In this framework, all dimensions of the value equation (outcome/related costs) must be considered and weighted. Health systems need to work on identified aspects.

An analysis of disparities in access to health care in Iran: evidence from Lorestan province.

Equal distribution of healthcare facilities in order to increase the accessibility of the individuals to services is one of the main pillars in improvement of health. This study was aimed to examine the disparities in access to health care services across the cities of Lorestan province located in west of Iran. This study is a descriptive study. Data related to indicators of institutional and manpower was collected using statistical yearbook of Statistical Centre of Iran (SCI) and analyzed by Scaogram Analysis Model. The results revealed distinct regional disparities in health care services across Lorestan province. According to Scalogram analysis model, Khorramabad and Delfan towns were ranked as the first and the last according to access to health care services. Overally, 44% of the cities are undeveloped and only 22% are credited as developed. Taking the advantage of development-oriented programs, reduction of the gap in health care services in the must be considered in the health policy. Therefore, Delfan, Dorood, Koohdasht and Selseleh are characterized as the underdeveloped and consequently urgently should be considered in planning and deprivation programs.