Abstract

Objective: This study aimed to diagnose hallux valgus (HV) using machine learning algorithms (MLAs) applied to angular measurements obtained from foot X-ray images.

Materials and Methods: The study was a retrospective observational investigation. The sample comprised 50 patients diagnosed with HV and 50 controls. The intermetatarsal angle (IMA), interphalangeal angle (IPA), talometatarsal angle (TMTA), metatarsal tangent angle (MTTA), metatarsus adductus angle (MTAA), and metatarsal parabola angle (MTPA) were measured on the anteroposterior X-ray image, and calcaneal inclination angle (CIA) and the lateral talocalcaneal angle (LTCA) were measured on the lateral X-ray image. The following algorithms were used as machine learning algorithms (MLAs): Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting (GB), XGBoost (XGB), LightGBM (LGBM), AdaBoost (ADA), Extra Trees (ET), K-Nearest Neighbor (KNN), and Linear Discriminant Analysis (LDA). Statistical analyses were performed using the open-source RStudio software.

Results: The diagnostic accuracy rates of the algorithms (CV) were 90% for XGB, ET, RF, LGBM, and LDA; 85% for ADA, LR, SVM, and GB; and 80% for KNN. The mean ± SD values of the variables for the control and patient groups, respectively, were calculated as 21.71 ± 1.83 and 22.52 ± 3.32 for IMA; 17.86 ± 1.79 and 18.35 ± 2.28 for MTAA; 143.43 ± 9.20 and 143.25 ± 9.14 for MTPA; and 50.96 ± 5.27 and 49.42 ± 6.98 for LTCA. The median (min–max) values were: for IPA, 36.48 (25.73–45.82) and 45.41 (29.60–76.90); for TMTA, 7.60 (5.91–11.45) and 12.54 (6.62–19.50); for MTTA, 7.93 (1.07–13.20) and 7.13 (2.60–12.07); and for CIA, 28.52 (22.31–37.65) and 27.19 (10.85–47.46).

Conclusions: Angular measurements derived from X-ray images enabled MLAs to diagnose HV with an accuracy of up to 90%. This finding demonstrates the applicability of artificial intelligence for diagnostic purposes in imaging-based applications.

Keywords: hallux valgus deformity, machine learning algorithms, foot anatomy, x-ray images, intermetatarsal angle

Copyright and license

Copyright © 2026 The Author(s). This is an open-access article published by Bolu İzzet Baysal Training and Research Hospital under the terms of the Creative Commons Attribution License (CC BY) which permits unrestricted use, distribution, and reproduction in any medium or format, provided the original work is properly cited.

How to cite

1.
Kurtboğan M, Ray G, Ray A, Kürtül İ, Karatop M. AI-based diagnosis of hallux valgus: evaluation of measurements derived from foot X-ray images. Northwestern Med J. 2026;6(4):330-42. https://doi.org/10.54307/NWMJ.2026.264

