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.

Compliance to Care Guidelines for Duchenne Muscular Dystrophy.

BACKGROUND: International care guidelines for Duchenne muscular dystrophy (DMD) were published in 2010, but compliance in clinical practice is unknown. OBJECTIVE: The objective of our study was to compare real-world DMD care in Germany, Italy, the UK, and the US with the clinical recommendations. METHODS: DMD patients from Germany, Italy, the UK, and the US were identified through Translational Research in Europe - Assessment & Treatment of Neuromuscular Diseases (TREAT-NMD) registries and invited with a caregiver to complete a questionnaire with questions regarding DMD-related healthcare. Estimates of care were stratified by disease stage (early/late ambulatory/non-ambulatory) and compared against the care guidelines. RESULTS: A total of 770 patients (173 German, 122 Italian, 191 UK, and 284 US) completed the questionnaire. Poor compliance to guidelines of routine follow-up by neuromuscular, cardiac, and respiratory specialists, physiotherapy, and access to medical devices and aids were observed in all countries. Less than 27% (209 of 770) of patients met all absolute recommendations, ranging from 9% (11 of 122) in Italy to 37% (70 of 191) in the UK, and from 49% (76 of 155) in the early ambulatory class to 16% (33 of 205) in the late non-ambulatory class. CONCLUSIONS: We show that the medical management of DMD varies substantially between Germany, Italy, the UK, and the US. Experience of real-world DMD care appears to be in poor agreement with the DMD clinical guidelines and increased compliance is urgently needed to improve treatment outcomes and enable patients to lead fulfilling, independent lives into adulthood.

The burden of Duchenne muscular dystrophy: an international, cross-sectional study.

OBJECTIVE: The objective of this study was to estimate the total cost of illness and economic burden of Duchenne muscular dystrophy (DMD). METHODS: Patients with DMD from Germany, Italy, United Kingdom, and United States were identified through Translational Research in Europe-Assessment & Treatment of Neuromuscular Diseases registries and invited to complete a questionnaire online together with a caregiver. Data on health care use, quality of life, work status, informal care, and household expenses were collected to estimate costs of DMD from the perspective of society and caregiver households. RESULTS: A total of 770 patients (173 German, 122 Italian, 191 from the United Kingdom, and 284 from the United States) completed the questionnaire. Mean per-patient annual direct cost of illness was estimated at between $23,920 and $54,270 (2012 international dollars), 7 to 16 times higher than the mean per-capita health expenditure in these countries. Indirect and informal care costs were substantial, each constituting between 18% and 43% of total costs. The total societal burden was estimated at between $80,120 and $120,910 per patient and annum, and increased markedly with disease progression. The corresponding household burden was estimated at between $58,440 and $71,900. CONCLUSIONS: We show that DMD is associated with a substantial economic burden. Our results underscore the many different costs accompanying a rare condition such as DMD and the considerable economic burden carried by affected families. Our description of the previously unknown economic context of a rare disease serves as important intelligence input to health policy evaluations of intervention programs and novel therapies, financial support schemes for patients and their families, and the design of future cost studies.

Annual direct medical cost of active systemic lupus erythematosus in five European countries.

OBJECTIVES: To evaluate the annual direct medical cost of managing adult systemic lupus erythematosus (SLE) patients with active autoantibody positive disease in Europe. METHODS: A 2-year, retrospective, multicentre, observational study was conducted in five countries (France, Germany, Italy, Spain and the UK). Data included patients' characteristics, disease activity and severity, flare assessments and health resource use (eg, laboratory tests, medications, specialist visits and hospitalisations). Costs were assessed from the public payers' perspective. Cost predictors were estimated by multivariate regression models. RESULTS: Thirty-one centres enrolled 427 consecutive eligible patients stratified equally by disease severity. At baseline, mean (SD) age was 44.5 (13.8) years, 90.5% were women and mean (SD) SLE duration was 10.7 (8.0) years. The SELENA-SLEDAI (11.2 vs 5.3) and SLICC/ACR index (1.0 vs 0.7) scores were higher in severe patients. Over the study period, patients experienced on average 1.02 (0.71) flares/year. The mean annual direct medical cost was higher in severe compared to non-severe patients (€4748 vs €2650, p<0.001). Medication costs were €2518 in severe versus €1251 in non-severe patients (p<0.001). Medications represented 53% and 47% of the total cost for severe and non-severe patients, respectively, primarily due to immunosuppressants and biologics. Flares, especially severe flares, were identified as the major cost predictor, with each flare increasing the annual total cost by about €1002 (p<0.001). CONCLUSIONS: The annual direct medical cost of SLE patients in Europe is related to disease severity and flares. Medical treatments were the main cost drivers. Severe flares and major organ involvement were identified as important cost predictors.

