Decision support tools in low back pain

Development of an International AO Spine Guideline for the Use of Osteobiologics in Anterior Cervical Fusion and Decompression (AO-GO)

STUDY DESIGN

Methodological study for guideline development.

OBJECTIVE

AO Spine Guideline for Using Osteobiologics (AO-GO) project for spine degenerative pathologies was an international, multidisciplinary collaborative initiative to identify and evaluate evidence on existing use of osteobiologics in Anterior Cervical Fusion and Decompression (ACDF). The aim was to formulate precisely defined, clinically relevant and internationally applicable guidelines ensuring evidence-based, safe and effective use of osteobiologics, considering regional preferences and cost-effectiveness.

METHODS

Guideline was completed in two phases: Phase 1- evidence synthesis; Phase 2- recommendation development based on the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) approach. In Phase 1, key questions identified by a panel of experts were addressed in a series of systematic reviews of randomized and non-randomized studies. In Phase 2, the GRADE approach was used to formulate a series of recommendations, including expert panel discussions via web calls and face-to-face meetings.

DISCUSSION

AO-GO aims to bridge an important gap between evidence and use of osteobiologics in spine fusion surgeries. Owing to differences in osteobiologics preparation and functional characteristics, regulatory requirements for approval may vary, therefore it is highly likely that these products enter market without quality clinical trials. With a holistic approach the guideline aims to facilitate evidence-based, patient-oriented decision-making processes in clinical practice, thus stimulating further evidence-based studies regarding osteobiologics usage in spine surgeries. In Phase 3, the guideline will be disseminated and validated using prospectively collected clinical data in a separate effort of the AO Spine Knowledge Forum Degenerative in a global multicenter clinical study.

Current Applications of Machine Learning for Spinal Cord Tumors

Spinal cord tumors constitute a diverse group of rare neoplasms associated with significant mortality and morbidity that pose unique clinical and surgical challenges. Diagnostic accuracy and outcome prediction are critical for informed decision making and can promote personalized medicine and facilitate optimal patient management. Machine learning has the ability to analyze and combine vast amounts of data, allowing the identification of patterns and the establishment of clinical associations, which can ultimately enhance patient care. Although artificial intelligence techniques have been explored in other areas of spine surgery, such as spinal deformity surgery, precise machine learning models for spinal tumors are lagging behind. Current applications of machine learning in spinal cord tumors include algorithms that improve diagnostic precision by predicting genetic, molecular, and histopathological profiles. Furthermore, artificial intelligence-based systems can assist surgeons with preoperative planning and surgical resection, potentially reducing the risk of recurrence and consequently improving clinical outcomes. Machine learning algorithms promote personalized medicine by enabling prognostication and risk stratification based on accurate predictions of treatment response, survival, and postoperative complications. Despite their promising potential, machine learning models require extensive validation processes and quality assessments to ensure safe and effective translation to clinical practice.

Reflection Machines: Supporting Effective Human Oversight Over Medical Decision Support Systems

Human decisions are increasingly supported by decision support systems (DSS). Humans are required to remain "on the loop," by monitoring and approving/rejecting machine recommendations. However, use of DSS can lead to overreliance on machines, reducing human oversight. This paper proposes "reflection machines" (RM) to increase meaningful human control. An RM provides a medical expert not with suggestions for a decision, but with questions that stimulate reflection about decisions. It can refer to data points or suggest counterarguments that are less compatible with the planned decision. RMs think against the proposed decision in order to increase human resistance against automation complacency. Building on preliminary research, this paper will (1) make a case for deriving a set of design requirements for RMs from EU regulations, (2) suggest a way how RMs could support decision-making, (3) describe the possibility of how a prototype of an RM could apply to the medical domain of chronic low back pain, and (4) highlight the importance of exploring an RM's functionality and the experiences of users working with it.

Applications of artificial intelligence in orthopaedic surgery

The practice of medicine is rapidly transforming as a result of technological breakthroughs. Artificial intelligence (AI) systems are becoming more and more relevant in medicine and orthopaedic surgery as a result of the nearly exponential growth in computer processing power, cloud based computing, and development, and refining of medical-task specific software algorithms. Because of the extensive role of technologies such as medical imaging that bring high sensitivity, specificity, and positive/negative prognostic value to management of orthopaedic disorders, the field is particularly ripe for the application of machine-based integration of imaging studies, among other applications. Through this review, we seek to promote awareness in the orthopaedics community of the current accomplishments and projected uses of AI and ML as described in the literature. We summarize the current state of the art in the use of ML and AI in five key orthopaedic disciplines: joint reconstruction, spine, orthopaedic oncology, trauma, and sports medicine.

An Evolution Gaining Momentum—The Growing Role of Artificial Intelligence in the Diagnosis and Treatment of Spinal Diseases

In recent years, applications using artificial intelligence have been gaining importance in the diagnosis and treatment of spinal diseases. In our review, we describe the basic features of artificial intelligence which are currently applied in the field of spine diagnosis and treatment, and we provide an orientation of the recent technical developments and their applications. Furthermore, we point out the possible limitations and challenges in dealing with such technological advances. Despite the momentary limitations in practical application, artificial intelligence is gaining ground in the field of spine treatment. As an applying physician, it is therefore necessary to engage with it in order to benefit from those advances in the interest of the patient and to prevent these applications being misused by non-medical partners.

