Peripheral arterial disease (PAD) is characterised as an atherosclerotic disease, most common in the lower limbs (aortoiliac, femoropopliteal, and infrapopliteal arterial segments), which causes a decrease in blood flow to the areas adjacent to and posterior to the affected area. Intermittent claudication (IC) is the most common symptom in this disease that appears with exertion and relieves with rest, causing fatigue, cramps, discomfort, or pain in the lower limbs due to limited blood flow to the affected muscles. Supervised physical exercise has emerged as the first line of intervention in improving the symptoms of intermittent claudication and disease progression, and in the last decade there has been an exponential increase in the use of wearable technologies to monitor dose-response. However, the approach used is still simplistic because it is not personalised. In other words, patients with similar diagnoses and symptoms get the same treatment, without personalising the stimulus according to their exercise responses and level of adaptation. With this in mind, this study aims to monitoring the real-time response of a multicomponent exercise programme (cardiovascular and resistance training) to personalise the dose-response, and use artificial intelligence models to gather and analyse vast amounts of data towards grouping/differentiating based on individual responses. The main hypothesis is that a supervised multicomponent exercise programme will improve the functional capacity of patients with PAD in a cluster personalised approach.