Artificial Intelligence to Search for Abnormalities in Ambulatory Cancer Patients (IASAAC)

During treatment, cancer patients may experience side effects related to their disease but also to the different treatments they receive. Currently, adverse effects and toxicities are well codified in the oncology community, notably via the NCI CTCAE criteria. Unlike objective data such as a blood sample or a CTscan, a major bias in patient assessment is the subjective assessment of the physician or its team at a given time, which may not reflect the overall situation (for better or worse). Several studies had already highlighted the discrepancies between medical and patient data collection. Self-assessment of symptoms is one way to overcome this bias. Moreover, there are now a large number of solutions that allow to perform these self-assessments at home. Thanks to these tools, there are now two situations, the scheduled evaluation (before a chemotherapy treatment, or after a surgical procedure for instance) and the unscheduled situations, where it is the patient himself who can trigger an evaluation form. These new evaluation methods also allow to take a quality of life approach. Patient-reported outcomes (PROs) is now a valid evidence-based assay to detect patient's symptoms and therefore provide helpful clinical information to healthcare providers. The goal of this study is to go one step further than the previous PROs studies and evaluate the ability to train a machine learning algorithm to detect at-risk situations and lay the foundation for a viable solution for future prospective and randomized trials.

Electronic survey, Artificial intelligence, Quality of life, Patient-Reported Outcomes (PROs), Symptom management, eHealth, Machine learning

At baseline, clinical research staff will: verify the possibility of an internet connection at the patient's home help the patient to fill in the 1st questionnaire (baseline questionnaire - frailty) Every two weeks for 3 months: patients complete questionnaires via app (toxicity; quality of life, medication adherence) responses are verified by clinical research staff In case of severe symptoms, the clinician contacts the patient and arranges for management. At the end of the study : - patients answer a satisfaction questionnaire

The number of unscheduled medical consultations or re-hospitalisations will be assessed based on abnormalities identified through the patient's self-report of symptoms.

Patient satisfaction will be assessed according to the Patient Assessment Chronic Illness Care Questionnaire (1= almost never : 5 = almost always)

The total dose of treatments given will be calculated from the total dose of chemotherapy received per course and the collection of dose adjustments.

Handling of the digital tool will be assessed by the System Usability Scale ( 0 =Strongly disagree; 10=Strongly agree)

Anticipation of injectable chemotherapy preparations will be evaluated based on the number of treatments ordered and actually administered, without the need to call the patient.

The occurrence of sarcopenia will be measured by the body mass/fat mass ratio using the CT scan performed for tumor evaluation

Inclusion Criteria: Follow-up for a solid tumor Chemotherapy treatment (oral and/or injectable) scheduled or in progress Life expectancy > 3 months Performance Status (PS) < 3 Have an internet connection or assistance to answer questions throughout the study (nurse, family members, etc.) Patient having understood, signed and dated the consent form Patient affiliated to the social security system Exclusion Criteria: Lack of means to answer the online questionnaires Patient in another therapeutic trial with an experimental molecule Patients and their families who cannot read or speak French Persons deprived of liberty or under guardianship (including curatorship)