Background: Clinical decision support (CDS) systems have emerged as tools providing intelligent decision making to address challenges of critical care. CDS systems can be based on existing guidelines or best practices; and can also utilize machine learning to provide a diagnosis, recommendation, or therapy course. Methods: This research aimed to identify evidence-based study designs and outcome measures to determine the clinical effectiveness of clinical decision support systems in the detection and prediction of hemodynamic instability, respiratory distress, and infection within critical care settings. PubMed, ClinicalTrials.gov and Cochrane Database of Systematic Reviews were systematically searched to identify primary research published in English between 2013 and 2018. Studies conducted in the USA, Canada, UK, Germany and France with more than 10 participants per arm were included. Results: In studies on hemodynamic instability, the prediction and management of septic shock were the most researched topics followed by the early prediction of heart failure. For respiratory distress, the most popular topics were pneumonia detection and prediction followed by pulmonary embolisms. Given the importance of imaging and clinical notes, this area combined Machine Learning with image analysis and natural language processing. In studies on infection, the most researched areas were the detection, prediction, and management of sepsis, surgical site infections, as well as acute kidney injury. Overall, a variety of Machine Learning algorithms were utilized frequently, particularly support vector machines, boosting techniques, random forest classifiers and neural networks. Sensitivity, specificity, and ROC AUC were the most frequently reported performance measures. Conclusion: This review showed an increasing use of Machine Learning for CDS in all three areas. Large datasets are required for training these algorithms; making it imperative to appropriately address, challenges such as class imbalance, correct labelling of data and missing data. Recommendations are formulated for the development and successful adoption of CDS systems.

Background: Clinical decision support (CDS) systems have emerged as tools providing intelligent decision making to address challenges of critical care. CDS systems can be based on existing guidelines or best practices; and can also utilize machine learning to provide a diagnosis, recommendation, or therapy course. Methods: This research aimed to identify evidence-based study designs and outcome measures to determine the clinical effectiveness of clinical decision support systems in the detection and prediction of hemodynamic instability, respiratory distress, and infection within critical care settings. PubMed, ClinicalTrials.gov and Cochrane Database of Systematic Reviews were systematically searched to identify primary research published in English between 2013 and 2018. Studies conducted in the USA, Canada, UK, Germany and France with more than 10 participants per arm were included. Results: In studies on hemodynamic instability, the prediction and management of septic shock were the most researched topics followed by the early prediction of heart failure. For respiratory distress, the most popular topics were pneumonia detection and prediction followed by pulmonary embolisms. Given the importance of imaging and clinical notes, this area combined Machine Learning with image analysis and natural language processing. In studies on infection, the most researched areas were the detection, prediction, and management of sepsis, surgical site infections, as well as acute kidney injury. Overall, a variety of Machine Learning algorithms were utilized frequently, particularly support vector machines, boosting techniques, random forest classifiers and neural networks. Sensitivity, specificity, and ROC AUC were the most frequently reported performance measures. Conclusion: This review showed an increasing use of Machine Learning for CDS in all three areas. Large datasets are required for training these algorithms; making it imperative to appropriately address, challenges such as class imbalance, correct labelling of data and missing data. Recommendations are formulated for the development and successful adoption of CDS systems.

Background: A wide range of rare diseases can have fiscal impacts on government finances that extend beyond expected healthcare costs. Conditions preventing people from achieving national lifetime work averages will influence lifetime taxes paid and increase the likelihood of dependence on public income support. Consequently, interventions that influence projected lifetime work activity, morbidity and mortality can have positive and negative fiscal consequences for government. The aim of this study was to apply a public economic framework to a rare disease that takes into consideration a broad range of costs that are relevant to government in relation to transfers received and taxes paid. As a case study we constructed a simulation model to calculate the fiscal life course of an individual with hereditary transthyretin-mediated (hATTR) amyloidosis in The Netherlands. In this lethal disease different progressive disease scenarios occur, including polyneuropathy and/or cardiomyopathy. Results: Due to progressive disability, health care resource use, and early death, hATTR amyloidosis with polyneuropathy receives more transfers from government compared to the general population. In a scenario where a patient is diagnoses with hATTR at age 45, an individual pays €180,812 less in lifetime taxes and receives incrementally €111,695 in transfers from the government, compared to a person without hATTR. Patients suffering from cardiomyopathy die after median 4 years. The health costs of this scenario are therefore lower than that of the other polyneuropathy-based scenarios. Conclusions: The fiscal analysis illustrates how health conditions influence not only health costs, but also the cross-sectorial public economic burden attributed to lost tax revenues and public disability allowances. Due to the progressive nature of hATTR amyloidosis used in this study, public costs including disability increase as the disease progresses with reduced lifetime taxes paid. The results indicate that halting disease progression early in the disease course would generate fiscal benefits beyond health benefits for patients. This analysis highlights the fiscal consequences of diseases and the need for broader perspectives applied to evaluate health conditions. Conventional cost-effectiveness framework used by many health technology assessment agencies have well-documented limitations in the field of rare diseases and fiscal modeling should be a complementary approach to consider.

Limited resources and high treatment costs are arguments often used in many public health systems in low-and middleincome countries to justify providing limited treatments for people with infertility. In this analysis, we apply a government public economic perspective to evaluate public subsidy for in-vitro fertilization (IVF) in South Africa. A fiscal model was developed that considered lifetime direct and indirect taxes paid and government transfers received by a child conceived by IVF. The model was constructed from public data sources and was adjusted for mortality, age-specific educational costs, participation in the informal economy, proportions of persons receiving social grants, and health costs. Based on current proportions of individuals receiving social grants and average payments, including education and health costs, we estimate each citizen will receive ZAR513,165 (USD35,587) in transfers over their lifetime. Based on inflated age-specific earnings, we estimate lifetime direct and indirect taxes paid per citizen of ZAR452,869 (USD31,405) and ZAR494,521 (USD34,294), respectively, which also includes adjustments for the proportions of persons participating in the informal economy. The lifetime net tax after deducting transfers was estimated to be ZAR434,225 (USD31,112) per person. Based on the average IVF investment cost needed to achieve one live birth, the fiscal return on investment (ROI) for the South African Government is 5.64. Varying the discount rate from 4% to 7%, the ROI ranged from 9.54 to 1.53, respectively. Positive economic benefits can emanate from public financing of IVF. The fiscal analytic framework described here can be a useful approach for health services to evaluate future public economic benefits.

Using FS resulted in cost savings in hospitals based on reduced time to complete surgery, hospitalization time post-op, and lower adverse outcomes. Indirect cost savings were also found in favor of FS when comparing the two alternatives from a societal perspective, as patients were able to return to work more promptly in the FS group versus the tack screws group.