DIGITAL ORTHODONTICS

Machine-learning–based detection of
degenerative temporomandibular joint
diseases using lateral cephalograms
Xinyi Fang,a,b Xin Xiong,a Jiu Lin,a Yange Wu,a Jie Xiang,a and Jun Wanga
Chengdu, Sichuan, and Hangzhou, Zhejiang, China

Introduction: Degenerative temporomandibular joint diseases (DJDs) are common diseases in dental practice,
characterized by a series of degenerative processes in the temporomandibular joint. Early clinical detection of
DJD by dental practitioners can be beneficial to prevent or alleviate the further progression of the disease. This
study aimed to develop a cephalogram-based multidimensional nomogram to screen DJD. Methods: A total of
502 patients (170 normal and 332 with DJD) were randomly assigned to a training set (n 5 351) or a validation set
(n 5 151). Thirty-six cephalometric parameters were extracted from the cephalograms to be used as input for a
predictive machine-learning algorithm. Multivariable logistic regression was used to construct a combined model
for visualization in the form of a nomogram. Receiver operating characteristic curve, calibration testing, and
decision curve analyses were conducted to evaluate the performance of the combined model. Results: A
Ceph score consisting of 22 cephalometric parameters were significantly associated with DJD (P\0.01). A com-
bined model that consisted of Ceph scores and clinical features (including age, gender, limited mouth opening,
crepitus, etc.) performed well in the receiver operating characteristic curve (area under the curve, 0.893), cali-
bration test, and decision curve analyses, indicating its potential clinical value. Conclusions: This study con-
structed and verified a multidimensional nomogram consisting of Ceph scores and clinical features, which
may contribute to the clinical screening of DJD in dental practice. Future studies are needed to test the reliability
of the model with similar parameters. (Am J Orthod Dentofacial Orthop 2023;163:260-71)

D
egenerative temporomandibular joint diseases
(DJDs) are common pathologic conditions
affecting the temporomandibular joint (TMJ)
with a prevalence of 11%-20% among temporomandib-
ular disorder (TMD) patients.1-3 DJD is characterized by a
series of degenerative processes in the TMJ, including
a
State Key Laboratory of Oral Diseases, National Clinical Research Center for Oral
Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, Si-
chuan, China.
b show no symptoms.6 They may experience various
Department of Orthodontics, Hospital of Stomatology, Key Laboratory of Oral
Biomedical Research of Zhejiang Province, School of Stomatology, Zhejiang Uni-
versity School of Medicine, Hangzhou, Zhejiang, China.
Xinyi Fang and Xin Xiong are joint first authors and contributed equally to this
work.
All authors have completed and submitted the ICMJE Form for Disclosure of Po-
tential Conflicts of Interest, and none were reported.
This research was funded by the National Natural Science Foundation of China
(nos. 81771114 and 81970967), the Sichuan Science and Technology Program
(no. 2020YFS0173), and the Major Special Science and Technology Project of Si-
chuan Province (no. 2022ZDZX0031).
Address correspondence to: Jun Wang, State Key Laboratory of Oral Diseases,
National Clinical Research Center for Oral Diseases, West China Hospital of Sto-
matology, Sichuan University, No. 14, 3rd section, People’s South Rd, Chengdu,
Sichuan 610041, China; e-mail, wangjunv@scu.edu.cn.
Submitted, February 2022; revised and accepted, October 2022.
0889-5406/$36.00
Ó 2022 by the American Association of Orthodontists. All rights reserved.
https://doi.org/10.1016/j.ajodo.2022.10.015
joint cartilage loss, osteoproliferative body formation,
and subchondral bone remodeling and hardening. DJD
is often accompanied by pain, dysfunction, joint
noises, and compromised oral health–related quality of
life.4,5 DJD with joint pain is classified as temporoman-
dibular joint osteoarthritis (TMJOA), whereas DJD
without joint pain is classified as osteoarthrosis.2 Ac-
cording to a previous study, 35% of the population
with minimal condyle and/or eminence flattening
morphologic and functional deformities when the
breakdown of the TMJ begins.7 Thus, screening for
DJD in the dental clinic during early, more treatable
stages is challenging and important.
The diagnosis of DJD is typically made on the basis of
a radiographic examination of the condyle and articular
eminence.4 TMJ with erosive resorption, attrition, scle-
rosis, cyst-like changes, and osteophyte formation is
classified as DJD.4 Orthopantomography (OPG), trans-
cranial oblique lateral radiography, cone-beam
computed tomography (CBCT), and magnetic resonance
imaging are often used for the detection of DJD.8-10
Among them, CBCT is recognized for its advantages in

260
Fang et al
an accurate, detailed presentation of the TMJ and can be
used to demonstrate the degree and location of TMJ
damage.11 However, CBCT is not commonly performed
in clinical screening for DJD because of its high radiation
dosage and cost. Generally, OPG is the most typical
method for screening of the maxillofacial region.12
However, this method of DJD diagnosis is low in accu-
racy and sensitivity because of image distortion and
overlap.12
Lateral cephalograms are another plain radiograph
commonly obtained in the dental clinic. They were orig-
inally used in diagnosis and evaluation in orthodontic
practice and are widely used for evaluating craniomaxil-
lofacial morphology.13-15 Lateral cephalograms are not
used for imaging the TMJ because they are a 2-
dimensional modality. Several investigations have re-
ported that patients with DJD show special cephalo-
metric features compared with normal patients.13,16
Patients with severe DJD have a short ramus height
and backward-rotated mandible observable on cephalo-
grams.17 Therefore, the use of lateral cephalograms can
assist in DJD diagnosis. In addition, the standard land-
marks used in cephalometric tracing make up for the
problem of morphologic deviations in OPG application.
Analyzing and summarizing cephalometric parameters
strongly related to DJD would be helpful for clinical
diagnosis.
Considering the high prevalence of degenerative alter-
ation in TMD patients and the lack of simple and sensitive
clinical diagnostic features,18 an accurate tool for primary
diagnosis of DJD would be helpful for clinical practice. As
an emerging field attracting numerous researchers’ inter-
est, radiomic feature-based artificial intelligence (AI)
models are widely used in diagnostics, decision-making,
and outcome prediction in clinics.19-22 Several
investigators have constructed AI-based models for the
detection of TMJOA using CBCT and OPG.19-21,23-25
However, the limited access to CBCT and variability of
panoramic features among different devices restricts the
application of these models. Moreover, their trained
deep-learning models cannot explain and analyze the re-
sults.26 Following the “as low as reasonably achievable”
principle with respect to radiation exposure, it is unethical
to regularly perform CBCT on every patient for the
screening of DJD. As most patients seeking orthodontic
treatment are already subject to cephalograms, a cephalo-
metric parameter-based DJD detection procedure may
assist in the primary diagnosis of DJD without requiring
additional radiation exposure. Therefore, we sought to
build and verify a cephalometric parameter-based predic-
tive machine-learning algorithm to assist in the clinical
screening of DJD.
American Journal of Orthodontics and Dentofacial Orthopedics
261
MATERIAL AND METHODS
This retrospective study was approved by the Ethics
Committee of West China Hospital of Stomatology Si-
chuan University (WCHSIRB-2020-418). All patients
and their legal guardians were informed of the possibility
that their records might be used for research purposes,
and oral informed consent was obtained. Patients from
whom both CBCT of the TMJs and a lateral cephalogram
were obtained during the period from 2018 to 2021 were
randomly evaluated. Only the first scan accompanied by
CBCT was included for training the AI model for patients
with $1 lateral cephalogram. All the patients’ personal
information was deidentified.
The inclusion criteria included (1) patients aged $18
years, (2) patients with TMJ-related clinical information,
and (3) CBCT conducted within 1 week before/after
lateral cephalogram. The exclusion criteria included (1)
patients with cephalogram or CBCT from which features
could not be successfully extracted; (2) patients with tu-
mor or maxillofacial deformity that could cause joint
deformity; (3) patients with a history of orthodontic
treatment, plastic surgery, or other craniofacial surgery;
and (4) patients with a history of TMJ treatment. Ulti-
mately, 502 patients were included in this study. Among
them, 351 patients (59 male and 292 female), with an
average age of 32.29 6 10.90 years (age range, 18-69
years), were randomly assigned to training set. The other
151 patients (29 male and 122 female), with an average
age of 30.14 6 9.51 years (age range, 18-64 years),
constituted the validation set. The TMD clinical exami-
nation, including evaluation of limited mouth opening,
deviation, clicking, and crepitus, was performed by the 2
TMJ specialists (with 8 and 10 years of experience,
respectively) as well according to DC/TMD criteria. Any
disagreement was resolved through consultation with a
third specialist with 20 years of experience diagnosing
and treating TMJ disorders. In addition, self-reported
symptoms were extracted from the medical records. A
flow diagram of this study is presented in Figure 1.
CBCT images were obtained from all patients using
the 3D Accuitomo scanner (J Morita Corp, Kyoto, Japan).
Scan settings were as follows: 90 kVp, 5 mA, exposure
time of 17.5 seconds, voxel size of 0.25 mm, slice thick-
ness of 0.25 mm, a field of view of 140 mm 3 100 mm,
and 360 rotation. The criteria for CBCT diagnosis of
DJD were developed with reference to previous litera-
ture: (1) normal-sized condyle with osteosclerosis and/
or joint flattening; (2) deformed condyle with a subcu-
taneous cyst, cortical resorption, or extensive osteoscle-
rosis.27 Patients with unilateral or bilateral TMJ
osteoarthritis were designated as DJD (Supplementary
Fig 1). Two TMJ specialists (with 4 and 5 years of
February 2023  Vol 163  Issue 2
262 Fang et al

