Optimization of management plan with a machine learning model for ovarian torsion cases: operative vs. conservative
-
By
-
Alia Alethawy
-
Omaima Al-Baghdadi
-
Yauhen Statsenko
-
Moamar Al-Jefout
-
June 25, 2026
-
Clinical Scorecard: Enhancing Management Strategies for Ovarian Torsion Using a Machine Learning Approach: Surgical Versus Conservative Options
At a Glance
| Category | Detail |
|---|
| Condition | Ovarian Torsion |
| Key Mechanisms | Torsion of the ovary on its pedicle leading to compromised venous return, stromal swelling, internal bleeding, and ischemia. |
| Target Population | Women of reproductive age experiencing gynecologic emergencies. |
| Care Setting | Emergency and surgical settings. |
Key Highlights
- Machine learning models can support individualized risk stratification in ovarian torsion.
- The class-weighted Decision Tree model showed AUC = 0.76, sensitivity = 0.75, specificity = 0.73.
- Key predictors include Doppler findings, BMI, blood group, ethnicity, and clinical symptoms.
- PCA identified eight clinical domains and two distinct patient profiles.
- Timely management is crucial for preserving ovarian function and fertility.
Guideline-Based Recommendations
Diagnosis
- Diagnosis typically involves clinical signs such as abdominal pain, nausea, and vomiting, along with imaging findings.
Management
- Surgical intervention is the gold standard, usually via diagnostic laparoscopy, with options for oophorectomy or detorsion.
Monitoring & Follow-up
- Monitor for complications associated with surgical intervention, which occur in approximately 2 per 1,000 cases.
Risks
- Risks include organ trauma and major vessel injury, which can lead to significant morbidity and mortality.
Patient & Prescribing Data
219 patients diagnosed with ovarian torsion.
Machine learning can enhance decision-making regarding operative versus conservative management.
Clinical Best Practices
- Utilize machine learning models to inform management decisions in ovarian torsion.
- Consider individual patient characteristics and clinical history when determining management strategy.
Related Resources & Content
