Interobserver Agreement and Performance of Concurrent AI Assistance for Radiographic Evaluation of Knee Osteoarthritis.

Background Due to conflicting findings in the literature, there are concerns about a lack of objectivity in grading knee osteoarthritis (KOA) on radiographs. Purpose To examine how artificial intelligence (AI) assistance affects the performance and interobserver agreement of radiologists and orthopedists of various experience levels when evaluating KOA on radiographs according to the established Kellgren-Lawrence (KL) grading system. Materials and Methods In this retrospective observer performance study, consecutive standing knee radiographs from patients with suspected KOA were collected from three participating European centers between April 2019 and May 2022. Each center recruited four readers across radiology and orthopedic surgery at in-training and board-certified experience levels. KL grading (KL-0 = no KOA, KL-4 = severe KOA) on the frontal view was assessed by readers with and without assistance from a commercial AI tool. The majority vote of three musculoskeletal radiology consultants established the reference standard. The ordinal receiver operating characteristic method was used to estimate grading performance. Light kappa was used to estimate interrater agreement, and bootstrapped t statistics were used to compare groups. Results Seventy-five studies were included from each center, totaling 225 studies (mean patient age, 55 years ± 15 [SD]; 113 female patients). The KL grades were KL-0, 24.0% (n = 54); KL-1, 28.0% (n = 63); KL-2, 21.8% (n = 49); KL-3, 18.7% (n = 42); and KL-4, 7.6% (n = 17). Eleven readers completed their readings. Three of the six junior readers showed higher KL grading performance with versus without AI assistance (area under the receiver operating characteristic curve, 0.81 ± 0.017 [SEM] vs 0.88 ± 0.011 [P < .001]; 0.76 ± 0.018 vs 0.86 ± 0.013 [P < .001]; and 0.89 ± 0.011 vs 0.91 ± 0.009 [P = .008]). Interobserver agreement for KL grading among all readers was higher with versus without AI assistance (κ = 0.77 ± 0.018 [SEM] vs 0.85 ± 0.013; P < .001). Board-certified radiologists achieved almost perfect agreement for KL grading when assisted by AI (κ = 0.90 ± 0.01), which was higher than that achieved by the reference readers independently (κ = 0.84 ± 0.017; P = .01). Conclusion AI assistance increased junior readers' radiographic KOA grading performance and increased interobserver agreement for osteoarthritis grading across all readers and experience levels. Published under a CC BY 4.0 license. Supplemental material is available for this article.

Alarming increase in the registration of degenerative rotator cuff-related lesions a nationwide epidemiological study investigating 244,519 patients.

PURPOSE AND HYPOTHESIS: Shoulder lesions are common and a challenge to diagnose. They often result in significant disability for the patient and are an economic burden to society. From recent studies, an increasing incidence has been reported. The purpose of this study was to investigate and map the incidence of shoulder lesions in Denmark from 1996 to 2013 with focus on sex, age and geographical area. METHODS: The Danish National Patient Registry was searched retrospectively to find the number of shoulder lesions in Denmark during the period 1996-2013. Regional population data were retrieved from the services of Statistics Denmark. Incidence rates were analysed using Poisson regression models, and all analyses were done in R 3.2.2, and p values less than 0.05 were considered statistically significant. RESULTS: During the 18-year period, 244,519 patients with a DM 75 diagnosis were registered. Male-to-female ratio was 51:49, and median age was 51. Most frequent were rotator cuff syndrome with a mean incidence rate of 313.3 (confidence interval 241.8-384.8) per 105 person-years at risk (PYRS). A statistically significant increase in overall incidence rate from 149.4 per 105 PYRS in 1996 to 715.3 per 105 PYRS in 2013 was found (p < 0.01). Incidence was highest for men aged 51-70 (1085.1 per 105 PYRS in 2013). There was no significant difference in incidence between sexes. Rural areas had a 1.4-fold higher mean incidence rate than urban areas. CONCLUSION: The incidence of shoulder lesions rapidly increased mainly due to an increase among people of working age (31-70 years). There were no significant differences in incidence between sexes. Rural areas had a 1.4-fold higher incidence rate than urban areas. As shoulder lesions impose a huge socioeconomic burden on society, not to mention a great distress to the patient, the present findings is highly relevant for political decision-making regarding preventive and health promoting initiatives.