TMJ Feature Feature Model Model

Evaluation Exreaction Selection Analysis Evaluation

Normal Cephalometric LASSO Nomogram

Ceph score
(n=170) tracing regression
Points

Gender

34 35 33 30 28 27 23 20 20 16 12 6 5 4 0
P<0.001 Age

75

1.35
Limited
mouth opening

Deviation

1.30
Binomial Deviance
Clicking

1.25
Crepitus

1.20
Pain

70
Ceph score

1.15

Ceph score
Total Points

1.10
Risk of DJD

1.05
−8 −6 −4 −2
Calibration curve
log (λ)
65

1.0
30 23 13 2

DJD 1.0

0.8
(n=332) Cephalometric
Coefficients

Actual DJD rate

0.5

0.6
60
parameters Normol DJD

0.4
0.0

Features Number

0.2
−0.5

Apparent
Bias−corrected

All 36 Ideal

0.0
−8 −6 −4 −2

ROC curves
log (λ)
0.0 0.2 0.4 0.6 0.8 1.0
Crainal base 3
Selected Predicted event probability

Maxillary skeletal 2
parameters Training set
Decision curve
Ar-Go-Me
1.0
Mandibular skeletal 6

1.0
Combined model
Y-Axis Clinical model
PP-OP All
None
L1-Me
ANB
0.8

Random

0.8
U6-PP
Maxillary/Mandibular 2 S-Ar-Go
Sensitivity

Go-Me

Net benefit
FMIA
0.6

0.6
allocation
PP-FH
Vertical dimension 11 U1-SN
LL-EP
N-S-Ar
0.4

0.4
Dc-Xi-Pm

(7:3) Dentoalveolar 10
MP-OP)
Co-A
S-Ar
AUC
0.2

0.2
Combined : 0.893 (0.847-0.919)
S-N Ceph score : 0.861 (0.822-0.900)
Overbite
Training set (n = 351) Test set (n = 151) Clinical : 0.701(0.645-0.756)
Facial profile 2 Y-Axis Length
ANS-Xi-Pm
0.0

0.0
TMJOA (n = 228) TMJOA (n = 104) FMA
Normal (n = 123) Normal (n = 47) 0.0 0.2 0.4 0.6 0.8 1.0
0.0 0.2 0.4 0.6 0.8 1.0
-0.4 -0.2 0.0 0.2 0.4
1 − Specificity Threshold probability
Coefficients

Fig 1. Flowchart depicting the design of the study.

experience, respectively) were assigned to evaluate these cephalometric parameters in the normal and DJD
TMJ independently using the CBCT without access to groups are listed in Supplementary Table I. To assess
the patients’ cephalograms. Any disagreement was the reproducibility of the cephalometric parameters, 2
resolved through consultation with a third specialist orthodontists traced 50 randomly selected cephalograms
with 20 years of experience diagnosing and treating and repeated these tracings after 30 days. The interclass
TMJ disorders. and intraclass correlation coefficients (ICCs) and Bland-
Cephalometric parameter extraction was performed Altman analysis were computed to evaluate the intraob-
on lateral cephalograms, which were acquired using server and interobserver reproducibility of cephalometric
the same radiographic machine. Cephalometric tracing parameters.
was conducted with the software Uceph (version 4.4.2; The least absolute shrinkage and selection operator
Yacent, China) by 2 orthodontists (X.F. and X.X.) with 5 (LASSO) logistic regression algorithm was applied to
years of experience each (Supplementary Fig 2). The or- choose the most effective and reproducible DJD-
thodontists were blinded to the clinical information and related cephalometric parameters out of the 36 listed
diagnosis of all patients. A total of 36 cephalometric pa- cephalometric parameters.28 Cephalometric parameters
rameters were digitized and divided into 7 categories: with nonzero coefficients in the LASSO regression were
cranial base relationship (3 parameters), size and posi- selected to generate a risk score (referred to as a Ceph
tion of the maxilla (2 parameters), size and position of score) in the training set. The Ceph score was then
the mandible (6 parameters), the relationship between used to predict the TMJ status in both the training
maxilla and mandible (2 parameters), vertical dimension and validation sets using a Mann-Whitney U test. The
(11 parameters), dentoalveolar features (10 parameters) predictive accuracy of the Ceph score was evaluated by
and facial profile (2 parameters). The reference plane the receiver operating characteristic (ROC) test and
was the Frankfort horizontal plane. Detailed values of area under the curve (AUC) in both sets.