A pilot study of multicriteria decision analysis for valuing orphan medicines.

OBJECTIVE: To pilot the use of multicriteria decision analysis to establish and apply a framework of weighted attributes to value orphan medicinal products. METHODS: Literature searches on the natural history and burden of 40 rare diseases and of how payers assess treatment value and three workshops with, respectively, GlaxoSmithKline managers working on orphan medicinal products, European Union clinical and health economics experts, and representatives of rare diseases patient groups in the European Union. RESULTS: Eight nonmonetary attributes were identified and weights agreed: four concern the disease being treated and four the treatment itself. About half of the weight went to attributes of the disease treated and half to attributes of the treatment. Patient group representatives gave greater weight than did the experts to patients' and carers' quality of daily life. CONCLUSIONS: The multicriteria decision analysis approach piloted works and could be developed for use by payers and health technology assessment bodies.

Prasugrel vs clopidogrel in patients with acute coronary syndrome undergoing percutaneous coronary intervention: a model-based cost-effectiveness analysis for Germany, Sweden, the Netherlands, and Turkey.

OBJECTIVE: To evaluate the long-term cost-effectiveness of 12-months treatment with prasugrel vs clopidogrel from four European healthcare systems' perspectives (Germany, Sweden, the Netherlands, and Turkey). METHODS: In the TRITON-TIMI 38 trial, patients with an acute coronary syndrome (ACS) undergoing percutaneous coronary intervention (PCI) were treated with prasugrel or clopidogrel. Prasugrel reduced the composite end-point (cardiovascular death, MI, or stroke), but increased TIMI major bleeding. A Markov model was constructed to facilitate a lifetime horizon for the analysis. A series of risk equations constructed using individual patient data from TRITON-TIMI 38 was used to estimate risks of clinical events. Quality-adjusted life-years (QALYs) were derived by weighting survival time by estimates of health-related quality-of-life. Incremental cost-effectiveness is presented based on differences in treatments' mean costs and QALYs for the licensed population in TRITON-TIMI 38, and the sub-groups of UA-NSTEMI, STEMI, diabetes, and the 'core clinical cohort' (<75 years, ≥60 kg, no history of stroke or TIA). RESULTS: Mean cost of study drug was €364 (Turkey) to €818 (Germany) higher for prasugrel vs clopidogrel. Rehospitalization costs at 12 months were lower for prasugrel due to reduced rates of revascularization, although hospitalization costs beyond 12 months were higher due to longer life expectancy associated with lower rates of non-fatal MI in the prasugrel group. The incremental cost per QALY saved with prasugrel in the licensed population ranged from €6520 (for Sweden) to €14,350 for (Germany). Prasugrel's cost per QALY was more favourable still in the STEMI and diabetes sub-groups of the licensed population. LIMITATIONS: Probabilistic analyses of the whole trial population is impractical due to the number of individual patient profiles over which population level results are calculated. CONCLUSION: Among patients undergoing PCI for ACS, treatment with prasugrel compared with clopidogrel resulted in favourable cost-effectiveness profiles from these healthcare systems' perspectives.

Clinical outcomes, resource use, and costs at 1 year in patients with acute coronary syndrome undergoing PCI: results from the multinational APTOR registry.

