6.1. Introduction

Cancer survival rates have increased significantly in comparison to past decades due to improvements in early detection, precision diagnostics, targeted therapies, immunotherapy and better surgical procedures. Even with all of the new advancements contributing to a larger population of cancer survivors, there is still a growing challenge in the clinical setting: survivorship care, which has become a prominent issue (Fitzgerald et al. 2022). Survivors grappling with the aftermath of their surgical treatment are known to experience a wide range of complications that may persist for months or years. Such complications are physical in nature and include chronic fatigue, pain, musculoskeletal dysfunction, lymphedema, cardiopulmonary restrictions and reduced mobility. Equally, cognitive deficits such as “chemo brain” paired with anxiety and depression are significant impediments to recovery and life (Packel 2024).

Survivors who are trying to manage their symptoms post-treatment frequently rely on physiotherapy as the primary form of rehabilitation. Physiotherapists facilitate survivors in restoring strength and range of motions, ensuring that full functionality is reacquired alongside the mitigation of secondary complications. The best approach is outlined by conventional physiotherapy but is hampered on numerous fronts. Survivors face numerous logistical and systemic hurdles that limit their access to rehabilitation, from exorbitant costs to transportation issues and lengthy wait times. In addition, rehabilitation programs are often generalized, failing to tailor each program to each individual’s particular needs (Richardson et al. 2021). Consequently, engagement rates tend to be low and outcomes do not portray the optimal recovery that can and should be achieved.

Moving forward, the application of artificial intelligence (AI) in physiotherapy is perhaps the most distinct shift that we have seen in practice. AI is the capability of a computer system to imitate intelligent human behavior, meaning they can learn from available data, identify trends and make decisions (Korteling et al. 2021). AI has the potential to solve many traditional rehabilitation issues through machine learning (ML), computer vision and natural language processing (NLP). These technologies can process significant amounts of clinical data, behavioral data and data from sensors in order to create therapy programs that are personalized, flexible and ever changing.

AI-powered rehabilitation systems enable patients to be monitored remotely using wearable sensors, motion capture and smartphones (Bint Khalid et al. 2024). Such systems are capable of monitoring physical performance metrics in real time, detecting any changes from preset routines and providing immediate remedial feedback. This strengthens the hands of patients and clinicians. Furthermore, AI systems are capable of predicting rehabilitation trajectories, enabling timely intervention and adjustments to formulated recovery plans. Healthcare providers can optimize recovery plans as needs arise (Alshami et al. 2025).

Decentralized care can be supported through tele-rehabilitation. AI enables cancer survivors to remotely participate in guided physiotherapy sessions from their homes, minimizing the need for clinic visits and alleviating strain on healthcare services. Incorporating gamification, virtual coaching and adaptive interventions fosters not only increased therapeutic efficacy but also sustained motivation and active participation over time (Damaševičius et al. 2023). This chapter delves into the impact AI has on cancer rehabilitation, focusing primarily on physiotherapy.

The chapter focuses on AI’s impact on rehabilitation for the increasing number of cancer survivors by studying contemporary technologies, their clinical uses and new research that AI seeks to address (Afridi and Khan 2024). The following parts explore the specific issues of survivorship, the role of AI in medicine and the technologies that facilitate convenient and effective rehabilitation tailored to individual needs.

6.2. The burden of cancer survivorship

The number of people diagnosed with cancer and living beyond diagnosis is on the rise, which is why cancer survivorship is becoming a focal point in oncology. While cancer treatment is increasingly becoming more successful, patients often face numerous, multi-faceted and interwoven physical and social difficulties in the post-treatment stage, which can span years after undergoing treatment. Survivorship issues combine with the gaps in care which include chronic disease, supportive needs, caregiving needs, etc. These gaps greatly depend upon the type of cancer, treatment methods, patient age, as well as other coexisting conditions (Miller et al. 2019).

Some of the surgical options available, including chemotherapy, radiation therapy, immunotherapy and surgery, come with their fair share of disadvantages. Some complications with chemotherapy include peripheral neuropathy, a condition that makes basic movements and mobility very difficult due to the numbness, tingling or pain felt in limbs. Other issues include radiation damage to healthy tissues surrounding the tumor site which leads to fibrosis, reduction in joint movement and long-term fatigue (Schirrmacher 2019). Surgical treatment poses risks of lymphedema and muscle bone dysfunctions after the removal of lymph nodes.

Apart from experiencing physical disabilities, surviving cancer often leaves patients with cognitive difficulties, commonly known as “chemo brain”. This cognitive impairment can include amnesia, impaired attention and slower cognitive operations. These mental challenges hinder functioning and reintegration into occupational or social settings. Psychological impacts such as anxiety, depression, PTSD and the worry of recurrence amplify the surviving burden further (Więckiewicz et al. 2024). These factors in unison tremendously diminish life’s satisfaction, functional autonomy and increase the burden on caregivers along with other healthcare resources.