Multidisciplinary integrative care versus chiropractic care for low back pain: a randomized clinical trial

BACKGROUND

Low back pain (LBP) is influenced by interrelated biological, psychological, and social factors, however current back pain management is largely dominated by one-size fits all unimodal treatments. Team based models with multiple provider types from complementary professional disciplines is one way of integrating therapies to address patients' needs more comprehensively.

METHODS

This parallel group randomized clinical trial conducted from May 2007 to August 2010 aimed to evaluate the relative clinical effectiveness of 12 weeks of monodisciplinary chiropractic care (CC), versus multidisciplinary integrative care (IC), for adults with sub-acute and chronic LBP. The primary outcome was pain intensity and secondary outcomes were disability, improvement, medication use, quality of life, satisfaction, frequency of symptoms, missed work or reduced activities days, fear avoidance beliefs, self-efficacy, pain coping strategies and kinesiophobia measured at baseline and 4, 12, 26 and 52 weeks. Linear mixed models were used to analyze outcomes.

RESULTS

201 participants were enrolled. The largest reductions in pain intensity occurred at the end of treatment and were 43% for CC and 47% for IC. The primary analysis found IC to be significantly superior to CC over the 1-year period (P = 0.02). The long-term profile for pain intensity which included data from weeks 4 through 52, showed a significant advantage of 0.5 for IC over CC (95% CI 0.1 to 0.9; P = 0.02; 0 to 10 scale). The short-term profile (weeks 4 to 12) favored IC by 0.4, but was not statistically significant (95% CI - 0.02 to 0.9; P = 0.06). There was also a significant advantage over the long term for IC in some secondary measures (disability, improvement, satisfaction and low back symptom frequency), but not for others (medication use, quality of life, leg symptom frequency, fear avoidance beliefs, self-efficacy, active pain coping, and kinesiophobia). Importantly, no serious adverse events resulted from either of the interventions.

CONCLUSIONS

Participants in the IC group tended to have better outcomes than the CC group, however the magnitude of the group differences was relatively small. Given the resources required to successfully implement multidisciplinary integrative care teams, they may not be worthwhile, compared to monodisciplinary approaches like chiropractic care, for treating LBP. Trial registration NCT00567333.

Which Chronic Low Back Pain Patients Respond Favorably to Yoga, Physical Therapy, and a Self-care Book? Responder Analyses from a Randomized Controlled Trial

PURPOSE

To identify baseline characteristics of adults with chronic low back pain (cLBP) that predict response (i.e., a clinically important improvement) and/or modify treatment effect across three nonpharmacologic interventions.

DESIGN

Secondary analysis of a randomized controlled trial.

SETTING

Academic safety net hospital and seven federally qualified community health centers.

SUBJECTS

Adults with cLBP (N = 299).

METHODS

We report patient characteristics that were predictors of response and/or modified treatment effect across three 12-week treatments: yoga, physical therapy [PT], and a self-care book. Using preselected characteristics, we used logistic regression to identify predictors of "response," defined as a ≥30% improvement in the Roland Morris Disability Questionnaire. Then, using "response" as our outcome, we identified baseline characteristics that were treatment effect modifiers by testing for statistical interaction (P < 0.05) across two comparisons: 1) yoga-or-PT vs self-care and 2) yoga vs PT.

RESULTS

Overall, 39% (116/299) of participants were responders, with more responders in the yoga-or-PT group (42%) than the self-care (23%) group. There was no difference in proportion responding to yoga (48%) vs PT (37%, odds ratio [OR] = 1.5, 95% confidence interval = 0.88 - 2.6). Predictors of response included having more than a high school education, a higher income, employment, few depressive symptoms, lower perceived stress, few work-related fear avoidance beliefs, high pain self-efficacy, and being a nonsmoker. Effect modifiers included use of pain medication and fear avoidance beliefs related to physical activity (both P = 0.02 for interaction). When comparing yoga or PT with self-care, a greater proportion were responders among those using pain meds (OR = 5.3), which differed from those not taking pain meds (OR = 0.94) at baseline. We also found greater treatment response among those with lower (OR = 7.0), but not high (OR = 1.3), fear avoidance beliefs around physical activity.

CONCLUSIONS

Our findings revealed important subgroups for whom referral to yoga or PT may improve cLBP outcomes.

Psychological outcomes, knowledge and preferences of pregnant women on first-trimester screening for fetal structural abnormalities: A prospective cohort study

INTRODUCTION

The primary aim of this study is to investigate the impact of a 13-week anomaly scan on the experienced levels of maternal anxiety and well-being. Secondly, to explore women's knowledge on the possibilities and limitations of the scan and the preferred timing of screening for structural abnormalities.