February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics
Fang et al
Multivariable logistic regression analysis was con-
ducted on the training set to create a clinical model
with the following factors: age, gender, and the experi-
ence of limited mouth opening, deviation, clicking, crep-
itus, joint pain, and orofacial pain.
Ceph scores were combined with the clinical model
above to develop a diagnostic model for DJD. A com-
bined model with all features was constructed on the
basis of a multivariate logistic regression model. A
nomogram was generated on the basis of the combined
model in the training set using the R package rms as a
quantitative tool to predict the individual probability
of DJD.
We compared the discriminatory performance of the
3 established models (clinical model, Ceph score, and
combined model) using ROC curves and AUC values in
both the training and validation sets. Then, calibration
curves and the Hosmer-Lemeshow test were also em-
ployed to evaluate the calibration of the combined
model. To further evaluate the efficiency of the com-
bined model for different demographic characteristics,
a stratified analysis was conducted. The performance
of the combined model was evaluated by the AUC values
in different subgroups, including gender (male or fe-
male), sagittal dimension (skeletal Class I, skeletal Class
II, or skeletal Class III), and vertical dimension (low angle,
average angle, or high angle). The calibration curves
were plotted using R package rms.
To evaluate the clinical application potential of our
combined model, we conducted a decision curve analysis
(DCA) to further assess the net benefit acquired from the
deployment of the clinical model and the combined
model. The performance of these 2 models was analyzed
at different threshold probabilities, and the model with
the larger region under the curve was chosen for better
clinical outcomes.29
Statistical analysis
Normally distributed variables were compared using
Student’s t test. Continuous variables that were not
normally distributed were compared using the Mann-
Whitney U test. The discrete variables were analyzed us-
ing the chi-square test. All the statistical analyses used in
this study were performed with SPSS (version 20; IBM,
Armonk, NY), R (4.1.0; R Foundation for Statistical
Computing, Vienna, Austria), and EmpowerStats
2.2.0.11 (X&Y solutions, Inc, Boston, Mass). P \0.05
was considered statistically significant.
RESULTS
The study workflow is presented in Figure 1. A total
of 502 patients were included in this study and were
American Journal of Orthodontics and Dentofacial Orthopedics
263
randomly assigned to the training and testing groups
at a ratio of 7:3. Clinical characteristics and cephalo-
metric measurement values of included patients are pre-
sented in Table I and Supplementary Table II. The
intraobserver ICCs and the interobserver ICCs were
both .0.75. Bland-Altman plots of ANB, FH-PP, and
S-N are shown in Supplementary Figure 3. Bias in the
Bland-Altman analysis ranged from 0.08 to 0.61. All
P values in the Bland-Altman analysis were .0.05, rep-
resenting acceptable intraobserver and interobserver
reproducibility of cephalometric parameters. No signifi-
cant difference was found in any clinical feature be-
tween the training and the validation sets, which
indicated excellent equivalency between the 2 sets. Sig-
nificant differences were found in gender and experience
of limited mouth opening and crepitus between the
normal and DJD groups in both the training and test
sets (Table I).
A total of 36 cephalometric parameters were used for
the LASSO analysis. LASSO regression was employed to
choose the optimized cephalometric parameters for the
cephalometrics model. In this manner, 22 cephalometric
parameters with nonzero coefficients were selected to
construct the cephalometrics signature (Fig 2, A-C),
which consisted of 7 vertical dimension parameters, 5
dentoalveolar parameters, 4 mandibular skeletal param-
eters, 3 cranial base parameters, 1 facial profile param-
eter, 1 maxillary skeletal parameter, and 1 maxillary/
mandibular parameter. Using all these cephalometric pa-
rameters, a formula for calculating a risk score (Ceph
score) was established on the basis of a multi-logistic
regression, as presented in the Supplementary Material.
The Ceph score of each patient was calculated. A sig-
nificant difference was detected between patients with
and without DJD in the training set (P \0.001, Fig 3,
A), which was verified in the validation set (P \0.001,
Fig 3, C). The AUC value of Ceph scores was 0.861
(95% confidence interval (CI), 0. 822-0.900, Fig 3, B)
in the training set and 0.812 (95% CI, 0.738-0.886;
Fig 3, D) in the validation set, which demonstrated
that Ceph scores have a good discriminatory ability.
A combined model was constructed using multivari-
able regression analysis on the basis of traditional clin-
ical features and Ceph scores. A detailed description of
the features is shown in Table II. Ceph scores, the expe-
rience of limited mouth opening, and crepitus were all
significantly correlated with DJD. A nomogram based
on these features was established (Fig. 4, A). The ROC
test showed that the combined model scored 0.893
(95% CI, 0.847-0.919) on the training set, 0.828 (95%
CI, 0.757-0.899) on the validation set, and thus per-
formed better than the clinical model, which scored
0.701 (95% CI, 0.645-0.756) on the training set and
February 2023  Vol 163  Issue 2
264 Fang et al

Table I. Characteristics of patients in the training and validation set

Training set (n 5 351) Test set (n 5 151)

Characteristics DJD (n 5 228) Normal (n 5 123) P values DJD (n 5 104) Normal (n 5 47) P values
Age, mean 6 standard deviation 31.81 6 10.43 33.17 6 11.75 0.189 30.33 6 9.58 29.74 6 9.56 0.803
Gender, n (%)
Male 28 (12.3) 31 (25.2) 0.002 25 (24.0) 4 (8.5) 0.018
Female 200 (87.7) 92 (74.8) 79 (76.0) 43 (91.5)
Limited mouth opening, n (%)
Yes 88 (38.6) 29 (23.6) 0.003 34 (32.7) 8 (17.0) 0.034
No 140 (61.4) 94 (76.4) 70 (67.3) 39 (83.0)
Deviation, n (%)
Yes 104 (45.6) 60 (48.8) 0.324 50 (48.1) 29 (61.7) 0.084
No 124 (54.4) 63 (51.2) 54 (51.9) 18 (38.3)
Clicking, n (%)
Yes 171 (75.0) 82 (66.7) 0.063 84 (80.8) 34 (72.3) 0.171
No 57 (25.0) 41 (33.3) 20 (19.2) 13 (27.7)
Crepitus, n (%)
Yes 86 (37.7) 16 (13.0) \0.0001 33 (31.7) 8 (17.0) 0.043
No 142 (62.3) 107 (87.0) 71 (68.3) 39 (83.0)
Pain, n (%)
Yes 188 (82.5) 101 (82.1) 0.523 87 (83.7) 37 (78.7) 0.303
No 40 (17.5) 22 (17.9) 17 (16.3) 10 (21.3)
Ceph score, median (interquartile range) 68.62 (67.86-69.32) 66.76 (65.98-67.60) \0.0001 68.14 (67.17-69.15) 66.74 (66.11-67.25) \0.0001

