Utilising artificial intelligence to determine patients at risk of a rare disease: idiopathic pulmonary arterial hypertension.

Idiopathic pulmonary arterial hypertension is a rare and life-shortening condition often diagnosed at an advanced stage. Despite increased awareness, the delay to diagnosis remains unchanged. This study explores whether a predictive model based on healthcare resource utilisation can be used to screen large populations to identify patients at high risk of idiopathic pulmonary arterial hypertension. Hospital Episode Statistics from the National Health Service in England, providing close to full national coverage, were used as a measure of healthcare resource utilisation. Data for patients with idiopathic pulmonary arterial hypertension from the National Pulmonary Hypertension Service in Sheffield were linked to pre-diagnosis Hospital Episode Statistics records. A non-idiopathic pulmonary arterial hypertension control cohort was selected from the Hospital Episode Statistics population. Patient history was limited to ≤5 years pre-diagnosis. Information on demographics, timing/frequency of diagnoses, medical specialities visited and procedures undertaken was captured. For modelling, a bagged gradient boosting trees algorithm was used to discriminate between cohorts. Between 2008 and 2016, 709 patients with idiopathic pulmonary arterial hypertension were identified and compared with a stratified cohort of 2,812,458 patients classified as non-idiopathic pulmonary arterial hypertension with ≥1 ICD-10 coded diagnosis of relevance to idiopathic pulmonary arterial hypertension. A predictive model was developed and validated using cross-validation. The timing and frequency of the clinical speciality seen, secondary diagnoses and age were key variables driving the algorithm's performance. To identify the 100 patients at highest risk of idiopathic pulmonary arterial hypertension, 969 patients would need to be screened with a specificity of 99.99% and sensitivity of 14.10% based on a prevalence of 5.5/million. The positive predictive and negative predictive values were 10.32% and 99.99%, respectively. This study highlights the potential application of artificial intelligence to readily available real-world data to screen for rare diseases such as idiopathic pulmonary arterial hypertension. This algorithm could provide low-cost screening at a population level, facilitating earlier diagnosis, improved diagnostic rates and patient outcomes. Studies to further validate this approach are warranted.

High levels of healthcare utilization prior to diagnosis in idiopathic pulmonary arterial hypertension support the feasibility of an early diagnosis algorithm: the SPHInX project.

Idiopathic pulmonary arterial hypertension (iPAH) is a rare progressive, life-shortening disease, usually diagnosed at an advanced stage. We hypothesize that patients with iPAH exhibit patterns of health-seeking behavior before diagnosis that will allow the development of earlier identification tools. The Sheffield Pulmonary Hypertension IndeX (SPHInX) project aims to develop a predictive algorithm based on routinely collected healthcare resource utilization (HCRU) data. This report focuses on the initial feasibility of the project, examining whether Hospital Episode Statistics (HES) data from the National Health Service in England have sufficient richness to support the development of an early diagnosis algorithm. This is a two-stage study. First, hospital interactions during 2009-2014 captured in HES data identified 127,815 adult patients with pulmonary hypertension (PH) ICD-10 codes, containing a probable iPAH cohort with incidence and demographics similar to the reported literature. HCRU was high in the three years before diagnosis. Second, to examine HCRU in patients with a confirmed iPAH diagnosis, we built the SPHInX dataset incorporating all patients investigated for suspected PH in the Sheffield Pulmonary Vascular Disease Unit during 2008-2016 (n = 6674). For the SPHInX dataset, data could be linked to HES in 98.6% of cases and patients with confirmed iPAH had similar levels of pre-diagnosis HCRU. In conclusion, patients with probable iPAH identified using HES and patients with confirmed iPAH have high levels of HCRU for several years before diagnosis. Artificial intelligence models will now be used to develop the SPHInX algorithm to screen for undiagnosed iPAH in the general population.

Assessing mNIS+7Ionis and international neurologists' proficiency in a familial amyloidotic polyneuropathy trial.

