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.
MULTIFILE
Het generalist-plus-specialistische palliatieve zorgmodel wordt wereldwijd onderschreven. In Nederland zijn de competenties en het profiel van de generalistische aanbieder van palliatieve zorg beschreven op alle professionele niveaus in de verpleegkunde en geneeskunde.
MULTIFILE
Objective: The aim of the study was to assess the effectiveness of intensive care unit (ICU)–initiated transitional care interventions for patients and families on elements of post-intensive care syndrome (PICS) and/or PICS-family (PICS–F). Review method used: This is a systematic review and meta-analysis Sources: The authors searched in biomedical bibliographic databases including PubMed, Embase (OVID), CINAHL Plus (EBSCO), Web of Science, and the Cochrane Library and included studies written in English conducted up to October 8, 2020. Review methods: We included (non)randomised controlled trials focussing on ICU-initiated transitional care interventions for patients and families. Two authors conducted selection, quality assessment, and data extraction and synthesis independently. Outcomes were described using the three elements of PICS, which were categorised into (i) physical impairments (pulmonary, neuromuscular, and physical function), (ii) cognitive impairments (executive function, memory, attention, visuo-spatial and mental processing speed), and (iii) psychological health (anxiety, depression, acute stress disorder, post-traumatic stress disorder, and depression). Results: From the initially identified 5052 articles, five studies were included (i.e., two randomised controlled trials and three nonrandomised controlled trials) with varied transitional care interventions. Quality among the studies differs from moderate to high risk of bias. Evidence from the studies shows no significant differences in favour of transitional care interventions on physical or psychological aspects of PICS-(F). One study with a nurse-led structured follow-up program showed a significant difference in physical function at 3 months. Conclusions: Our review revealed that there is a paucity of research about the effectiveness of transitional care interventions for ICU patients with PICS. All, except one of the identified studies, failed to show a significant effect on the elements of PICS. However, these results should be interpreted with caution owing to variety and scarcity of data. Prospero registration: CRD42020136589 (available via https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42020136589).