Checklist for robust methodology and statistical analyses?

Recent editorial in the CORR was about EQUATOR guidelines and the editors write: Since reporting guidelines rely on consensual scientific principles and evidence-based research, consulting them before beginning a project will tend to cause clinician scientists to consider why an element of a checklist is included; doing so inevitably results in discussion and consideration of […]

Machine learning algorithm for correlation analysis – Yes!

I have a PubMed alert for studies involving search with “machine learning”. This study was included in the search list recently: “One-year Follow-Up Results with Hydrogel Implant in Therapy of Hallux Rigidus: Case Series with 44 Patients“. That really stood out. But yes, they indeed used machine learning algorithm to investigate risk factors for treatment […]

Methodological aspects for future in the TJR research

Cuthbert et al. published a study in CORR titled “What Is the Effect of Using a competing-risks Estimator when Predicting Survivorship After Joint Arthroplasty: A Comparison of Approaches to Survivorship Estimation in a Large Registry“. They recommend using competing risk approach when assessing long-term survival of total joint replacements. This is of course an important […]

Mesmerized by clinical prediction models

I am not a surgical oncologist but I came across with this study:  A deep survival interpretable radiomics model of hepatocellular carcinoma patients. Authors conclude: In summary, novel deep radiomic analysis provides improved performance for risk assessment of HCC prognosis compared with Cox survival models and may facilitate stratification of HCC patients and personalization of […]

Problems in all-cause revision analyses in total joint replacement research?

I had a chance to collaborate with Nordic Arthroplasty Register Association in a study published in the Acta Orthopaedica last year. Study was titled “The effect of fixation type on the survivorship of contemporary total knee arthroplasty in patients younger than 65 years of age: a register-based study of 115,177 knees in the Nordic Arthroplasty […]

It´s all about explained variation in the periprosthetic joint infections

I showed this slide in my clinic meeting presentation which was about periprosthetic joint infections. Infection rates were very high in the early years of modern total joint replacement surgery in 1960s. Today, the risk of deep infection after a total hip or knee replacement surgery is something close to 1%. This major improvement is […]

Basics of artificial intelligence and machine learning for every trainee?

This was an interesting perspective: What Should Radiology Residency and Fellowship Training in Artificial Intelligence Include? A Trainee’s Perspective—Radiology In Training. Just some take from the commentary: Trainees should be introduced to the basic concepts of data collection, annotation, and algorithm validation. AI and ML are here to stay. Hence it is important that these […]

No difference and type II error – a guideline?

Domb and Sebatian discuss about type II error in a “Level V guideline“. Among other things they conclude: Type II errors may be present in greater than 20% of studies that fail to find statistically significant differences. Incorrectly concluding that there is no difference in such studies poses a danger to the advancement of clinical practice, and indeed […]

Orthopaedic prediction models are getting there!

Purely predictive studies are becoming more common also in the orthopaedics. Unfortunately they have quite often very poor methodology and do not give much insight to actual prediction problems. Hence it was great to read the study by Schaefer et al. in Clinical Orthopaedics and Related Research. Their study was titled “What Factors Predict Adverse […]