INTRODUCTION: Polyneuropathy signs (Neuropathy Impairment Score, NIS), neurophysiologic tests (m+7Ionis ), disability, and health scores were assessed in baseline evaluations of 100 patients entered into an oligonucleotide familial amyloidotic polyneuropathy (FAP) trial. METHODS: We assessed: (1) Proficiency of grading neurologic signs and correlation with neurophysiologic tests, and (2) clinometric performance of modified NIS+7 neurophysiologic tests (mNIS+7Ionis ) and its subscores and correlation with disability and health scores. RESULTS: The mNIS+7Ionis sensitively detected, characterized, and broadly scaled diverse polyneuropathy impairments. Polyneuropathy signs (NIS and subscores) correlated with neurophysiology tests, disability, and health scores. Smart Somatotopic Quantitative Sensation Testing of heat as pain 5 provided a needed measure of small fiber involvement not adequately assessed by other tests. CONCLUSIONS: Specially trained neurologists accurately assessed neuropathy signs as compared to referenced neurophysiologic tests. The score, mNIS+7Ionis , broadly detected, characterized, and scaled polyneuropathy abnormality in FAP, which correlated with disability and health scores. Muscle Nerve 56: 901-911, 2017.

Health-economic comparison of paricalcitol, calcitriol and alfacalcidol for the treatment of secondary hyperparathyroidism during haemodialysis.

This study evaluated the health-economic consequences of use of intravenous paricalcitol (Zemplar), oral calcitriol or oral and intravenous alfacalcidol for the treatment of patients with secondary hyperparathyroidism, focusing on a third-party payer perspective through inclusion of medication and hospital costs, survival rates and utilities. Cost values were based on German treatment recommendations and prices. Reference values for survival rates and utilities were based on the results of a MEDLINE search. The analysis showed a clear advantage for intravenous paricalcitol with respect to costs, effectiveness and utilities compared with treatment with oral calcitriol or intravenous alfacalcidol. Since the results were very cost sensitive with respect to selected diagnosis-related groups (DRGs) for kidney disease with dialysis, a sensitivity analysis was performed. This demonstrated first-order dominance of intravenous paricalcitol for a wide range of hospitalisation costs. In conclusion, this analysis suggested a clear benefit from the perspective of a third-party payer for intravenous paricalcitol compared with oral calcitriol and intravenous alfacalcidol in the treatment of patients with secondary hyperparathyroidism.

Assessment of clinical and economic benefits of weight management with sibutramine in general practice in Germany.

Obesity is associated with major health risks and a high economic burden impacting on health care systems. This study utilises the latest evidence from randomised clinical trials (RCTs) to explore and to assess the cost effectiveness of sibutramine in combination with diet and lifestyle advice compared to diet and lifestyle advice alone for the treatment of obese subjects without comorbidities at baseline in Germany. New evidence from recently published RCTs and post-marketing surveillance studies, including health economic data as well as quality of life (QoL) data, were used to model the long-term outcomes of weight management with sibutramine in German practice. German healthcare costs and new data from over 8,000 patients were analysed based on a recently published model. These new RCT data were used to model weight losses, proportion of responders to treatment, utilities by weight loss and variability in weight regain post-treatment. Costs and QoL benefits associated with weight loss (using SF-36 data from sibutramine trials), reduced incidence of coronary heart disease (using Framingham equations) and diabetes were used to estimate the cost per quality adjusted life year of sibutramine treatment. For 1,000 patients treated with sibutramine for 1 year, extrapolating outcomes over 4 further years, sibutramine is estimated to save 4.18 CHD events, 2.58 diabetes incident cases and give 51.5 more quality-adjusted life years (QALYs). The cost-utility analysis (CUA) estimates 13,706 euro per QALY gained. Results are sensitive to changes in weight loss, rate of weight regain and discounting rate. Although the non-pharmacological weight management programme in the comparator arm yielded higher weight losses than generally observed in clinical practice, these results demonstrate that additional sibutramine treatment is a cost effective therapy for an obese population without comorbidities in Germany. The CUA results are within the range generally accepted as cost effective and should be viewed as conservative when generalizing to settings offering standard non-pharmacological treatment.

