Oncological Comorbidities (e. g. Hypertension, Diabetes, Malnutrition)
Conditions
Keywords
Malignant neoplasm, Comorbidity, Artificial intelligence
Brief summary
Combined with the digital whole process management data pool, a multi-modal data fusion framework is developed, and an AI model is established to realize risk stratification and personalized treatment Recommendation and dynamic prognosis prediction; validation of whole-process management based on multimodal digital fusion AI-aided decision support system through prospective non-randomized controlled interventional study The effect on survival, complication control and utilization of medical resources in patients with comorbid malignant tumors.
Detailed description
The title of this study isThe Impact of Multimodal Digital Fusion AI-Assisted Decision Support System-Based Comprehensive Management on Clinical Outcomes in County-Level Patients with Comorbid Cancer: A prospective non-randomized controlled interventional study, to evaluate the impact of full-course management based on a multimodal digital fusion AI-assisted decision support system on the clinical outcomes of county-level oncologic comorbid patients through a prospective non-randomized controlled interventional study. The study plans to enroll 5,000 patients with pathologically confirmed malignancies and at least one comorbid condition (diabetes, hypertension, etc.) , in the first stage, the epidemiological characteristics of co-morbidity and its impact on prognosis, treatment response and quality of life were analyzed In the second phase, patients with comorbid pulmonary malignancies were selected to compare the clinical effects of the voluntary whole-process management group (including personalized intervention such as nutritional screening and dynamic monitoring) and the conventional treatment group, the third stage integrates multi-center Electronic Medical Records, genomic data, wearable device monitoring and other multi-modal data to construct an AI decision-making system, developing risk stratification, personalized treatment recommendation, and dynamic prognostic prediction models, finally, the differences in core indicators such as survival rate (PFS, OS) , complication control and medical resource efficiency between AI-assisted management and traditional mode were compared. This study realizes the integrated intervention of in-hospital and out-of-hospital through digital whole-process management, which is expected to provide an AI-driven precise decision support paradigm for primary medical institutions and improve the efficiency of comprehensive management of tumor comorbidity.
Interventions
OTHERAI-assisted comprehensive management system
Precision Risk Stratification and personalized treatment recommendation through AI models may improve the suitability of treatment regimens and thus reduce the incidence of antineoplastic therapy-related adverse effects (e.g. , reduction of chemotherapy toxicity through nutritional intervention) , and improve the efficacy of chemotherapy, and prolonged progression-free survival (PFS) and overall survival (OS)
Sponsors
The First Affiliated Hospital of Xinxiang Medical College
Study design
Allocation
NON_RANDOMIZED
Intervention model
PARALLEL
Primary purpose
TREATMENT
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Patients with a definite diagnosis of malignancy by histopathology and/or cytology; * Age ≥18 years; * There is no gender limit * Plan to receive antineoplastic therapy within 2 weeks or are receiving standard antineoplastic care (surgery, radiation, chemotherapy, or targeted therapy) ; * Conscious and able to answer questions and use electronic devices autonomously; * Patients were able to understand the study and voluntarily sign an informed consent form;
Exclusion criteria
* Having severe mental or cognitive impairments that prevent them from understanding the content of the study or implementing the programme; * With severe heart disease, acute respiratory failure, liver kidney failure and other critical illness; * Women during pregnancy or lactation； * Have participated in other interventional studies in the past 1 month or are currently participating; * Patients with ECOG ≥ 3 that do not respond to treatment; * Patients with an expected survival of \< 3 months that do not respond to treatment; * Cases deemed unsuitable for enrollment by the investigator.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Progression-free survival (PFS) | 24 months | Progression-free survival (PFS) : the time from randomization (or study enrollment) to the observation of disease progression or the occurrence of death from any cause. This period was assessed every 6-8 weeks using RECIST 1.1 criteria. |
| Overall survival (OS） | 24 months | Overall survival (OS） : the time from study enrollment to death from any cause from any cause, every 3 months during treatment, and every 3 months after the end of treatment. The patients were followed up at 6 months and the cause of death was recorded. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Comorbidity control rate. | 24 months | Comorbidity control rate: the proportion of comorbidities achieving guideline-recommended control targets during the study period; stratified criteria should be established based on specific comorbidity types. |
| Quality of life(QLQ-C30). | 24 months | Quality of life: changes in scores at baseline, on-treatment, and follow-up were assessed using the European Organisation for Research and Treatment of Cancer QLQ-C30 scale, between-group differences |
| Medical resource consumption index. | 24 months | Medical resource consumption index: Comparing DRG-adjusted medical resource consumption indices between two groups. |
| Adherence to AI system interventions. | 24 months | Adherence to AI Interventions: 1. In-Hospital Rate - Percentage of inpatients completing AI-recommended actions (e.g., nutritional screening, real-time monitoring). 2. Out-of-Hospital Completion Rate: Percentage of discharged/outpatients adhering to AI-guided care (e.g., telehealth, wearable data tracking). Enables precise evaluation of AI-driven care across clinical settings. |
Countries
China
Contacts
Primary ContactWei Shen Wei Shen, MD, Doctor of Medicine
Backup ContactPing Lu Ping Lu, MD, Doctor of Medicine
Outcome results
None listed