As an integral component of the multidisciplinary approach to cancer rehabilitation, physiotherapy plays a critical role. Physiotherapists help restore someone’s functional ability, reduce pain and enhance mobility by treating muscles and bones, as well as nerve and heart problems. Therapeutic exercises alleviate the effects of cancer-related fatigue, enhance balance and coordination, and aid in fall prevention (Hussey and Gupta 2022). Moreover, physiotherapy has been proven to enhance the control someone has of their cardiovascular system, strength and functional autonomy, which improves long-term surviving outcomes.

Regardless of the positive outcomes, the accessibility of physiotherapy is still not the same for everyone. Many survivors, particularly those residing in rural or neglected areas, encounter severe difficulties such as geographic remoteness, a lack of available practitioners, expensive treatment options and prolonged waiting periods. Even when services are present, the lack of personalization as well as insufficient incorporation of patient-reported outcomes can significantly reduce the effectiveness of customary physiotherapy protocols (Adeghe et al. 2024). Compliance with rehabilitation plans is another important challenge that is often affected by treatment exhaustion, difficulty reaching the treatment location, treatment cost and emotional trauma.

In addition, gaps in the availability of healthcare services significantly add to these problems. Ethnic minorities and people in the lower socioeconomic classes, as well as older people, may not be able to access advanced rehabilitative care, which affects inequity in survivorship outcomes. Trust issues towards healthcare systems pose cultural, linguistic and even infrastructural obstacles which can restrict engagement with mainstream physiotherapy clinics.

With such complex hardships, there is a growing demand for new approaches that address these shortfalls, improve customization and enable enduring recovery. In this context, AI offers a promising solution as contemporary physiotherapy has the possibility to become more responsive to patient needs, be data-driven and automated. As more AI tools are developed, using AI to complement rehabilitation efforts for cancer survivors – whose survivorship issues become critical in public health concerns – may be a means to improve the equity, effectiveness and accessibility of rehabilitation services (Petry Moecke).

6.3. AI in healthcare and rehabilitation

AI is a multidisciplinary field which integrates a variety of different technologies such as ML, deep learning (DL), NLP, computer vision and robotics. These technologies mean machines can process data, identify intricate relationships and make decisions; all of which have been extremely useful in medical care (Javaid et al. 2022). Recently, AI has advanced considerably in numerous branches of medicine, including diagnostics, radiology, pathology, pharmacology and personalized therapy.

An area of AI development that requires immediate attention is medical imaging, which seems to be performing well. DL algorithms that can determine the same diagnoses that expert medical doctors can for advanced stage cancer, cardiovascular disease or even neurological disorders have been created. Similar to other industries, AI also improves clinical decision support systems (CDSS) of different settings. Having the capability to make treatment recommendations by synthesizing the patient’s history, laboratory results and even medical textbooks makes AI efficient. In addition to real-time patient monitoring, a powered wearable and smart equipment can analyze, assess and improve clinical intervention way before warning signs are noted (Khan et al. 2024).

Moreover, AI appears to be making inroads, for good or bad, in rehabilitation services. AI-enabled rehabilitation technologies apply optimization techniques to provide personalized and individualized interventions alongside progress monitoring, with a focus on providing data-driven rehabilitation. These systems have the ability to process biomechanical and kinematic information obtained from sensors, videos and motion capturing. Posture, gait and movement evaluation can be carried out. This makes it possible to provide timely and accurate feedback needed for adjustments in therapy design (Alshami et al. 2025).

AI systems can automatically alter rehabilitation treatment plans, such as exercises for individuals, according to the patient’s performance measures. This ensures that therapy is optimized and remains challenging enough in relation to therapeutic aims. Predictive algorithms can chart the recovery journey by recognizing certain patterns that a patient’s response to therapies evokes. This informs the clinicians on the appropriate intensity and duration of the efforts to be made by the patient. Such tailoring of rehabilitation means overexertion and injury can be voided while, at the same time, the gains obtained from rehabilitation can be optimized.

The application of AI in combination with wearable sensors, smartphone technologies and robotics has broadened the boundaries and reach of rehabilitation services. Devices such as inertial measurement units (IMUs), electromyography (EMG) sensors and even smart clothing make it possible to monitor patients’ limbs and muscles and collect data on the movement and angles of joints continuously (Malesevic et al. 2023). These data, when integrated with AI, enable supervision, outcome evaluation and even progress visualization to be achieved in real time. Smartphone rehabilitation apps powered by AI can help customize therapy sessions, track performing deviations from set exercise prescriptions and signal the need for healthcare interventions concerning some issues.

Related posts:

The Role of Artificial Intelligence in Personalized Physiotherapy and Cancer Treatment Model Validation Techniques for AI in Cancer Research Based on Physiotherapy and Oncology Machine Learning in Oncology and Physiotherapy: A New Era of Precision Medicine AI and Wearable Technology in Physiotherapy for Oncology Patients Smart Robotics in Physiotherapy and Oncology: Redefining Patient Outcomes Recurrent Neural Networks for Predictive Modeling in Cancer Time Series Data

Stay updated, free articles. Join our Telegram channel

Join