Development and validation of the Economic Assessment of Glycemic Control and Long-Term Effects of diabetes (EAGLE) model.

BACKGROUND: The Economic Assessment of Glycemic control and Long-term Effects of diabetes (EAGLE) model was developed to provide a flexible and comprehensive tool for the simulation of the long-term effects of diabetes treatment and related costs in type 1 and type 2 diabetes. METHODS: EAGLE simulations are based on risk equations, which were developed using published data from several large studies including the Diabetes Control and Complications Trial, the United Kingdom Prospective Diabetes Study, and the Wisconsin Epidemiological Study of Diabetic Retinopathy. Risk equations for the probability of complications (including hypoglycemia, retinopathy, macular edema, end-stage renal disease, neuropathy, diabetic foot syndrome, myocardial infarction, and stroke) were based on regression analyses, using linear, exponential, and quadratic regression formulae. Subsequent cost calculations are made from the simulated event rates. Internal validation of the EAGLE model was completed by comparing simulated event rates with the published event rates used as the basis for the model. RESULTS: EAGLE provides microsimulations of virtual patient cohorts for type 1 and type 2 diabetes over n years in 1-year cycles. Complications include microvascular and macrovascular events and death, which are calculated over time as cumulative incidences. Glycosylated hemoglobin levels over time are simulated in relation to treatment regimen. Internal validation demonstrated that each mean event rate simulated by EAGLE overlapped with the published mean event (within a range of +/-10%). CONCLUSIONS: The EAGLE model is an evidence-based, internally valid tool for the assessment of the long-term effects of diabetes treatment and related costs.

Costs of irritable bowel syndrome in the UK and US.

Irritable bowel syndrome (IBS) is one of the most common functional gastrointestinal disorders, with an estimated prevalence rate in the general population of 10-15% in industrialised countries. Although IBS is not a life-threatening disease, it contributes significantly to a large segment of healthcare resource consumption. This review provides an overview of studies addressing the direct and indirect costs of IBS in the US and the UK. A systematic literature search was conducted in MEDLINE and the Cochrane library; additionally, all reference lists covering the years from 1960 to May 2004 were scanned. Twenty-four publications for the US and the UK, published between 1991 and 2003, were identified: 6 were excluded, 18 were included. Data for the UK, US and UK + US were reported in 5, 11 and 2 publications, respectively. Total direct cost estimates per patient per year ranged from US 348 dollars to US 8750 dollars (calculated for year 2002). The average number of days off work per year because of IBS was between 8.5 and 21.6; indirect costs ranged from US 355 dollars to US 3344 dollars. The total costs and cost components of IBS are influenced by several factors: features of the investigated patient group (age, limitation to healthcare seekers or all IBS patients, comorbidity, severity of symptoms), database used, method of data collection (retrospective or prospective, varying cost components, time-point of data collection in relation to index-date of IBS diagnosis, method of cost calculation [incidence or prevalence based]) and different healthcare systems in the US and the UK. These factors led to the incomparability of published data, thus no comprehensive picture can be drawn of the total costs related to IBS in the UK and US. Data underline the magnitude of the economic impact of IBS in the UK and US, which is increased by a factor of 1.1-6.0, compared with matched non-IBS control groups. IBS contributes both direct and indirect costs to the total healthcare bill. Further studies should take influencial factors into account and report related data carefully in order to provide useful and comparable published cost data. Additionally, further research on the cost effectiveness of diagnostic procedures and therapies in IBS is required to define strategies to help IBS patients improve their quality of life and reduce related costs.

Influence of two different reporting systems on counts of thromboembolic and bleeding complications after St. Jude medical valve replacement: results from the GELIA study.

