Evaluating the age of rib fractures through ^99mTc-MDP SPECT strategy based on a machine learning algorithm: a...

Area of Science:

• Forensic Science
• Radiology
• Orthopedics

Background:

• Rib fractures are common in traffic accidents, necessitating accurate age estimation for forensic reconstruction and legal proceedings.
• Current diagnostic methods may not meet forensic requirements for determining fracture age.
• Technetium-99m-methyldiphosphonate (^99mTc-MDP) scintigraphy offers a potential method for age estimation due to its dynamic uptake at fracture sites during healing.

Purpose of the Study:

• To evaluate the efficacy of ^99mTc-MDP uptake measured by single-photon emission computed tomography (SPECT) in estimating the age of rib fractures.
• To correlate ^99mTc-MDP uptake with fracture age in a cohort of individuals.

Main Methods:

• 151 rib fractures from 55 individuals were analyzed.
• ^99mTc-MDP uptake was quantified using the target-to-non-target (T/NT) ratio via SPECT.
• Fracture age ranged from 3 to 491 days and was categorized into three groups: within 30 days, 30-60 days, and over 60 days.
• Six machine-learning models were developed to predict fracture age groups.

Main Results:

• Significant differences in T/NT values were observed among the three fracture age groups (P < 0.0001).
• A moderate correlation (R² = 0.36, P < 0.0001) was found between fracture age and T/NT ratio.
• The support vector machine model demonstrated strong performance in classifying fracture age groups, achieving an AUC of 0.91, F1-score of 0.78, accuracy of 0.80, and recall of 0.79.

Conclusions:

• ^99mTc-MDP SPECT imaging provides a novel functional imaging approach for estimating rib fracture age.
• This method can offer valuable objective data for forensic case reconstruction and serve as a complementary tool in bone trauma analysis.