0.603 (95% CI, 0.505-0.701) on the validation set (Figs
4, B and C). Significant differences were shown in AUC
values between the combined model and the clinical
model (P \0.001), which confirmed the combined
model’s superior predictive performance. In addition,
the combined model revealed a good capacity for iden-
tifying DJD in different subgroups (Table III), indicating
its utility for recognizing the disease in different stratifi-
cation contexts.
The calibration curves of the combined model be-
tween predicted and actual DJD showed good consis-
tency in both the training and validation sets (Figs 5,
A and B). According to the Hosmer-Lemeshow test,
nonsignificant P values were found in both the training
set (P 5 0.863) and validation set (P 5 0.881), demon-
strating that the combined model achieved acceptable
goodness of fit.
The DCA for the combined model and the traditional
clinical model is presented in Figure 6. The decision
curve demonstrated that the combined model would
be more beneficial than the “treat all patients” strategy
or the “treat none” strategy when the threshold proba-
bility was .0.312.
DISCUSSION
In this study, we built and validated a combined
model consisting of a cephalometric parameter-based
Ceph score and traditional clinical features, which can
assist in the clinical screening of DJD. This combined
model and its nomogram displayed superb resolution
ability on the training and validation sets in the ROC
test. The AUC values of the Ceph score (0.861 in the
training set, 0.812 in the validation set) and the com-
bined model (0.893 in the training set, 0.828 in the vali-
dation set) were significantly higher than those of
the clinical model (0.701 in the training set, 0.603 in
the validation set). Furthermore, the DCA showed that
the combined model could be more effective for clinical
decision-making than the clinical model. The standard
and well-developed landmarks used in cephalography
make it possible for this cephalometric parameter-
based combined model to be widely used in diagnosing
DJD.
We established that cephalometrics could distinguish
patients with DJD from normal patients through a
comprehensive analysis of cephalometric parameters,
including cranial base relationship, size and position of
the maxilla, size and position of the mandible, the rela-
tionship between maxilla and mandible, vertical dimen-
sion, dentoalveolar features, and facial profile.
Considering potential doubts that could arise regarding
the reproducibility and robustness of cephalometric pa-
rameters, we took strong precautions to ensure the ob-
jectivity and reproducibility of our cephalometric
model. The diagnosis of DJD and cephalometric feature
extraction used in this study have been commonly
applied and verified in previous studies. Two orthodon-
tists traced the cephalograms based on the established

February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics
Fang et al 265

A 34 35 33 30 28 27 23 20 20 16 12 6 5 4 0 B 30 23 13 2
1.35

1.0
1.30
Binomial Deviance

Coefficients
1.25

0.5
1.20
1.15

0.0
1.10

−0.5
1.05

−8 −6 −4 −2
−8 −6 −4 −2
log (λ) log (λ)

C Ar-Go-Me(Gonial/JawAngle,°)
Y-Axis(SGn-FH,°)
PP-OP(°)
Cephalometric parameters

L1-Me(mm)
ANB(°)
U6-PP(mm)
S-Ar-Go(ArticularAngle,°)
Go-Me(Mandibular body length,mm)
FMIA(L1-FH)
PP-FH(°)
U1-SN(°)
LL-EP(mm)
N-S-Ar(SaddleAngle,°)
Dc-Xi-Pm(°)
MP-OP(°)
Co-A (Midface Length,mm)
S-Ar (Posterior Cranial Base,mm)
S-N (Anterior Cranial Base,mm)
Overbite (mm)
Y-Axis Length (mm)
ANS-Xi-Pm (°)
FMA (FH-MP)

-0.4 -0.2 0.0 0.2 0.4

Coefficients

Fig 2. Cephalometrics feature selection using the LASSO binary logistic regression model: A, Tuning
parameter (l) selection in the LASSO model used 10-fold cross-validation via minimum criteria. Dotted
vertical lines were drawn at the optimal values using the minimum criteria and the l standard error of the
minimum criteria (1-standard error [SE] criteria). The optimal l value of 0.0027 with log (l) 5 5.8992
was selected (1-SE criteria) according to 10-fold cross-validation; B, LASSO coefficient profiles of the
36 cephalometrics features. The dotted line was plotted at the value selected using 10-fold cross-
validation in A, in which optimal l resulted in 22 nonzero coefficients; C, 22 cephalometric features
were selected for the signature building.

standards, and both ICCs and the Bland-Altman analysis All 36 cephalometric parameters from 7 categories
were used to evaluate subjectivity and operator error. describing the relationships between cranial and maxil-
Random errors for the digital tracing were observed in lofacial soft and hard tissues and occlusion were sub-
the Bland-Altman analysis, which might decrease the jected to analysis to rule out the influences of scale
reliability of the model. Future researchers are encour- differences. To prevent overfitting, parameters less
aged to test the reliability of the model with similar correlated with DJD were excluded from the final calcu-
cephalometric parameters. lation. Using all the above methods, a comparatively

American Journal of Orthodontics and Dentofacial Orthopedics February 2023  Vol 163  Issue 2
266 Fang et al

P<0.001

1.0
A 75 B

0.8
Training set

Training set
70

0.6
Sensitivity
Ceph score

0.4
65

0.2
AUC ： 0.861 (0.822-0.900)

0.0
60 0.0 0.2 0.4 0.6 0.8 1.0
Normol DJD
1 − Specificity
C 75 D
P<0.001

1.0
0.8
Validation set

70 Validation set

Sensitivity
Ceph score

0.6
0.4
65
0.2

AUC : 0.812 (0.738-0.886)

60
0.0

Normol DJD 0.0 0.2 0.4 0.6 0.8 1.0

1 − Specificity

Fig 3. The ROC curves of the Ceph score in the (A) training set and the (B) validation set. The box-dot
plots of the Ceph score in the training set (A) and the validation set (C). Plots (B) and (D) show the ROC
curves of the Ceph score in the training and validation sets, respectively.

Table II. Risk factor for DJD

Combined model (95% CI) Clinical model (95% CI)

Variable Odds ratio P values DJD P values

Age 0.9781(0.9520-1.0049) 0.1085 0.9847 (0.9636-1.0064) 0.1656
Gender 0.8911(0.4149-1.9139) 0.7676 0.4451 (0.2418-0.8193) 0.0093
Limited mouth opening 2.1320(1.0890-4.1739) 0.0272 1.8815 (1.1117-3.1842) 0.0185
Deviation 0.9991(0.5459-1.8287) 0.9977 0.7347 (0.4558-1.1844) 0.2058
Clicking 1.4780 (0.7591-2.8777) 0.2504 1.4814 (0.8750-2.5080) 0.1435
Crepitus 4.2697 (2.0247-9.0040) \0.0001 4.0898 (2.2162-7.5471) \0.0001
Pain 1.2900 (0.5956-2.7940) 0.5184 0.7766 (0.4122-1.4630) 0.4339
Ceph score 3.5658 (2.6574-4.7848) \0.0001 NA NA
NA, not available.

evidence-based cephalometric model was built for DJD
screening in dental practice.
In our cephalometric model, 22 cephalometric pa-
rameters with strong correlations with osseous abnor-
malities were extracted, most of which were vertical
dimension parameters. Specifically, counterclockwise
rotation of the occlusal plane and short posterior facial
height were closely related to DJD. Similarly, several
investigators have reported that a tendency toward
mandibular counterclockwise rotation, mandibular ret-
rognathism, and a shorter mandible are associated
with TMJOA.13,16,30,31 Moreover, in the sagittal dimen-
sion, larger ANB angles were positively related to
TMJOA, which is consistent with the higher prevalence
of TMJOA observed in patients with Class II patients
malocclusion compared with those with Class I and Class

February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics
Fang et al 267

A
Points

Gender

Age

Limited
mouth opening

Deviation

Clicking

Crepitus

Pain

Ceph score

Total Points

Risk of DJD

B Training set
C Validation set
1.0

1.0
0.8

0.8
Sensitivity

Sensitivity
0.6

0.6
0.4

0.4

AUC
AUC
0.2

0.2

Combined : 0.893 (0.847-0.919) Combined: 0.828 (0.757-0.899)

Ceph score : 0.861 (0.822-0.900)
Clinical : 0.701(0.645-0.756)
Ceph score: 0.812 (0.738-0.886)
Clinical: 0.603 (0.505-0.701)
0.0

0.0

0.0 0.2 0.4 0.6 0.8 1.0 0.0 0.2 0.4 0.6 0.8 1.0

1 − Specificity 1 − Specificity

Fig 4. Combined model for the prediction of DJD: A, The nomogram was developed in the training set,
with the Ceph score and clinical features. Plots (B) and (C) show the ROC curves for the combined
model, Ceph score, and clinical model in the training and validation sets, respectively.

