Search results

Development and internal validation of a machine learning prediction model for low back pain non-recovery in patients with an acute episode consulting a physiotherapist in primary care

Background While low back pain occurs in nearly everybody and is the leading cause of disability worldwide, we lack instruments to accurately predict persistence of acute low back pain. We aimed to develop and internally validate a machine learning model predicting non-recovery in acute low back pain and to compare this with current practice and ‘traditional’ prediction modeling. Methods Prognostic cohort-study in primary care physiotherapy. Patients (n = 247) with acute low back pain (= one month) consulting physiotherapists were included. Candidate predictors were assessed by questionnaire at baseline and (to capture early recovery) after one and two weeks. Primary outcome was non-recovery after three months, defined as at least mild pain (Numeric Rating Scale > 2/10). Machine learning models to predict non-recovery were developed and internally validated, and compared with two current practices in physiotherapy (STarT Back tool and physiotherapists’ expectation) and ‘traditional’ logistic regression analysis. Results Forty-seven percent of the participants did not recover at three months. The best performing machine learning model showed acceptable predictive performance (area under the curve: 0.66). Although this was no better than a’traditional’ logistic regression model, it outperformed current practice. Conclusions We developed two prognostic models containing partially different predictors, with acceptable performance for predicting (non-)recovery in patients with acute LBP, which was better than current practice. Our prognostic models have the potential of integration in a clinical decision support system to facilitate data-driven, personalized treatment of acute low back pain, but needs external validation first.

Modeling scientific research articles

We review over 10 years of research at Elsevier and various Dutch academic institutions on establishing a new format for the scientific research article. Our work rests on two main theoretical principles: the concept of modular documents, consisting of content elements that can exist and be published independently and are linked by meaningful relations, and the use of semantic data standards allowing access to heterogeneous data. We discuss the application of these concepts in five different projects: a modular format for physics articles, an XML encyclopedia in pharmacology, a semantic data integration project, a modular format for computer science proceedings papers, and our current work on research articles in cell biology.

ACL research retreat VII

The seventh ACL Research Retreat was held March 19–21, 2015, in Greensboro, North Carolina. The retreat brought together clinicians and researchers to present and discuss the most recent advances in anterior cruciate ligament (ACL) injury epidemiology, risk factor identification, and injury risk screening and prevention strategies. Subsequently, our goal was to identify important unknowns and future research directions. The ACL Research Retreat VII was attended by 64 clinicians and researchers from Australia, Canada, India, Ireland, the Netherlands, South Africa, the United States, and the United Kingdom. The meeting featured 3 keynote and 29 podium presentations highlighting recent research. Keynotes were delivered by Bruce Beynnon, PhD (Univer- sity of Vermont), Charles ‘‘Buz’’ Swanik, PhD, ATC (University of Delaware), and Mark Paterno, PhD, PT, ATC, SCS (Cincinnati Children’s Hospital Medical Cen- ter), addressing their ongoing work related to sex-specific multivariate risk factor models for ACL injury,1 the role of the brain in noncontact ACL injury,2 and the incidence and predictors of a second ACL injury after primary ACL reconstruction and return to sport,3 respectively. Podium and poster presentations were organized into thematic sessions of prospective and case-control risk factor studies, anatomical and hormonal risk factors, neuromuscular and biomechanical risk factors, injury risk assessment after ACL injury, and injury-prevention strategies. Time was provided for group discussion throughout the conference. At the end of the meeting, attendees participated in 1 of 3 breakout sessions on the topics of genetic, hormonal, and anatomical risk factors; neuromechanical contributions to ACL injury; and risk factor screening and prevention. From these discussions, we updated the 2012 consensus state- ment4 to reflect the most recent advances in the field and to revise the important unknowns and future directions necessary to enhance our understanding of ACL injury. Following are the updated consensus statement, keynote presentation summaries, and free communication abstracts organized by topic and presentation order.

Cerebral activations related to audition-driven performance imagery in professional musicians

Functional Magnetic Resonance Imaging (fMRI) was used to study the activation of cerebral motor networks during auditory perception of music in professional keyboard musicians (n=12). The activation paradigm implied that subjects listened to two-part polyphonic music, while either critically appraising the performance or imagining they were performing themselves. Two-part polyphonic audition and bimanual motor imagery circumvented a hemisphere bias associated with the convention of playing the melody with the right hand. Both tasks activated ventral premotor and auditory cortices, bilaterally, and the right anterior parietal cortex, when contrasted to 12 musically unskilled controls. Although left ventral premotor activation was increased during imagery (compared to judgment), bilateral dorsal premotor and right posterior-superior parietal activations were quite unique to motor imagery. The latter suggests that musicians not only recruited their manual motor repertoire but also performed a spatial transformation from the vertically perceived pitch axis (high and low sound) to the horizontal axis of the keyboard. Imagery-specific activations in controls were seen in left dorsal parietal-premotor and supplementary motor cortices. Although these activations were less strong compared to musicians, this overlapping distribution indicated the recruitment of a general 'mirror-neuron' circuitry. These two levels of sensori-motor transformations point towards common principles by which the brain organizes audition-driven music performance and visually guided task performance.

Research methods - how to write a research question

Improving provider-initiated testing for HIV and other STI in the primary care setting in Amsterdam, the Netherlands

Background In the Netherlands, general practitioners (GPs) play a key role in HIV testing. However, the proportion of people diagnosed with late-stage HIV remains high, and opportunities for earlier diagnosis are being missed. We implemented an educational intervention to improve HIV and STI testing in primary care in Amsterdam, the Netherlands. Methods GPs were invited to participate in an educational program between 2015 and 2020, which included repeat sessions using audit and feedback and quality improvement plans. Data on HIV, chlamydia and gonorrhoea testing by GPs were collected from 2011 through 2020. The primary outcome was HIV testing frequency, which was compared between GPs before and after participation using Poisson regression. Secondary outcomes were chlamydia and gonorrhoea testing frequencies, and positive test proportions. Additional analyses stratified by patient sex and age were done. Findings GPs after participation performed 7% more HIV tests compared to GPs before participation (adjusted relative ratio [aRR] 1.07, 95%CI 1.04–1.09); there was no change in the proportion HIV positive tests (aRR 0.87, 95%CI 0.63–1.19). HIV testing increased most among patients who were female and ≤19 or 50–64 years old. After participation, HIV testing continued to increase (aRR 1.02 per quarter, 95%CI 1.01–1.02). Chlamydia testing by GPs after participation increased by 6% (aRR 1.06, 95%CI 1.05–1.08), while gonorrhoea testing decreased by 2% (aRR 0.98, 95%CI 0.97–0.99). We observed increases specifically in extragenital chlamydia and gonorrhoea testing. Conclusions The intervention was associated with a modest increase in HIV testing among GPs after participation, while the proportion positive HIV tests remained stable. Our results suggest that the intervention yielded a sustained effect.