This prospective observational cohort study aims to develop and evaluate an early warning and risk prediction model for medication-related osteonecrosis of the jaw (MRONJ) based on multimodal data fusion.

Eligible participants will include adults who have received bone-modifying agents, including bisphosphonates or denosumab, for at least 24 months for osteoporosis or bone metastases and who are scheduled to undergo clinically indicated invasive oral procedures. The study will not assign any treatment or intervention. All oral procedures will be performed as part of routine clinical care.

Clinical characteristics, medication exposure, oral examination findings, cone-beam computed tomography imaging data, and biological samples including saliva, blood, urine, and gingival crevicular fluid will be collected. Proteomic and metabolomic analyses will be performed to identify candidate biomarkers associated with MRONJ risk.

Participants will be followed prospectively after the oral procedure to assess wound healing, clinical symptoms, imaging changes, and the occurrence of MRONJ. The study will evaluate whether a multimodal model combining clinical, imaging, and biological data can predict the risk of MRONJ after invasive oral procedures.

Inclusion Criteria:

1. Adults aged 18 to 70 years, regardless of sex.
2. Currently receiving bone-modifying agents, including bisphosphonates or denosumab, for osteoporosis or bone metastases.
3. Continuous use of bone-modifying agents for at least 24 months before enrollment.
4. Scheduled to undergo clinically indicated invasive oral procedures, including root canal therapy, periapical surgery, tooth extraction, periodontal scaling and root planing, periodontal surgery, or other invasive oral procedures as clinically needed.
5. No clinical signs of medication-related osteonecrosis of the jaw before the planned oral procedure, according to the diagnostic criteria of the American Association of Oral and Maxillofacial Surgeons.
6. Able to understand the study purpose and procedures and willing to provide written informed consent.

Exclusion Criteria:

1. Previously diagnosed or suspected medication-related osteonecrosis of the jaw.
2. Other diseases or conditions that may cause osteonecrosis of the jaw, such as osteoradionecrosis or malignant tumors of the jaw.
3. Severe coagulation disorders or active bleeding disorders that preclude invasive oral procedures.
4. Severe cardiac, hepatic, or renal dysfunction, including New York Heart Association class III-IV heart failure, Child-Pugh class C liver disease, or renal failure requiring dialysis.
5. Autoimmune disease or current immunosuppressive therapy that may affect bone metabolism or immune status assessment.
6. Salivary gland dysfunction, such as Sjögren's syndrome, that may affect the quality of saliva sample collection.
7. Pregnancy or breastfeeding.
8. Psychiatric disorders or cognitive impairment that would prevent understanding of the study procedures or compliance with follow-up.
9. Uncontrolled hypertension or diabetes mellitus, or a history of stroke or transient ischemic attack within the past 6 months.
10. Use of any vaccine for the prevention of infectious diseases, such as influenza or varicella vaccine, within 4 weeks before enrollment.
11. Congenital or acquired immunodeficiency, such as HIV infection, or active hepatitis B or hepatitis C infection. Active hepatitis B is defined as HBV DNA above the upper limit of normal, and active hepatitis C is defined as HCV viral titer or RNA above the upper limit of normal.
12. Participation in another clinical study that may interfere with the results of this study.

Patients at risk of medication-related osteonecrosis of the jaw will be prospectively recruited from the School & Hospital of Stomatology, Wuhan University. Eligible participants will include adults with a history of antiresorptive or antiangiogenic medication exposure who require oral and maxillofacial evaluation, dental treatment, or follow-up. Clinical, imaging, laboratory, and follow-up data will be collected to develop and evaluate an early warning and risk prediction model for medication-related osteonecrosis of the jaw.