Journal of Clinical Respiratory Diseases & Care: Open Access

Purpose: The 6 minute walk test used to evaluate patients with PH has many limitations. The ISWT, an automated progressively incremental and more physically demanding exercise test, has been useful to assess exercise tolerance in patients with severe COPD. Its application in patients with PH and particularly, pulmonary arterial hypertension (PAH) raises the concern of eliciting cardiovascular complications during testing. We wished to evaluate the safety of ISWT in patients with PH.

Methods: A retrospective review was performed on patients with RHC-confirmed PH who had undergone outpatient ISWT, predominantly those with WHO FC II and III. Eighty-four ISWTs from 46 patients were assessed according to WHO functional class (FC), echocardiogram, 6 distances walked, pulse oximetry, fatigue, BORG dyspnea scores, blood pressure, heart rate and adverse events.

Results: A total of 21 adverse events were reported from the 84 ISWT performed as follows: Two patients - angina, 1 - worsening dyspnea, 12 - locomotor difficulties including leg and joint pain, and 6 - lightheadedness. There were no deaths or sustained adverse events after the ISWT. There were no documented episodes of syncope or tachyarrhythmia’s even in patients with right ventricular dysfunction.

Conclusions: Performance of ISWT appears to be safe in stable outpatients with PH and right-sided heart disease as an assessment of the functional capacity in the PH population and should be included in future clinical trials to assess whether it may provide a meaningful assessment of patient exercise tolerance. Its limitations are similar to those shared by the 6 minute walk and include locomotor difficulties.

Chronic respiratory diseases like Asthma and Chronic Obstructive Pulmonary Diseases (COPD) have attracted research interest in the area of risk stratification and many machine learning techniques have been the subject of interest in prediction systems involving risk stratification that perform  early identification of the risk factors for the disease. Identification of patient populations at high risk is an important intervention in the early detection and clinical assessment of chronic diseases like asthma, as it can lead to targeted and personalized therapies. Here, we propose and deploy different machine learning approaches for the risk stratification under different study settings. All the approaches primarily predict the disease outcome or identify the severity/control level by recognizing the key risk factors for the disease depending on the nature of the data made available.