III malocclusion.32 On one hand, a hyperdivergent skel-
etal pattern and mandibular retrognathism could result
from aggressive condylar resorption. It has been reported
that the digastric muscle and the mylohyoid muscle
retract the mandible downward and backward in pa-
tients with short mandibular ramus height.17,33 On the
other hand, these 2 clinical features have been regarded
as risk factors for TMD.34 In patients with DJD, compres-
sive deflection loaded on the condyle is produced with
masticatory muscular force during the interdigitation
of teeth, which may result in compressive condyle
resorption.17 Regarding mandibular skeletal parameters,
we found that increased articular angle (S-AR-GO) is
positively associated with DJD. A larger articular angle,
reflecting a backward position of the mandible, might
cause an unfavorable muscle attachment position and
abnormal muscle activity, leading to tooth extrusion
and subsequent counterclockwise mandibular rota-
tion.35,36 Moreover, abnormal overbite has also been
shown to be related to DJD. Although controversy re-
mains regarding the relationship between overbite and
TMD, it is undisputed that normal occlusal guidance is

American Journal of Orthodontics and Dentofacial Orthopedics February 2023  Vol 163  Issue 2
268 Fang et al

Table III. The AUC values of the combined model for stratified analysis in different subgroups
Subgroup Patients AUC values (95% CI)
Gender
Male (n 5 88) DJD (n 5 53) 0.812 (0.717-0.907)
Normal (n 5 35)
Female (n 5 414) DJD (n 5 279) 0.877 (0.841-0.912)
Normal (n 5 135)
Sagittal dimension
Skeletal Class I (n 5 256) DJD (n 5 148) 0.816 (0.763-0.869)
Normal (n 5 108)
Skeletal Class II (n 5196) DJD (n 5 160) 0.885 (0.820-0.949)
Normal (n 5 36)
Skeletal Class III (n 5 50) DJD (n 5 24) 0.899 (0.806-0.992)
Normal (n 5 26)
Vertical dimension
Low angle (n 5 167) DJD (n 5 98) 0.847 (0.786-0.909)
Normal (n 5 69)
Average angle (n 5 264) DJD (n 5 174) 0.855 (0.807-0.902)
Normal (n 5 90)
High angle (n 5 71) DJD (n 5 60) 0.949 (0.882-1.000)
Normal (n 5 11)

A Training set B Validation set

1.0
1.0
0.8

0.8
Actual DJD rate
Actual DJD rate

0.6

0.6
0.4

0.4
0.2

Apparent Apparent
Bias−corrected Bias−corrected
0.2

Ideal Ideal
0.0

0.0 0.2 0.4 0.6 0.8 1.0 0.2 0.4 0.6 0.8 1.0

Predicted event probability Predicted event probability

Fig 5. The calibration curves in the training set (A) and validation set (B) represent the predictive per-
formance of the combined model. Gray represents a perfect prediction, and pink represents the predic-
tive performance of the combined model.

important to a healthy muscle-occlusal system and the prevalence of crepitus is significantly higher in pa-
TMJ.37-39 tients with TMJOA,41 and our results are consistent
Among all clinical factors included in the combined with this finding. Usually, clicking indicates disc
model, the history of limited mouth opening (odds ratio, displacement with reduction,42 whereas crepitus is
2.132; 95% CI, 1.089-4.174; P 5 0.027) and crepitus more often related to erosion and the formation of sub-
(odds ratio, 4.270; 95% CI, 2.025-9.004; P \0.0011) chondral cysts and osteophytes in the condyles,43 indi-
were significantly correlated with DJD (Table II). Limited cating a late stage of degeneration. Pain is a
mouth opening is a typical symptom of disc displace- complicated situation that can derive from muscles,
ment without reduction. The prevalence of early-stage the TMJ or other orofacial areas.44 The relationship be-
DJD increases from 24% to 60% 1 month after limited tween pain and DJD is inconclusive because around one-
mouth opening occurs.40 Previous studies implied that third of patients with DJD might not suffer from