BACKGROUND: Limited prospectively collected data are available on the total outcomes, cost estimates, and quality of life associated with treatment of acute coronary syndrome (ACS) through 1 year in a nonclinical-trial setting, or on the impact of new clinical events by 1 year on resource utilization and costs. METHODS: The Antiplatelet Therapy Observational Registry (APTOR) 12-month study followed 1,335 concurrently recruited ACS patients undergoing percutaneous coronary intervention (PCI) and treated with antiplatelet therapy from France, Spain, and the United Kingdom in a "real world" clinical setting. Data were collected on clinical events, resource utilization, quality of life, and cost estimates through 1-year follow-up. RESULTS: By 1 year, 14.4% (95% CI 12.7-16.4%) of patients experienced a clinical event of death, MI, stroke, unstable angina, urgent target vessel revascularization, or acute heart failure. Costs by 1 year were higher among those who had a new clinical event (£8,988, 95% CI £7,848, £10,395) as compared with those with no events (£5,809, 95% CI £5,486, £6,161). This increased cost was due to higher postdischarge resource use costs. Using the EQ-5D assessment at 1 year, quality of life was directionally lower in those patients who had experienced a new clinical event. CONCLUSIONS: The risk of experiencing a new clinical event during the year following an ACS, which was treated with PCI, remains high among European patients, with one-seventh of patients having a new event. These additional clinical outcomes reduce quality of life and increase health care expenditures, expanding the already high cost of treatment for ACS.

International data on supportive therapies at 1 year in acute coronary syndrome patients undergoing PCI: results from the APTOR study.

BACKGROUND: Supportive therapies of exercise and diet-modifying secondary prevention programmes are associated with reduced morbidity and mortality in acute coronary syndrome (ACS) patients. We sought to evaluate the frequency and correlates of referral to these supportive therapies, and their impact on concordance with prescribed secondary prevention medications at 1 year among ACS patients undergoing percutaneous coronary intervention (PCI) in three European countries. DESIGN/METHODS: Data on referral for exercise and diet supportive therapies were collected at discharge through to 1 year in the Antiplatelet Therapy Observational Registry (APTOR) prospective observational study conducted in France, Spain and the UK in 1335 patients. RESULTS: 40% of patients received referral for exercise or diet, while three out of five patients received neither, with large variation between countries. Predictors of recommendation for either diet or exercise when excluding country were enrolment in a non-teaching centre (odds ratio [OR] 1.62, 95% CI [confidence interval] 1.33-1.97, p < 0.0001) and use of only a bare metal stent during PCI (OR 1.59, 95% CI 1.30-1.92, p = 0.0002), while weight and BMI had no bearing. Patients recommended either diet or exercise programmes had significantly more secondary prevention medication rates for each of the five predefined evidence-based BASIC (beta-blockers, aspirin, statins, ACE-inhibitors/ARBs and clopidogrel) medication therapies at 1 year. CONCLUSION: Following an ACS treated with PCI, by 1 year the majority of European patients were not recommended supportive therapies of exercise and dietary secondary prevention programmes, which have previously been associated with reduced morbidity and mortality and are recommended in the guidelines. Those recommended such therapies had considerably improved concordance with evidence-based therapies such as aspirin, clopidogrel and statins prescribed at 1 year. These data show a need for greater adherence to the European guidelines to ensure ACS patients are recommended such therapies.

Treatment patterns in acute coronary syndrome patients in the United Kingdom undergoing PCI.

AIMS: To evaluate practice patterns in acute coronary syndrome (ACS) patients undergoing percutaneous coronary intervention (PCI), focusing on the United Kingdom (UK). METHODS AND RESULTS: The Antiplatelet Therapy Observational Registry (APTOR) is a prospective observational study of consecutive ACS patients undergoing PCI (N=1525) from January-August 2007 in the UK, France, and Spain. In the UK, median time from hospital admission to PCI was one day post-admission (IQR 0,4) among STEMI patients and five days (IQR 2,9) among unstable angina/non-ST-segment elevation myocardial infarction (UA/NSTEMI) patients. Patients in the UK most frequently received a 300 mg aspirin loading dose (85%), 300 mg clopidogrel loading dose (70%), and 75 mg clopidogrel maintenance dose (99%). Loading dose was given on the day of hospitalisation to 80% of STEMI patients and 68% of UA/NSTEMI patients. Clopidogrel was discontinued by 12 months in 30% of UK patients. Length of hospitalisation was similar between the three countries. CONCLUSIONS: Despite established consensus guidelines for ACS patient management, APTOR data show disparity in management practices for ACS patients undergoing PCI in the UK and two other European countries. These data can help provide focus for areas of ACS management requiring improvements to meet guideline therapy, including reducing time from hospitalisation to PCI and maintaining 12 months of dual antiplatelet therapy for all ACS patients undergoing stenting.

