Diagnostic value of random forest algorithm based on condylar CBCT features for the staging of patients with idiopathic condylar resorption

doi:10.19439/j.sjos.2026.02.006

Abstract

Abstract: PURPOSE: To evaluate the diagnostic value of a random forest (RF) algorithm based on CBCT features of the condyle for staging idiopathic condylar resorption(ICR). METHODS: A total of 120 patients with ICR admitted to Nanjing Stomatological Hospital from January 2016 to December 2024 were selected and divided into the stationary phase group (n=70) and the progressive phase group (n=50). Healthy individuals who underwent physical examinations during the same period (n=40) were selected as the control group. The CBCT features of condylar length, inner 1/3 width, middle 1/3 width, outer 1/3 width, condylar height, mandibular ramus height, condylar surface angle, condylar axis angle, condylar volume, condylar surface area and condylar cross-sectional area were measured. Results: There were no significant differences in gender, age, height and disease duration among each group(P>0.05), while there were significant differences in CBCT characteristic indicators (P<0.05). Compared with the stationary group, the condylar length, condylar height, mandibular elevation height, condylar volume, condylar surface area and condylar cross-sectional area in the progressive group were significantly reduced(P<0.05). Taking the stationary or progressive stage of ICR patients as the dependent variable, the variables with significant differences in univariate analysis were included in the random forest (RF) algorithm, the order of importance from high to low was condylar volume, condylar surface area, condylar length, mandibular elevation height, condylar cross-sectional area, and condylar height. The above-mentioned CBCT features were subjected to stepwise RF,when the number of features was 5, the error rate of the out-of-pocket data was the lowest. The order of importance from high to low was condylar volume, condylar surface area, condylar length, mandibular elevation height and condylar area. Using the top 5 variables from the RF importance ranking for analysis, condylar volume, condylar surface area, condylar length and condylar cross-sectional area were identified as influencing factors for ICR staging (P<0.05). The receiver operating characteristic (ROC) curve analysis demonstrated that condylar volume, condylar surface area, condylar length, condylar cross-sectional area and their combination could all be used to diagnose ICR staging(P<0.05), with area under the curve(AUC)>0.70, sensitivity>58.5%, and specificity≥64%. Compared with a single indicator, the AUC, sensitivity and specificity of the combined detection were significantly increased. CONCLUSIONS: RF based on the CBCT features of the condyle of ICR patients has a high diagnostic value for disease staging. Condylar volume, condylar surface area, condylar length and condylar cross-sectional area are the key imaging indicators for differentiating the stationary phase from the progressive phase, among which condylar volume is of the highest importance. The combined detection of multiple features can significantly improve diagnostic efficiency, manifested as higher AUC, sensitivity and specificity.

Key words: Idiopathic condylar resorption, CBCT, Random forest, Staging, Diagnostic value

CLC Number:

R782.6

Ma Yuxuan, Nie Rongrong, Zhang Li, Sun Weibin, Zhu Feng. Diagnostic value of random forest algorithm based on condylar CBCT features for the staging of patients with idiopathic condylar resorption[J]. Shanghai Journal of Stomatology, 2026, 35(2): 148-153.

References

[1] Nobrega MTC, Almeida FT, Friesen R, et al.Idiopathic condylar resorption in adolescents: a scoping review[J]. J Oral Rehabil, 2024, 51(8): 1610-1620.
[2] Ji YD, Resnick CM, Peacock ZS.Idiopathic condylar resorption: a systematic review of etiology and management[J]. Oral Surg Oral Med Oral Pathol Oral Radiol, 2020, 130(6): 632-639.
[3] Tanaka E.Etiology and diagnosis for idiopathic condylar resorption in growing adolescents[J]. J Clin Med, 2023,12(20): 6607-6611.
[4] Exposto CR, Stoustrup P, Kristensen KD, et al.Condylar changes in patients with idiopathic condylar resorption: retrospective 2-year follow-up CBCT-based case-control study[J]. Eur J Orthod, 2020, 42(6): 619-625.
[5] 刘华蔚, 李永锋, 母晓丹, 等. 颞下颌关节髁突囊样变的多模态影像学分析[J]. 中华口腔医学杂志, 2022, 57(2): 142-148.
[6] Phyo Thu A, Song S, Karmacharya N, et al.Three-dimensional analysis of the morphological changes of the craniofacial jaw and condyle in patients with idiopathic condylar resorption[J]. Br J Oral Maxillofac Surg, 2023, 61(9): 598-604.
[7] Donelli M, Lanteri V, Ugolini A,et al.Cone-beam computed tomography (CBCT) analysis of mandibular condyles' diameters in patient with juvenile idiopathic arthritis and temporomandibular joint affection: a cross-sectional investigation[J]. J Clin Med, 2024, 13(17): 5104-5115.
[8] Mao B, Tian Y, Li J, et al.A quantitative analysis of facial changes after orthodontic treatment with vertical control in patients with idiopathic condylar resorption[J]. Orthod Craniofac Res, 2023, 26(3): 402-414.
[9] Marya A, Inglam S, Chantarapanich N, et al.Development and validation of predictive models for skeletal malocclusion classification using airway and cephalometric landmarks[J]. BMC Oral Health, 2024, 24(1): 1064-1070.
[10] Saric R, Kevric J, Hadziabdic N, et al.Dental age assessment based on CBCT images using machine learning algorithms[J]. Forensic Sci Int, 2022, 334(4): 111245.
[11] 中华口腔医学会. 进行性髁突吸收的正畸诊疗规范: T/CHSA XX-2025[S]. 北京: 中华口腔医学会, 2025.
[12] Arnett GW, Milam SB, Gottesman L.Progressive mandibular retrusion-idiopathic condylar resorption. Part II[J]. Am J Orthod Dentofacial Orthop, 1996, 110(2): 117-127.
[13] Alali YS, Al Habeeb KM, Al Malhook KA, et al.Diagnosis and management of idiopathic condylar resorption: a review of literature[J]. Saudi Dent J, 2024, 36(11): 1397-1405.
[14] Valladares-Neto J, Acioli GMR, Teodoro AB, et al.Conservative and minimally invasive approaches to control idiopathic condylar resorption: a scoping review[J]. Int J Oral Maxillofac Surg, 2023, 52(11): 1188-1196.
[15] Munakata K, Miyashita H, Nakahara T, S et al. The use of SPECT/CT to assess resorptive activity in mandibular condyles[J]. Int J Oral Maxillofac Surg, 2022, 51(7): 942-948.
[16] Prado BN, Pereira LC, Prado JN.Aggressive idiopathic condylar reabsorption after orthognathic surgery: a complex imaging diagnosis[J]. Radiol Case Rep, 2025, 20(6): 2940-2945.
[17] Wang H, Xue C, Luo E, et al.Three-dimensional surgical guide approach to correcting skeletal ClassⅡmalocclusion with idiopathic condylar resorption[J]. Angle Orthod, 2021, 91(3): 399-415.
[18] Boos-Lima FBDJ, Guastaldi FPS, Nielsen GP, et al.Histopathology of idiopathic condylar resorption differs from temporomandibular joint-only juvenile idiopathic arthritis[J]. J Oral Maxillofac Surg, 2025, 83(1): 26-36.
[19] Zhou J, Fu Y, Yu L, et al.A novel three-dimensional morphological analysis of idiopathic condylar resorption following stabilisation splint treatment[J]. J Oral Rehabil, 2021, 48(5): 560-567.