February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics
Fang et al
1.0
Combined model
Clinical model
All
None
0.8
Net benefit
0.6
0.4
0.2
0.0
0.0 0.2 0.4 0.6 0.8
Threshold probability
Fig 6. DCA for the combined model compared with the
clinical model. The y-axis represents the standardized
net benefit. The x-axis represents the threshold probabil-
ity. Gray represents the possibility that all patients had
DJD. Black represents the possibility that no patients
had DJD. The decision curves in the validation set
showed that using the combined model to predict DJD
adds more benefit than treating all or no patients when
the threshold probability is .0.312.
pain,45,46 and conversely, patients with orofacial pain
might not have osseous changes in the TMJ.43,47 There-
fore, it is reasonable that pain symptoms alone exhibited
limited ability in our model to predict DJD because of the
ambiguity of pain-related symptoms. However, with the
contribution of the Ceph score and clinical factors, the
combined model achieved better diagnostic ability.
Compared with previous research using radiographic
examination to diagnose TMJOA,19-21,23 our combined
model is advantageous for several reasons. First, the
clinical application potential of this combined model
under various circumstances was validated, as the strat-
ified analysis performed for further evaluation showed.
In addition to cephalometric parameters, conventional
clinical features were adopted in the combined model.
The combination of cephalometric and clinical features
offers a convenient DJD screening method without any
special imaging beyond what is routinely done. There
is no need for specialized equipment such as CBCT,
which is not commonly available in an average dental
clinic. Within limiting radiation exposure, the screening
of DJD is completed. Some newly graduated or general
dentists may have limited knowledge about DJD and
have difficulty diagnosing TMJ status in their orthodon-
tic practice.48,49 An algorithm based solely on cephalo-
metric measurements in our study can be built into
American Journal of Orthodontics and Dentofacial Orthopedics
269
software or a Web site, and using this algorithm to
analyze the cephalograms of patients could help clini-
cians to assess the joint status of patients and identify
patients with a higher likelihood of developing DJD. Af-
ter identifying patients with high odds of DJD, the
dentist could perform a more comprehensive clinical ex-
amination and imaging of the TMJ or refer the patient to
a TMJ specialist.
Several limitations of this study should be noted.
First, this research was conducted in a single hospital.
Although the cephalometric parameters based on stan-
dard and well-developed landmarks performed well in
numerous cephalometric analyses,13,14,16 further inves-
tigations based on multicentric databases are still
1.0 required to validate the accuracy and robustness of
this model. Second, the cephalometric tracing was con-
ducted by 2 orthodontists, but this might be acceptable
because the landmarks were identified strictly on the ba-
sis of cephalometric analysis criteria that are accepted
internationally. Moreover, the intraobserver ICCs and
the interobserver ICCs confirmed good intraobserver
and interobserver reproducibility of cephalometric pa-
rameters. Finally, to achieve data integrity, only the
most active features were included in the predictive
model, and it is possible that some other relevant ceph-
alometric features were excluded.
CONCLUSIONS
A novel cephalogram-based combined model was
constructed and verified to screen for DJD. The model
consists of Ceph scores and clinical features (including
age, gender, limited mouth opening, crepitus, etc.).
This combined model could enhance the accuracy of
DJD screening and increase the optimization of
decision-making in dental practice. Future studies are
needed to test the reliability of the model with similar
cephalometric parameters.
AUTHOR CREDIT STATEMENT
Xinyi Fang contributed to conceptualization, meth-
odology, software, validation, formal analysis, investiga-
tion, original draft preparation, and visualization; Xin
Xiong contributed to conceptualization, methodology,
software, investigation, and original draft preparation;
Jiu Lin contributed to validation, formal analysis, inves-
tigation, original draft preparation, and visualization;
Yange Wu contributed to resources and data curation;
Jie Xiang contributed to resources and data curation;
and Jun Wang contributed to manuscript review and ed-
iting, supervision, project administration, and funding
acquisition.
February 2023  Vol 163  Issue 2
270
SUPPLEMENTARY DATA
Supplementary data associated with this article can
be found, in the online version, at https://doi.org/10.
1016/j.ajodo.2022.10.015.
REFERENCES
1. Mejersj€ o C, Hollender L. Radiography of the temporomandibular
joint in female patients with TMJ pain or dysfunction. A seven
year follow-up. Acta Radiol Diagn (Stockh) 1984;25:169-76.
2. Tanaka E, Detamore MS, Mercuri LG. Degenerative disorders of the
temporomandibular joint: etiology, diagnosis, and treatment. J
Dent Res 2008;87:296-307.
3. Valesan LF, Da-Cas CD, Reus JC, Denardin ACS, Garanhani RR,
Bonotto D, et al. Prevalence of temporomandibular joint disorders:
a systematic review and meta-analysis. Clin Oral Investig 2021;25:
441-53.
4. Wang XD, Zhang JN, Gan YH, Zhou YH. Current understanding of
pathogenesis and treatment of TMJ osteoarthritis. J Dent Res
2015;94:666-73.
5. Yap AU, Zhang MJ, Cao Y, Lei J, Fu KY. Comparison of psycholog-
ical states and oral health-related quality of life of patients with
differing severity of temporomandibular disorders. J Oral Rehabil
2022;49:177-85.
6. Brooks SL, Westesson PL, Eriksson L, Hansson LG, Barsotti JB.
Prevalence of osseous changes in the temporomandibular joint
of asymptomatic persons without internal derangement. Oral
Surg Oral Med Oral Pathol 1992;73:118-22.
7. Zarb GA, Carlsson GE. Temporomandibular disorders: osteoar-
thritis. J Orofac Pain 1999;13:295-306.
8. Whyte A, Boeddinghaus R, Bartley A, Vijeyaendra R. Imaging of the
temporomandibular joint. Clin Radiol 2021;76:76.e21-35.
9. Xiong X, Ye Z, Tang H, Wei Y, Nie L, Wei X, et al. MRI of temporo-
mandibular joint disorders: recent advances and future directions.
J Magn Reson Imaging 2021;54:1039-52.
10. Nicolielo LFP, Van Dessel J, Shaheen E, Letelier C, Codari M,
Politis C, et al. Validation of a novel imaging approach using
multi-slice CT and cone-beam CT to follow-up on condylar re-
modeling after bimaxillary surgery. Int J Oral Sci 2017;9:139-44.
11. Larheim TA, Abrahamsson AK, Kristensen M, Arvidsson LZ.
Temporomandibular joint diagnostics using CBCT. Dentomaxillo-
fac Radiol 2015;44:20140235.
12. White SC, Pharoah MJ. Oral Radiology: Principles and Interpreta-
tion. 6th ed. St Louis: Mosby; 1982. p. 2009.
13. Kang JH, Yang IH, Hyun HK, Lee JY. Dental and skeletal matura-
tion in female adolescents with temporomandibular joint osteoar-
thritis. J Oral Rehabil 2017;44:879-88.
14. Janson G, Mendes LM, Junqueira CH, Garib DG. Soft-tissue
changes in Class II malocclusion patients treated with extractions:
a systematic review. Eur J Orthod 2016;38:631-7.
15. Mi JP, He P, Shi K, Feng SY, Chen XZ, He QQ, et al. Cephalometric