Treatment patterns in patients with acute coronary syndrome undergoing percutaneous coronary intervention.

BACKGROUND: The Antiplatelet Therapy Observational Registry (APTOR) is a prospective observational study of acute coronary syndrome (ACS) patients undergoing percutaneous coronary intervention (PCI) in a 'real world' clinical setting. Here the authors report on the management of ACS patients in three European countries during the hospital phase and through 12-months' follow-up, including use of antiplatelet agents, co-medications and stents, as well as clinical outcomes at 12 months. METHODS: ACS patients undergoing PCI (N = 1525) from January to August 2007 were planned to be consecutively recruited in France, Spain and the UK. RESULTS: Index diagnosis was unstable angina/non-ST-segment elevation myocardial infarction (MI) in 62% and ST-segment elevation MI in 38%. Prior to the index ACS event, 17% were prescribed both aspirin and clopidogrel. While in-hospital clopidogrel and aspirin use was similar across countries, considerable variation was observed between countries at 12 months (clopidogrel 66-75%; aspirin 86-95%). The UK most frequently used a 300-mg clopidogrel loading dose (70%) compared with France (53%) and Spain (56%), while >300 mg was used in 21%, 34% and 16% patients, respectively. Bare metal stents only were used in 42% of subjects, drug-eluting stents (DES) only in 40%, and both in 10%, with the highest rates of DES use in Spain (70%) followed by the UK (47%) and France (31%). The composite endpoint of cardiovascular (CV) death, MI or stroke occurred in 4.7% of patients by 12 months. CONCLUSIONS: APTOR shows marked variation in ACS management between countries in antiplatelet therapy, co-medications and stent use. Due to the observational design of the registry, statistical testing was not applied and data should be seen as hypothesis generating. These data provide a useful benchmark for comparison with current guidelines.

Adherence to guidelines for sensitivity analysis: cost-effectiveness analyses of dual oral antiplatelet therapy.

OBJECTIVE: Cost-effectiveness analyses of new treatments for cardiovascular disease frequently require input parameters whose values are known with uncertainty due to limited data. The objective of this paper is to examine the extent to which published sensitivity analyses addressing this uncertainty adhere to Health Technology Assessment (HTA) guidelines. RESEARCH DESIGN AND METHODS: A systematic review of published cost-effectiveness analyses was performed for an example drug treatment scenario, dual oral antiplatelet therapy compared with aspirin alone following acute coronary syndromes and/or percutaneous coronary intervention. The following medical literature databases were searched for articles published from January 1997 to June 2007: PubMed, Cochrane Collaboration, EMBASE and the Health Economic Evaluation Database (HEED). Evidence tables were created to show the sensitivity of the cost-effectiveness estimates to changes in the input parameter values, as well as the data sources used for the reference-case and sensitivity analysis input parameter values. The extent to which the sensitivity analyses adhered to HTA guidelines were also examined. RESULTS: Cost-effectiveness ratios were most sensitive to changes in the efficacy of dual antiplatelet therapy and reference-case model assumptions about costs beyond the trial period. Although alternative values tested in the sensitivity analysis for some input parameters were based on observed ranges or distributions, alternative values tested for many other input parameters were assumed without justification. CONCLUSIONS: Sensitivity analyses in the cost-effectiveness studies of dual oral antiplatelet therapy were not fully adherent with HTA guidelines. In particular, long-term costs and benefits were not always included in the sensitivity estimates, the impact of differential effects on death and myocardial infarction was not explored, and justification for the alternative parameter values tested was not always provided.

[Fibromyalgia prevalence in Tunisia]. / Prévalence de la fibromyalgie en Tunisie.