BACKGROUND AND AIM OF THE STUDY: Different standards for the reporting of morbid events and different follow up techniques have a profound impact on reported morbidity after prosthetic valve replacement. Most studies follow the guidelines of The American Association of Thoracic Surgery (AATS) and The Society of Thoracic Surgeons (STS); the present authors' group has now developed an adapted Karnofsky scale which allows a more precise grading of the severity of morbid events. METHODS: The AATS/STS criteria and the adapted Karnofsky criteria were applied to the database of the German Experience with Low-Intensity Anticoagulation (GELIA) study. In a study population of 2,735 patients, GELIA compared three different intensities of oral anticoagulation in a prospective and randomized design. Patients registered morbid events prospectively by means of documentation cards. RESULTS: The overall rate of complications was comparable when utilizing the two classification systems. However, use of the AATS/STS criteria resulted in the counting of fewer bleeding complications, because only major bleedings were recorded. In contrast, the incidence of embolic complications was higher compared to the Karnofsky criteria because all events were counted, irrespective of their severity, while clinically insignificant (transient, reversible within 24 h) events were disregarded when using the Karnofsky grading. CONCLUSION: The adapted Karnofsky criteria provide a precise and easily understandable framework for the assessment of complications, with equal weighting of both hemorrhagic and embolic events.

Influenza treatment with neuraminidase inhibitors: cost-effectiveness and cost-utility in healthy adults in the United Kingdom.

We assessed the cost-effectiveness and cost-utility of treating influenza with neuraminidase inhibitors (oseltamivir and zanamivir) from a health care payer's and societal perspective in the United Kingdom. A simulation model was developed to predict morbidity and mortality due to influenza and its specified complications, comparing neuraminidase inhibitors with usual care in an otherwise healthy adult population. Robustness of the results was tested by one-way and multiway as well as probabilistic sensitivity analyses. Treatment with either neuraminidase inhibitor results in reduced morbidity and faster return to normal activities. However, oseltamivir dominates zanamivir in cost-utility analysis due to its lower costs. Comparing oseltamivir with usual care, the costs are pound14.36 per day of normal activity gained and pound5,600 per quality-adjusted life-year gained from the healthcare payer perspective. Oseltamivir dominates usual care from the societal perspective. Treatment with oseltamivir is a cost-effective strategy for otherwise healthy adults in the UK from both the healthcare payer and societal perspective.

International variation in resource utilisation and treatment costs for rheumatoid arthritis: a systematic literature review.

Recent years have witnessed substantial progress in understanding the cost implications of rheumatoid arthritis (RA). To assess the divergent methodologies and their impact on the resulting cost analyses in RA, we conducted a systematic literature review to summarise the scientific evidence of RA-induced costs. Sixty-five reviews, models or cost analyses on the burden of illness and general costs associated with RA were identified. They covered the US, Canada, Sweden, the UK, The Netherlands, Germany and Finland. Twenty-four cost analyses provided appropriate data about direct and/or indirect costs. Each study was summarised separately. Costs were discounted to 2003 and converted to US dollars. The costs per RA-year ranged from USD 1503 to USD 16,514. However, each study has to be interpreted individually, with consideration given to the study population, indication, age of the study, database used, type of therapy, setting, level of cost differentiation and data derivation. Health technology assessment reports offer sufficient space to adequately describe the composite parts and restrictive elements of different methodological approaches and analyses.

Thromboembolic and bleeding complications following St. Jude Medical valve replacement: results of the German Experience With Low-Intensity Anticoagulation Study.