References

  1. Kwolek K, Gądek A, Kwolek K, Lechowska-Liszka A, Malczak M, Liszka H. Artificial intelligence-based diagnosis of hallux valgus interphalangeus using anteroposterior foot radiographs. World J Orthop. 2025; 16(6): 103832. https://doi.org/10.5312/wjo.v16.i6.103832
  2. Açikgöz AK, Mutluay ŞD, Binokay F, Bozkir MG. Evaluation of the relationship between hallux valgus and foot measurements in radiographic images of adult female. Surg Radiol Anat. 2022; 44(9): 1281-8. https://doi.org/10.1007/s00276-022-03012-8
  3. Nebhani N, Yatin Trivedy M, Heyes G, Molloy A, Mason L. Hallux valgus interphalangeus measurement: comparison of the 2 radiographic methods. Foot Ankle Spec. 2024; 17(4): 323-8. https://doi.org/10.1177/19386400221078677
  4. Hida M, Eto S, Wada C, et al. Development of hallux valgus classification using digital foot images with machine learning. Life (Basel). 2023; 13(5): 1146. https://doi.org/10.3390/life13051146
  5. Zhao R, Wang G, Li F, et al. Developing machine learning-based predictive models for hallux valgus recurrence based on measurements from radiographs. Foot Ankle Int. 2024; 45(9): 1000-8. https://doi.org/10.1177/10711007241256648
  6. Kwolek K, Gądek A, Kwolek K, Kolecki R, Liszka H. Automated decision support for hallux valgus treatment options using anteroposterior foot radiographs. World J Orthop. 2023; 14(11): 800-12. https://doi.org/10.5312/wjo.v14.i11.800
  7. Forin Valvecchi T, Marcolli D, De Cesar Netto C. Advanced three-dimensional assessment and planning for hallux valgus. Foot Ankle Clin. 2025; 30(2): 349-62. https://doi.org/10.1016/j.fcl.2024.06.008
  8. Spindler FT, Ettinger S, D. A. F. Scientific committee, Baumbach SF. Classification of hallux valgus deformity-is there a standard? Arch Orthop Trauma Surg. 2024; 144(11): 4737-43. https://doi.org/10.1007/s00402-024-05522-z
  9. Chen YS, Liang CH, Shih HT, Tu KC, Tang SC, Wang SP. Correlation between hallux valgus severity and the prevalence of metatarsus adductus in hallux valgus. J Foot Ankle Res. 2025; 18(2): e70049. https://doi.org/10.1002/jfa2.70049
  10. Li R, Tan K, Xie Y, Wang F. Morphology variations with medial cuneiform in hallux valgus. Anat Sci Int. 2024; 99(1): 59-67. https://doi.org/10.1007/s12565-023-00734-6
  11. Bu P, Li C, Pu L, Ma X, Meng X, Xu Y. Radiographic assessment of relationship between medial cuneiform obliquity and hallux valgus. J Foot Ankle Surg. 2023; 62(3): 583-9. https://doi.org/10.1053/j.jfas.2022.06.009
  12. Takeda R, Mizuhara H, Uchio A, et al. Automatic estimation of hallux valgus angle using deep neural network with axis-based annotation. Skeletal Radiol. 2024; 53(11): 2357-66. https://doi.org/10.1007/s00256-024-04618-2
  13. Matsumoto T, Higuchi J, Maenohara Y, et al. The discrepancy between radiographically-assessed and self-recognized hallux valgus in a large population-based cohort. BMC Musculoskelet Disord. 2022; 23(1): 31. https://doi.org/10.1186/s12891-021-04978-z
  14. Kwolek K, Liszka H, Kwolek B, Gądek A. Measuring the angle of hallux valgus using segmentation of bones on X-ray images. In: Tetko I, Kůrková V, Karpov P, Theis F, editors. Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions. ICANN 2019. Lecture Notes in Computer Science, Vol 11731. Cham: Springer; 2019: 327-38. https://doi.org/10.1007/978-3-030-30493-5_32
  15. Izquierdo P, Calderon A, Jenkins GL, Thorne S, Mathieson I. Automatic angle recognition in hallux valgus. In: Proceedings of the UKSim-AMSS 22nd International Conference on Computer Modelling and Simulation (UKSim2020); 2020; Cambridge, United Kingdom. https://doi.org/10.5013/IJSSST.a.21.02.23
  16. Li T, Wang Y, Qu Y, Dong R, Kang M, Zhao J. Feasibility study of hallux valgus measurement with a deep convolutional neural network based on landmark detection. Skeletal Radiol. 2022; 51(6): 1235-47. https://doi.org/10.1007/s00256-021-03939-w
  17. Ray A, Ray G, Kürtül İ, Şenol GT. Sex estimation from the variables of talocrural joint by using machine learning algorithms. J Forensic Leg Med. 2025; 114: 102912. https://doi.org/10.1016/j.jflm.2025.102912
  18. Taşkın Şenol G, Kürtül İ, Ray A, Ahmetoğlu G, Seçgin Y, Öner Z. Determination of gender by machine learning algorithms, through using craniocervical junction parameters and dimensions of the cervical spinal canal. Osmangazi Journal of Medicine. 2023; 45(5): 672-7. https://doi.org/10.20515/otd.1291030
  19. Ma S, Wang H, Zhao W, et al. An interpretable deep learning model for hallux valgus prediction. Comput Biol Med. 2025; 185: 109468. https://doi.org/10.1016/j.compbiomed.2024.109468
  20. Wang Q, Wang JH, Ji DD, Zhang Y, Zhao HM. Automated measurement of hallux valgus angles using a deep learning model: validation and comparison with surgeons of varying expertise. Sci Rep. 2026; 16(1): 12280. https://doi.org/10.1038/s41598-026-42100-2
  21. Wang Q, Wang JH, Ji DD, Liang JQ, Yang XQ, Zhao HM. Deep learning versus manual measurement of hallux valgus angle and intermetatarsal angle on weight-bearing X-rays in hallux valgus. BMC Musculoskelet Disord. 2025; 27(1): 58. https://doi.org/10.1186/s12891-025-09420-2
  22. Hussain A, Lee C, Hu E, Amirouche F. Deep learning automation of radiographic patterns for hallux valgus diagnosis. World J Orthop. 2024; 15(2): 105-9. https://doi.org/10.5312/wjo.v15.i2.105
  23. Takeda R, Uchio A, Iidaka T, et al. Automatic Hardy and Clapham’s classification of hallux sesamoid position on foot radiographs using deep neural network. Foot Ankle Surg. 2025; 31(3): 220-6. https://doi.org/10.1016/j.fas.2024.10.002
  24. Wang C, Li C, Zhang R, et al. Identification of radiographic characteristics associated with pain in hallux valgus patients: a preliminary machine learning study. Front Public Health. 2022; 10: 943026. https://doi.org/10.3389/fpubh.2022.943026
  25. Jung DY, Jung SH, Gwak GT. Contributions of age, gender, body mass index, and normalized arch height to hallux valgus: a decision tree approach. BMC Musculoskelet Disord. 2023; 24(1): 278. https://doi.org/10.1186/s12891-023-06389-8