Artificial Intelligence (AI) is becoming more powerful but is barely used to counter the growth in health care burden. AI applications to increase efficiency in orthopedics are rare. We questioned if (1) we could train machine learning (ML) algorithms, based on answers from digitalized history taking questionnaires, to predict treatment of hip osteoartritis (either conservative or surgical); (2) such an algorithm could streamline clinical consultation.

Multiple ML models were trained on 600 annotated (80% training, 20% test) digital history taking questionnaires, acquired before consultation. Best performing models, based on balanced accuracy and optimized automated hyperparameter tuning, were build into our daily clinical orthopedic practice. Fifty patients with hip complaints (>45 years) were prospectively predicted and planned (partly blinded, partly unblinded) for consultation with the physician assistant (conservative) or orthopedic surgeon (operative). Tailored patient information based on the prediction was automatically sent to a smartphone app. Level of evidence: IV.

Random Forest and BernoulliNB were the most accurate ML models (0.75 balanced accuracy). Treatment prediction was correct in 45 out of 50 consultations (90%), p<0.0001 (sign and binomial test). Specialized consultations where conservatively predicted patients were seen by the physician assistant and surgical patients by the orthopedic surgeon were highly appreciated and effective.

Treatment strategy of hip osteoartritis based on answers from digital history taking questionnaires was accurately predicted before patients entered the hospital. This can make outpatient consultation scheduling more efficient and tailor pre-consultation patient education.

Background: One of the disadvantages of the Impact Factor (IF) is self-citation. The SCImago Journal Rank (SJR) indicator excludes self-citations and incorporates quality of citations that a journal receives by other journals, rather than absolute numbers. This study re-evaluated self-citation influence on the 2007 IF for 17 major orthopaedic journals and the difference in ranking using IF or SJR was investigated.

Methods: Divided in a general (n = 8) and specialized (n = 9) group, all journals were analysed for self-citation rate, self-cited rate and citation density. Rankings of the 17 journals for IF and SJR were determined and the difference in ranking was calculated.

Results: Specialized journals had higher self-citation rates (p = 0.05), self-cited rates (p = 0.003) and lower citation-densities (p = 0.01). Both groups correlated for self-citation rate and impact factor (general: r = 0.85 ; p = 0.008) (specialized: r = 0.71 ; p = 0.049).

When ranked for SJR instead of IF, five journals maintained rank, six improved their rank and six experienced a decline in rank. Biggest differences were seen for BMC MD (+7 places) and CORR (− 4 places). Group-analyses for the IF (general: 7.50 – 95%CI 3.19 to 11.81) (specialized: 10.33 – 95%CI 6.61 to 14.06) (p = 0.26), SJR (general: 6.63 – 95%CI 2.66 to 10.60) (specialized: 11.11 – 95%CI 7.62 to 14.60) (p = 0.07) and the difference between both rankings (general: 0.88 – 95%CI –1.75 to 3.50) (specialized: − 0.78 – 95%CI –2.20 to 0.65) (p = 0.20), showed an enhanced underestimation of sub-specialist journals.

Conclusion: Citation analysis shows that general journals tend to use more citations per published article and a larger portion of self-citations constitutes citations of sub-specialist journals compared to more general journals. The SJR excludes the influence of self-citation and awarded prestige by the SJR implies a different quality-evaluation for most orthopaedic journals. A disadvantage using this indicator, is an enhanced effect of underestimation of sub-specialist journals.