craniofacial features of patients with Sagliker syndrome: a primary
analysis of our experience. Ann Transl Med 2021;9:963.
16. Chen S, Lei J, Fu KY, Wang X, Yi B. Cephalometric analysis of the
facial skeletal morphology of female patients exhibiting skeletal
Class II deformity with and without temporomandibular joint os-
teoarthrosis. PLoS One 2015;10:e0139743.
17. Kajii TS, Fujita T, Sakaguchi Y, Shimada K. Osseous changes of the
mandibular condyle affect backward-rotation of the mandibular
ramus in Angle Class II orthodontic patients with idiopathic
condylar resorption of the temporomandibular joint. Cranio
2019;37:264-71.
February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics
Fang et al
18. Kim K, Wojczy nska A, Lee JY. The incidence of osteoarthritic
change on computed tomography of Korean temporomandibular
disorder patients diagnosed by RDC/TMD; a retrospective study.
Acta Odontol Scand 2016;74:337-42.
19. Choi E, Kim D, Lee JY, Park HK. Artificial intelligence in detecting
temporomandibular joint osteoarthritis on orthopantomogram.
Sci Rep 2021;11:10246.
20. Lee KS, Kwak HJ, Oh JM, Jha N, Kim YJ, Kim W, et al. Automated
detection of TMJ osteoarthritis based on artificial intelligence. J
Dent Res 2020;99:1363-7.
21. Kim D, Choi E, Jeong HG, Chang J, Youm S. Expert system for
mandibular condyle detection and osteoarthritis classification in
panoramic imaging using R-CNN and CNN. Appl Sci 2020;10:
7464.
22. Minston W, Benchimol D, Jacobs R, Lund B, Kr€ uger Weiner C,
Coucke W, et al. Pre-surgical radiographic and clinical features
as predictors for temporomandibular joint discectomy prognosis.
Oral Dis 2022;28:2185-93.
23. de Dumast P, Mirabel C, Cevidanes L, Ruellas A, Yatabe M,
Ioshida M, et al. A Web-based system for neural network based
classification in temporomandibular joint osteoarthritis. Comput
Med Imaging Graph 2018;67:45-54.
24. Jung W, Lee KE, Suh BJ, Seok H, Lee DW. Deep learning for oste-
oarthritis classification in temporomandibular joint. Oral Dis 2021.
25. Emshoff R, Bertram A, Hupp L, Rudisch A. A logistic analysis pre-
diction model of TMJ condylar erosion in patients with TMJ
arthralgia. BMC Oral Health 2021;21:374.
26. Holzinger A. From machine learning to explainable AI. 2018 World
Symposium on Digital Intelligence for Systems and Machines.
DISA); 2018. p. 55-66.
27. Schiffman E, Ohrbach R, Truelove E, Look J, Anderson G,
Goulet JP, et al. Diagnostic criteria for temporomandibular disor-
ders (DG/TMD) for clinical and research applications: recommen-
dations of the international RDC/TMD consortium network and
orofacial pain Special Interest Group. J Oral Facial Pain Headache
2014;28:6-27.
28. Tibshirani R. Regression shrinkage and selection via the lasso. J R
Stat Soc B (Methodol) 1996;58:267-88.
29. Van Calster B, Wynants L, Verbeek JFM, Verbakel JY,
Christodoulou E, Vickers AJ, et al. Reporting and interpreting de-
cision curve analysis: a guide for investigators. Eur Urol 2018;74:
796-804.
30. Nogami S, Yamauchi K, Satomi N, Yamaguchi Y, Yokota S, Abe Y,
et al. Risk factors related to aggressive condylar resorption after or-
thognathic surgery for females: retrospective study. Cranio 2017;
35:250-8.
31. Sun ZP, Zou BS, Zhao YP, Ma XC. Craniofacial morphology of Chi-
nese patients with bilateral temporomandibular joint osteoarthro-
sis. Chin J Dent Res 2011;14:21-7.
32. Krisjane Z, Urtane I, Krumina G, Neimane L, Ragovska I. The prev-
alence of TMJ osteoarthritis in asymptomatic patients with dento-
facial deformities: a cone-beam CT study. Int J Oral Maxillofac
Surg 2012;41:690-5.
33. Al-Moraissi EA, Wolford LM. Does temporomandibular joint pa-
thology with or without surgical management affect the stability
of counterclockwise rotation of the maxillomandibular complex
in orthognathic surgery? A systematic review and meta-analysis.
J Oral Maxillofac Surg 2017;75:805-21.
34. Miller JR, Mancl L, Critchlow C. Severe retrognathia as a risk factor
for recent onset painful TMJ disorders among adult females. J Or-
thod 2005;32:249-56: discussion 247.
35. Aymach Z, Kawamura H. Facilitating ramus lengthening following
mandibular-dependent surgical closing of a skeletal open bite with
Fang et al
short ramus: a new modified technique. J Craniomaxillofac Surg
2012;40:169-72.
36. Dinsdale A, Liang Z, Thomas L, Treleaven J. Is jaw muscle activity
impaired in adults with persistent temporomandibular disorders? A
systematic review and meta-analysis. J Oral Rehabil 2021;48:
487-516.
37. Ishizaki K, Suzuki K, Mito T, Tanaka EM, Sato S. Morphologic,
functional, and occlusal characterization of mandibular lateral
displacement malocclusion. Am J Orthod Dentofacial Orthop
2010;137(454):e451-9: discussion 454-5.
38. John MT, Hirsch C, Drangsholt MT, Mancl LA, Setz JM. Overbite
and overjet are not related to self-report of temporomandibular
disorder symptoms. J Dent Res 2002;81:164-9.
39. Olliver SJ, Broadbent JM, Thomson WM, Farella M. Occlusal fea-
tures and TMJ clicking: A 30-year evaluation from a cohort study.
J Dent Res 2020;99:1245-51.
40. Lei J, Han J, Liu M, Zhang Y, Yap AU, Fu KY. Degenerative tempo-
romandibular joint changes associated with recent-onset disc
displacement without reduction in adolescents and young adults.
J Craniomaxillofac Surg 2017;45:408-13.
41. Abrahamsson AK, Kristensen M, Arvidsson LZ, Kvien TK,
Larheim TA, Haugen IK. Frequency of temporomandibular joint
osteoarthritis and related symptoms in a hand osteoarthritis
cohort. Osteoarthritis Cartilage 2017;25:654-7.
42. Dias IM, Cordeiro PC, Devito KL, Tavares ML, Leite IC, Tesch Rde S.
Evaluation of temporomandibular joint disc displacement as a risk
factor for osteoarthrosis. Int J Oral Maxillofac Surg 2016;45:313-7.
American Journal of Orthodontics and Dentofacial Orthopedics
271
43. Arayasantiparb R, Mitrirattanakul S, Kunasarapun P,
Chutimataewin H, Netnoparat P, Sae-Heng W. Association of
radiographic and clinical findings in patients with temporoman-
dibular joints osseous alteration. Clin Oral Investig 2020;24:221-7.
44. Gil-Martınez A, Paris-Alemany A, Lopez-de-Uralde-Villanueva I,
La Touche R. Management of pain in patients with temporoman-
dibular disorder (TMD): challenges and solutions. J Pain Res 2018;
11:571-87.
45. Campos MI, Campos PS, Cangussu MC, Guimar~aes RC, Line SR.
Analysis of magnetic resonance imaging characteristics and pain
in temporomandibular joints with and without degenerative
changes of the condyle. Int J Oral Maxillofac Surg 2008;37:
529-34.
46. Liang X, Liu S, Qu X, Wang Z, Zheng J, Xie X, et al. Evaluation of
trabecular structure changes in osteoarthritis of the temporoman-
dibular joint with cone beam computed tomography imaging. Oral
Surg Oral Med Oral Pathol Oral Rad 2017;124:315-22.
47. Yi Y, Zhou X, Xiong X, Wang J. Neuroimmune interactions in pain-
ful TMD: mechanisms and treatment implications. J Leukoc Biol
2021;110:553-63.
48. Porto F, Harrell R, Fulcher R, Gonzales T. Knowledge and beliefs
regarding temporomandibular disorders among orthodontists.
Am J Orthod Dentofacial Orthop 2019;156:475-84.
49. Al-Huraishi HA, Meisha DE, Algheriri WA, Alasmari WF,
Alsuhaim AS, Al-Khotani AA. Newly graduated dentists’ knowl-
edge of temporomandibular disorders compared to specialists in
Saudi Arabia. BMC Oral Health 2020;20:272.
February 2023  Vol 163  Issue 2
271.e1 Fang et al

