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.

Natural History, Quality of Life, and Outcome in Cardiac Transthyretin Amyloidosis.

BACKGROUND: Transthyretin amyloidosis cardiomyopathy (ATTR-CM) is an increasingly recognized cause of heart failure in older individuals. We sought to characterize the natural history of ATTR-CM and compare outcomes and quality of life among patients with acquired and hereditary forms of the disease. METHODS: We studied 711 patients with wild-type ATTR-CM, 205 with hereditary ATTR-CM associated with the V1221 variant (V122I-hATTR-CM), and 118 with non-V122I-hATTR-CM at the UK National Amyloidosis Center between 2000 and 2017. Patients underwent prospective protocolized evaluations comprising assessment of cardiac parameters, functional status by 6-minute walk test, quality of life according to the Kansas City Cardiomyopathy Questionnaire, and survival. Hospital service usage pre- and postdiagnosis was established using English central health records in a subset of patients. RESULTS: There was substantial diagnostic delay, with patients using hospital services a median (interquartile range) of 17 (9-27) times during the 3 years before diagnosis, by which time quality of life was poor; diagnosis of wild-type ATTR-CM was delayed >4 years after presentation with cardiac symptoms in 42% of cases. Patients with V122I-hATTR-CM were more impaired functionally ( P<0.001) and had worse measures of cardiac disease ( P<0.001) at the time of diagnosis, a greater decline in quality of life, and poorer survival ( P<0.001) in comparison with the other subgroups. CONCLUSIONS: ATTR-CM is an inexorably progressive and eventually fatal cardiomyopathy associated with poor quality of life. Diagnosis is often delayed for many years after symptoms develop. Improved awareness and wider use of recently validated diagnostic imaging methods are urgently required for patients to benefit from recent therapeutic developments.

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.