Severe Functional Debilitations After Complications Associated With Acute Achilles Tendon Rupture With 9 Years of Follow-Up.

The purpose of the present study was to investigate the long-term effect of deep infection, sural nerve injury, and repeat rupture in the treatment of acute Achilles tendon rupture. A total of 324 patients had made a claim to the Danish Patient Insurance Association from 1992 to 2010 for a complication after acute Achilles tendon rupture. Of the 324 patients, 119 (36.7%) (77 [64.7%] males and 42 [35.3%] females) returned the Achilles tendon total rupture score and the 36-item short-form survey questionnaires. Patients with deep infection (n = 10), sural nerve injury (n = 10), and repeat rupture (n = 16) participated in a follow-up investigation. The mean follow-up period was 8.9 (range 3 to 21) years. The mean Achilles tendon total rupture score was 49 ± 27. The summary scores of the physical component and mental components scales of the 36-item Short Form Survey were 43 ± 11 and 52 ± 11, respectively. No significant differences were found among the subpopulations with deep infection, injury to the sural nerve, or repeat rupture. The physical evaluation investigating tendon length and heel rise work revealed a statistically significant difference between the affected and unaffected limb after repeat rupture (p < .01) but not after injury to the sural nerve (p > .05) or deep infection (p > .05). In conclusion, patients with from a complication after acute Achilles tendon rupture had a remarkable reduction of the Achilles tendon total rupture score and physical component scale score at mean follow-up point of 9 years. Patients with repeat rupture had a significant elongation of the tendon and reduction of strength in the affected limb.

Increasing incidence of acute Achilles tendon rupture and a noticeable decline in surgical treatment from 1994 to 2013. A nationwide registry study of 33,160 patients.

PURPOSE: The purpose of this study is to investigate the incidence of acute Achilles tendon rupture in Denmark from 1994 to 2013 with focus on sex, age, geographical areas, seasonal variation and choice of treatment. METHODS: The National Patient Registry was retrospectively searched to find the number of acute Achilles tendon rupture in Denmark during the time period of 1994-2013. Regional population data were retrieved from the services of Statistics Denmark. RESULTS: During the 20-year period, 33,160 ruptures occurred revealing a statistically significant increase in the incidence (p < 0.001, range = 26.95-31.17/100,000/year). Male-to-female ratio was 3:1 and average age 45 years for men and 44 years for women. There was a statistically significant increasing incidence for people over 50 years. A higher incidence in rural compared with urban geographical areas was found, but this was not statistically significant. There was a statistically significant decreasing incidence of patients treated with surgery from 16.9/105 in 1994 to 6.3/105 in 2013. CONCLUSIONS: The incidence of acute Achilles tendon rupture increased from 1994 to 2013 based on increasing incidence in the older population. There was no difference in incidence of acute Achilles tendon rupture in the rural compared with urban geographical areas. A steady decline in surgical treatment was found over the whole period, with a noticeable decline from 2009 to 2013, possibly reflecting a rapid change in clinical practice following a range of high-quality randomized clinical trials (RCT). LEVEL OF EVIDENCE: IV.

Validity and reliability of the Achilles tendon total rupture score.

The best treatment of acute Achilles tendon rupture remains debated. Patient-reported outcome measures have become cornerstones in treatment evaluations. The Achilles tendon total rupture score (ATRS) has been developed for this purpose but requires additional validation. The purpose of the present study was to validate a Danish translation of the ATRS. The ATRS was translated into Danish according to internationally adopted standards. Of 142 patients, 90 with previous rupture of the Achilles tendon participated in the validity study and 52 in the reliability study. The ATRS showed moderately strong correlations with the physical subscores of the Medical Outcomes Study 36-item Short-Form Health Survey (r = .70 to .75; p < .0001) and Victorian Institute of Sports Assessment-Achilles questionnaire (r = .71; p < .0001). Test-retest of the ATRS showed no significant difference in the mean (2.41; p = .07). The limits of agreement were ±18.53. A strong correlation was found between test and retest (intercorrelation coefficient .908); the standard error of measurement was 6.7, and the minimal detectable change was 18.5. The Danish version of the ATRS showed moderately strong criterion validity. For study and follow-up purposes, the ATRS seems reliable for comparisons of groups of patients. Its usability is limited for repeated assessment of individual patients. The development of analysis guidelines would be desirable.