SUPPLEMENTARY DATA 0.07146 3 FMIA (L1-FH) 1 0.24926 3 U6.PP.MM 1

Calculation formulas for Ceph score, clinical model, and
combined model
Ceph score 5 0.00776 3 N-S-Ar (SaddleAngle,  ) 1
0.20498 3 S-Ar-Go (ArticularAngle,  ) 0.09766 3
S-N (Anterior Cranial Base, mm) 0.06531 3 S-Ar (Pos-
terior Cranial Base, mm) 0.02252 3 Co-A (Midface
Length, mm) 1 0.3145 3 Ar-Go-Me (Gonial/JawAngle,

) 0.009 3 Dc-Xi-Pm ( ) 1 0.2901 3 Y-Axis (SGn-FH,

) 0.22797 3 Y-Axis Length (mm) 1 0.20486 3 Go-
Me (Mandibular body length, mm) 1 0.26303 3 ANB
0.29693 3 FMA (FH-MP) 1 0.03459 3 PP-FH ( )
0.02125 3 MP-OP ( ) 1 0.27777 3 PP-OP ( )
0.27614 3 ANS-Xi-Pm ( ) 1 0.03083 3 U1-SN ( ) 1
0.26686 3 L1-Me (mm) 0.1302 3 Overbite (mm) 1
0.0174 3 LL-EP (mm)
Clinical score 5 0.81005 0.80942 3 (1, Gender 5
male) 0.01537 3 Age 1 0.63207 3 (1, Limited mouth
opening 5 yes) 0.30825 3 (1, Deviation 5 yes) 1
0.39300 3 (1, Clicking 5 yes) 1 1.40849 3 (1,
Crepitus 5 yes) 0.25286 3 (1, Pain 5 yes)
Nomoscore 5 85.75810 0.11527 3 (Gender 5
male) 0.02214 3 Age 1 0.75705 3 (1, Limited mouth
opening 5 yes) 0.00087 3 (1, Deviation 5 yes) 1
0.39070 3 (1, Clicking 5 yes) 1 1.45155 3 (1,
Crepitus 5 yes) 1 0.25464 3 (1, Pain 5 yes) 1
1.27139 3 Ceph score.

Supplementary Fig 1. Images of health TMJ and TMJs with degenerative joint diseases: A, Flat-
tening; B, Erosion; C, Osteophyte; D, Subcutaneous cyst; E, Extensive sclerosis; F, Erosion (coronal
view); G, Erosion (transverse view); H, l healthy joint; K, Healthy joints (transverse view).

February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics
Fang et al 271.e2

Supplementary Fig 2. Cephalometric tracing.

American Journal of Orthodontics and Dentofacial Orthopedics February 2023  Vol 163  Issue 2
271.e3 Fang et al

Supplementary Fig 3. Bland-Altman plots demonstrate the bias for cephalometric variables: A-C,
ANB; D-F, FH-PP; G-I, S-N. Only 3 parameters were shown in this figure. A, D, and G, Showed intra-
observer error for observer 1. B, E, and H, Showed intraobserver error for observer 2. C, F, and I,
Showed interobserver error. Red indicates the 95% limits of test-retest agreement. Black indicates
the mean of the differences, which are close to 0, indicating low test-retest bias.

February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics
Fang et al 271.e4

Supplementary Table I. Detailed description of extracted cephalometrics features

Variables DJD Normal P value
Cranial base
N-S-Ar (saddle angle) ( ) 125.2 6 5.4 126.6 6 4.9 0.004
S-N (anterior cranial base) (mm) 62.2 6 3.1 63.3 6 3.3 \0.001
S-Ar (posterior cranial base) (mm) 32.4 6 3.2 33.2 6 3.3 0.013
Maxillary skeletal
Co-A (midface length) (mm) 80.1 6 4.6 81.1 6 6.1 0.044
SNA ( ) 82.2 6 3.5 81.5 6 3.5 0.033
Mandibular skeletal
SNB ( ) 77.5 6 3.8 78.1 6 4.0 0.089
S-Ar-Go (articular angle) ( ) 151.9 6 6.7 148.6 6 5.9 \0.001
Ar-Go-Me (gonial/Jaw angle) ( ) 117.7 6 6.5 116.8 6 5.6 0.121
Dc-Xi-Pm ( ) 36. 9 6 6.0 37.3 6 4.9 0.467
Ar-Go (ramus height) (mm) 45.8 6 4.4 48.9 6 4.5 \0.001
Go'-Me (mandibular body length) (mm) 68.5 6 4.7 68. 8 6 5.2 0.592
Maxillary/Mandibular
ANB ( ) 4.7 6 2.8 3.4 6 2.2 \0.001
Wits (mm) 0.9 6 3.8 0.2 6 2.9 0.043
Vertical dimension
FMA (FH-MP) 25.0 6 5.6 22.8 6 5.2 \0.001
SN-MP ( ) 34.9 6 6.1 32.4 6 5.9 \0.001
PP-FH ( ) 0.17 6 2.8 0.2 6 2.7 0.759
OP-FH ( ) 8.7 6 3.9 7.5 6 3.7 0.001
MP-OP ( ) 16.3 6 4.2 15.4 6 3.8 0.018
PP-OP ( ) 8.5 6 3.6 6. 8 6 3.2 \0.001
ANS-Xi-Pm ( ) 47.2 6 4.9 47.0 6 4.4 0.637
N-Me (anterior face height) (mm) 114.8 6 6.2 115.3 6 7.3 0.400
S-Go (mm) 75.8 6 5.9 79.1 6 6.3 \0.001
Y-axis (SGn-FH) ( ) 61.5 6 3.6 60.7 6 3.2 0.012
Y-axis length (mm) 115. 4 6 6.2 117.2 6 7.5 0.004
Dentoalveolar
U1-L1 (interincisal angle) ( ) 125.6 6 12.8 126.2 6 10.2 0.625
U1-SN ( ) 102.2 6 8.6 103.5 6 8.1 0.087
FMIA ( ) 57. 7 6 9.2 59.3 6 7.0 0.040
IMPA (L1-MP) 97.3 6 8.1 97.8 6 6.5 0.487
U6-PP (mm) 22.5 6 2.2 22.8 6 2.3 0.173
L6-MP (mm) 31.9 6 2.8 31.9 6 2.8 0.971
U1-ANS (mm) 28.7 6 2.6 28.1 6 2.6 0.011
L1-Me (mm) 40.0 6 3.1 39.8 6 3.3 0.508
Overjet (mm) 4.2 6 1.8 3.7 6 1.4 0.006
Overbite (mm) 2.6 6 2.0 2.5 6 1.4 0.671
Facial profile
UL-EP (mm) 0.7 6 2.8 0.1 6 2.2 0.001
LL-EP (mm) 0.8 6 2.8 0.8 6 2.3 0.876

Note. Values are presented as mean 6 standard deviation.

American Journal of Orthodontics and Dentofacial Orthopedics February 2023  Vol 163  Issue 2
271.e5 Fang et al

Supplementary Table II. Diagnostic performance of models on the training and validation sets
Training set (n 5 332) Test set (n 5 141)

AUC
Models Sensitivity Specificity Accuracy AUC (95% CI) Sensitivity Specificity Accuracy (95% CI)
Clinical model 0.513 0.805 0.615 0.701 (0.645-0.756) 0.606 0.638 0.616 0.603 (0.505-0.701)
Ceph score 0.750 0.846 0.784 0.861 (0.822-0.900) 0.702 0.894 0.762 0.812 (0.738-0.886)
Combined model 0.873 0.756 0.832 0.883 (0.847-0.919) 0.702 0.872 0.755 0.828 (0.757-0.899)

February 2023  Vol 163  Issue 2 American Journal of Orthodontics and Dentofacial Orthopedics