Search

Background: Machine learning (ML) is increasingly used to predict the prognosis of numerous diseases. This retrospective analysis aimed to develop a prediction model using ML algorithms and to identify predictors associated with the recurrence of hallux valgus (HV) following surgery. Methods: A total of 198 symptomatic feet that underwent chevron osteotomy combined with a distal soft tissue procedure were enrolled and analyzed from 2 independent medical centers. The feet were grouped according to nonrecurrence or recurrence based on 1-year follow-up outcomes. Preoperative weightbearing radiographs and immediate postoperative nonweightbearing radiographs were obtained for each HV foot. Radiographic measurements (eg, HV angle and intermetatarsal angle) were acquired and used for ML model training. A total of 9 commonly used ML models were trained on the data obtained from one institute (108 feet), and tested on the other data set from another independent institute (90 feet) for external validation. Optimal feature sets for each model were identified based on a 2000-resample bootstrap-based internal validation via an exhaustive search. The performance of each model was then tested on the external validation set. The area under the curve (AUC), classification accuracy, sensitivity, and specificity of each model were calculated to evaluate the performance of each model. Results: The support vector machine (SVM) model showed the highest predictive accuracy compared to other methods, with an AUC of 0.88 and an accuracy of 75.6%. Preoperative hallux valgus angle, tibial sesamoid position, postoperative intermetatarsal angle, and postoperative tibial sesamoid position were identified as the most selected features by several ML models. Conclusion: ML classifiers such as SVM could predict the recurrence of HV (an HVA >20 degrees) at a 1-year follow-up while identifying associated predictors in a multivariate manner. This study holds the potential for foot and ankle surgeons to effectively identify individuals at higher risk of HV recurrence postsurgery. [ABSTRACT FROM AUTHOR]

Background: Intractable hallucal ganglion cysts (HGCs) are often a symptomatic and recurrent condition. Its connection with the ankle joint is not well understood. Our aim was to evaluate the relationship between tenosynovitis of the flexor hallucis longus (FHL) tendon at the level of the ankle with formation of an HGC. In addition, we sought to analyze the outcomes of cyst excision combined with ankle capsulorrhaphy. Methods: Nineteen patients with HGC who underwent surgical intervention were included between June 2016 and June 2019. Eight had known recurrences. Ankle arthrography and cyst excision were performed on all patients. Clinical evaluations included the American Orthopaedic Foot & Ankle Society (AOFAS) scores, visual analog scale (VAS), and evaluation of postoperative complications. The mean follow-up period was 16.5 ± 8.6 months. Results: Thirteen of the 19 HGCs (68.4%) had a connection with the FHL tendon sheath. Combined with ankle capsulorrhaphy, there was no recurrence after cyst excision. The VAS score decreased from 2.1 ± 1.5 to 0.4 ± 0.8, and AOFAS score significantly improved from 84.3 ± 8.7 to 97.4 ± 5.2 at final follow-up (P <.001). Conclusions: Most of these patients had a connection between the HGC and ankle joint. Ankle arthrography appeared to be useful for diagnosis, and cyst excision combined with ankle capsulorrhaphy was an effective treatment without cyst recurrence. Level of Evidence: Level IV, case series. [ABSTRACT FROM AUTHOR]

Background: Although patients with an anterior cruciate ligament (ACL) injury have a high risk of developing posttraumatic osteoarthritis (PTOA), the role of meniscus hypertrophy and mineralization in PTOA after an ACL injury remains unknown. Purpose/Hypothesis: The purpose of this study was to determine if menisci respond to abnormal loading and if an ACL injury results in meniscus hypertrophy and calcification. The hypotheses were that (1) abnormal mechanical loading after an ACL injury induces meniscus hypertrophy and mineralization, which correlates to articular cartilage damage in vivo, and (2) abnormal mechanical loading on bovine meniscus explants induces the overexpression of hypertrophic and mineralization markers in vitro. Study Design: Controlled laboratory study. Methods: In vivo guinea pig study (hypothesis 1): Three-month-old male Hartley guinea pigs (n = 9) underwent ACL transection (ACLT) on the right knee; the left knee served as the control. Calcification in the menisci was evaluated by calcein labeling 1 and 5 days before knee harvesting at 5.5 months. Cartilage and meniscus damage and mineralization were quantified by the Osteoarthritis Research Society International score and meniscus grade, respectively. Indian hedgehog (Ihh), matrix metalloproteinase–13 (MMP-13), collagen type X (Col X), progressive ankylosis homolog (ANKH), ectonucleotide pyrophosphatase/phosphodiesterase–1 (ENPP1), alkaline phosphatase (ALP), inorganic pyrophosphate (PPi), and inorganic phosphate (Pi) concentrations were evaluated by immunohistochemistry and enzyme-linked immunosorbent assay. In vitro bovine meniscus explant study (hypothesis 2): Bovine meniscus explants were subjected to 25% strain at 0.3 Hz for 1, 2, and 3 hours. Cell viability was determined using live/dead staining. The levels of mRNA expression and protein levels were measured using real-time quantitative reverse transcription polymerase chain reaction and Western blot after 24, 48, and 72 hours in culture. The conditioned medium was collected for sulfated glycosaminoglycan (GAG) release and Pi/PPi assay. Results: In vivo guinea pig study: Meniscus size and area as well as intensity of meniscus calcification were significantly increased in the ACLT group compared with the control group. Both calcified area and intensity were correlated with cartilage damage in the ACLT group (meniscus calcified area: r = 0.925, P < .0001; meniscus calcified intensity: r = 0.944, P < .0001). Ihh, MMP-13, Col X, ANKH, ENPP1, and ALP expression were increased in the ACLT group compared with the control group. The Pi level and Pi/PPi ratio increased by 63% and 42%, respectively, in the ACLT group compared with the control group. In vitro bovine meniscus explant study: Cell death was found in the superficial zone of the bovine meniscus explants after loading for 3 hours. The mRNA expression and protein levels of MMP-13, ANKH, ENPP1, and ALP were up-regulated in all 3-hour loaded samples. The Pi/PPi ratio and sulfated GAG content in the culture medium were increased in the 3-hour loaded group. Conclusion: Meniscus hypertrophy and mineralization correlated to cartilage degeneration after ACL injuries. Clinical Relevance: The study data suggest that the suppression of meniscus hypertrophy and calcification may decrease the risk of PTOA after ACL injuries. [ABSTRACT FROM AUTHOR]