STUDY OBJECTIVES: Due to their inherent thrombogenicity, mechanical cardiac valves necessitate lifelong oral anticoagulation. Less intensive oral anticoagulation than recommended earlier might result in a lower incidence of bleeding complications without increasing the embolic hazard significantly. DESIGN: Comparison of three different intensities of oral anticoagulation in a prospective, randomized multicenter design. Three months after valve replacement, patients were randomly assigned to stratum A, international normalized ratio (INR) 3.0 to 4.5; stratum B, INR 2.5 to 4.0; or stratum C, INR 2.0 to 3.5. PATIENTS: Data from 2,735 patients following aortic valve replacement (AVR; n = 2,024), mitral valve replacement (MVR; n = 553), and combined AVR and MVR (n = 158) with the St. Jude Medical (SJM) valve (St. Jude Medical; St. Paul, MN) between July 1993 and May 1999 were analyzed, covering a total follow-up period of 6,801 patient-years. All complications were registered prospectively. MEASUREMENTS AND RESULTS: Fifty-one thromboembolic events (TEs) were documented, resulting in a linearized incidence of 0.75 TEs per 100 patient-years, 22 of which were minor (0.32% per patient-year), 10 were moderate (0.15% per patient-year), and 19 were severe (0.28% per patient-year). Thromboembolism following AVR was significantly lower than after MVR (0.53% per patient-year vs 1.64% per patient-year). Patients reported 1,687 bleeding complications (24.8% per patient-year). The vast majority of bleeding complications (n = 1,509; 22.2% per patient-year) were classified as minor, 140 were classified as moderate (2.06% per patient-year), and 38 were classified as severe (0.56% per patient-year). The clinically relevant incidences of moderate and severe TEs and bleeding complications were not significantly different between the three prespecified INR strata. CONCLUSIONS: The intention-to-treat analysis of the results of the German Experience With Low Intensity Anticoagulation study leads to the unexpected result that despite a sophisticated reporting system, the incidence of moderate and severe TE and bleeding complications was comparably low in all INR strata and more or less within the so-called background incidence reported for an age-related "normal" population. This study supports reexamination of the intensity of anticoagulation in patients with the SJM valve.

Can progression of valvar aortic stenosis be predicted accurately?

BACKGROUND: It was the aim of the present study to elaborate criteria for the assessment of rapid hemodynamic progression of valvar aortic stenosis. These criteria are of special importance when cardiac surgery is indicated for other reasons but the established criteria for aortic valve replacement are not yet fulfilled. Such aspects of therapeutic planing were mostly disregarded in the past so that patients had to undergo cardiac reoperation within a few years. METHODS: Hemodynamic, echocardiographic, and clinical data of 169 men and 88 women with aortic stenosis, aged 55.2 +/- 15.7 years at their first and 63.4 +/- 15.6 years at their second cardiac catheterization, were analyzed. RESULTS: The progression rate of aortic valve obstruction was found to be dependent on the degree of valvar calcification ([VC] scoring 0 to III) and to be exponentially correlated with the aortic valve opening area (AVA) at initial catheterization. Neither age nor sex of the patient nor etiology of the valvar obstruction significantly influence the progression of aortic stenosis. If AVA decreases below 0.75 cm(2) with a present degree of VC = 0, or AVA of 0.8 with VC of I, AVA of 0.9 with VC of II, or AVA of 1.0 with VC of III, it is probable that aortic stenosis will have to be operated upon in the following years. CONCLUSIONS: The present data indicate that for clinical purposes and planning of valvar surgery the progression of asymptomatic aortic stenosis can be sufficiently predicted by the present aortic valve opening area and the degree of valvar calcification.

Economic burden of obesity and its complications in Germany.

This study estimated the economic burden of illness of obesity and selected comorbidities in terms of health outcome and costs to society and healthcare payer in Germany. The proportions of selected diseases (comorbidities) attributable solely to obesity were estimated using odds ratios/relative risks and prevalences based on data from the literature. The top-down approach was employed to match healthcare spending with the number of patients suffering from obesity (BMI 30+) and the major comorbidities to evaluate overall direct and indirect costs. In Germany there are approximately 12.24 million obese adults, 2.06-3.76 million of whom suffer from the selected comorbidities. From a societal perspective the total costs for obesity and comorbidities are euro 2,701-5,682 million per year and the direct treatment costs alone account for euro 1,343-2,699 million, imposing a major burden to the healthcare system. In view of the magnitude of the economic burden of illness there is a need for both further research and action at the health policy level.