OBJECTIVE: to estimate fibromyalgia (FM) prevalence in Tunisia. METHODS: Data on a cross-section of 1000 individuals aged 15 years or older living in Sfax were collected by interviewers using the London Fibromyalgia Epidemiology Study Screening Questionnaire (LFES- SQ). The sampling was realized by empirical poll and respecting quota according to delegation, rural or urban environment, sex and age according to the demographic national data. The positive screened subjects were invited to be examined to confirm or exclude the FM by applying the 1999 ACR criteria. The questionnaire was administered to a second group of 252 volunteers, all were afterward examined. This allowed to study specificity and sensibility of the questionnaire and allowed to calculate the FM prevalence. RESULTS: 159 subjects were screened positive, only 141 were examined. The specialized exam allowed confirming the diagnosis of FM in 67 subjects. FM prevalence is different according to sex, age, study level and socio-economic level. Two hundred and fifty two volunteers answered the questionnaire then all examined. The questionnaire specificity was 90.8% and the sensibility 79.4%. FM prevalence in Tunisia, calculated by Bayes theorem, is estimated between 8.27% and 12.3%. CONCLUSION: FM prevalence in Tunisia is estimated at least at 8.27%.

Intravenous drug preparation practices: a survey in a French university hospital.

OBJECTIVE: To describe current practices for i.v. drug admixture preparation, to identify potential improvements for the enhancement of patient safety. DESIGN: A survey was conducted in a University hospital in Paris. Nurse practices were explored through the evaluation of five i.v. drug delivery systems: reconstituted freeze-dried drugs administered by syringe or i.v. bags, reconstituted drugs from vials administered by syringe or i.v. bags Ready to Use (RtU). PARTICIPANTS: i.v. drug preparation practices were documented by a representative sample of nurses in the following departments: intensive care, emergency, abdominal surgery, cardiology, infectious diseases, hepatology. MAIN OUTCOME MEASURES: Data were collected regarding: existence of written procedures for preparations, sources of information, labelling, methods of preparation and calculation of doses, nurse satisfaction regarding safety and ease of use of the different i.v. systems. RESULTS: A total of 299 questionnaires were completed and 100 nurses from the chosen wards were surveyed. The study highlighted a lack of procedure (71-85%) and a lack of labelling (37%). CONCLUSION: This survey highlighted areas for improvement in the preparation of i.v. drugs. It may contribute to raising awareness among nurses and physicians about the risks of medication errors. This survey also helped the pharmacy department in supporting the development of pharmaceutical procedures, the development of satellite pharmacy, the set up of training sessions for i.v. preparation and the switch toward ready to use packages when these are available.

Ready-to-use injection preparations versus conventional reconstituted admixtures: economic evaluation in a real-life setting.

OBJECTIVE: To measure, in a real-life setting, the benefits of using ready-to-use (RTU) injection preparations compared with conventional reconstituted admixtures (Admix) in terms of cost savings. DESIGN AND PERSPECTIVE: An economic model was developed, based on a randomised study. The perspective of the economic evaluation was that of the hospital administration. A microcosting approach was used to determine costs. SETTING: Department of Cardiac Surgery at the Charleroi University Hospital in Belgium. STUDY PARTICIPANTS: Fifty-eight patients undergoing cardiac surgery under cardiopulmonary bypass were randomised to Admix dobutamine or to the RTU dobutamine group and were followed up during 24 hours after initiation of dobutamine therapy. MAIN OUTCOME MEASURES AND RESULTS: Nursing time was reduced by 32% in the RTU group compared with the Admix group. Material cost was also reduced and the overall cost savings in the RTU group amounted to a 60% reduction in the cost of the conventional Admix process (p<0.001). When drug cost was included in the equation, cost savings varied from 1.60 euros (EUR) to EUR21.40 per patient depending on dosage. There was no difference between the two groups in terms of safety and efficacy. A user satisfaction survey showed that medical staff especially welcomed improved ease of preparation and potential for prevention of errors and risks of handling. CONCLUSION: This study confirmed the potential for RTU forms to reduce nursing time associated with preparation and administration of intravenous admixtures and to enable overall cost savings.