MATERIAL AND METHODS

In a prospective-cohort study conducted between 2013-2015, pregnant women in the North-Netherlands underwent a 13-week anomaly scan. Four online-questionnaires (Q1, Q2, Q3 and Q4) were completed before and after the 13- and the 20-week anomaly scans. In total, 1512 women consented to participate in the study and 1118 (74%) completed the questionnaires at Q1, 941 (64%) at Q2, 807 (55%) at Q3 and 535 (37%) at Q4. Psychological outcomes were measured by the state-trait inventory-scale (STAI), the patient's positive-negative affect (PANAS) and ad-hoc designed questionnaires.

RESULTS

Nine-nine percent of women wished to be informed as early as possible in pregnancy about the absence/presence of structural abnormalities. In 87% of women levels of knowledge on the goals and limitations of the 13-week anomaly scan were moderate-to-high. In women with a normal 13-week scan result, anxiety levels decreased (P < .001) and well-being increased over time (P < .001). In women with false-positive results (n = 26), anxiety levels initially increased (STAI-Q1: 39.8 vs. STAI-Q2: 48.6, P = 0.025), but later decreased around the 20-week anomaly scan (STAI-Q3: 36.4 vs. STAI-Q4: 34.2, P = 0.36).

CONCLUSIONS

The 13-week scan did not negatively impact the psychological well-being of pregnant women. The small number of women with screen-positive results temporarily experienced higher anxiety after the scan but, in false-positive cases, anxiety levels normalized again when the abnormality was not confirmed at follow-up scans. Finally, most pregnant women have moderate-to-high levels of knowledge and strongly prefer early screening for fetal structural abnormalities.

Artificial intelligence facilitates decision-making in the treatment of lumbar disc herniations

PURPOSE

Apart from patients with severe neurological deficits, it is not clear whether surgical or conservative treatment of lumbar disc herniations is superior for the individual patient. We investigated whether deep learning techniques can predict the outcome of patients with lumbar disc herniation after 6 months of treatment.

METHODS

The data of 60 patients were used to train and test a deep learning algorithm with the aim to achieve an accurate prediction of the ODI 6 months after surgery or the start of conservative therapy. We developed an algorithm that predicts the ODI of 6 randomly selected test patients in tenfold cross-validation.

RESULTS

A 100% accurate prediction of an ODI range could be achieved by dividing the ODI scale into 12% sections. A maximum absolute difference of only 3.4% between individually predicted and actual ODI after 6 months of a given therapy was achieved with our most powerful model. The application of artificial intelligence as shown in this work also allowed to compare the actual patient values after 6 months with the prediction for the alternative therapy, showing deviations up to 18.8%.

CONCLUSION

Deep learning in the supervised form applied here can identify patients at an early stage who would benefit from conservative therapy, and on the contrary avoid painful and unnecessary delays for patients who would profit from surgical therapy. In addition, this approach can be used in many other areas of medicine as an effective tool for decision-making when choosing between opposing treatment options, despite small patient groups.

Treatment based classification systems for patients with non-specific neck pain. A systematic review

OBJECTIVE

We aimed to identify published classification systems with a targeted treatment approach (treatment-based classification systems (TBCSs)) for patients with non-specific neck pain, and assess their quality and effectiveness.

DESIGN

Systematic review.

DATA SOURCES

MEDLINE, CINAHL, EMBASE, PEDro and the grey literature were systematically searched from inception to December 2019.

STUDY APPRAISAL AND SYNTHESIS

The main selection criterium was a TBCS for patients with non-specific neck pain with physiotherapeutic interventions. For data extraction of descriptive data and quality assessment we used the framework developed by Buchbinder et al. We considered as score of ≤3 as low quality, a score between 3 and 5 as moderate quality and a score ≥5 as good quality. To assess the risk of bias of studies concerning the effectiveness of TBCSs (only randomized clinical trials (RCTs) were included) we used the PEDro scale. We considered a score of ≥ six points on this scale as low risk of bias.

RESULTS

Out of 7664 initial references we included 13 studies. The overall quality of the TBCSs ranged from low to moderate. We found two RCTs, both with low risk of bias, evaluating the effectiveness of two TBCSs compared to alternative treatments. The results showed that both TBCSs were not superior to alternative treatments.

CONCLUSION

Existing TBCSs are, at best, of moderate quality. In addition, TBCSs were not shown to be more effective than alternatives. Therefore using these TBCSs in daily practice is not recommended.

Shared decision making by United Kingdom osteopathic students: an observational study using the OPTION-12 instrument

Background

At the crux of patient centred care is Shared Decision Making (SDM), which benefits patient and practitioner. Despite external pressures, studies indicate that SDM remains poorly practised across a variety of healthcare professions. The degree of SDM engagement within United Kingdom osteopathic undergraduate teaching clinics is currently unknown.

Methods

In 2014 we used the reliable and validated OPTION-12 (O12) instrument to calculate a score that reflected the degree of SDM utility in one United Kingdom Osteopathic Educational Institute’s teaching clinic. We also aimed to compare these scores with those previously obtained for physiotherapists working within the United Kingdom’s National Health Service. Student-patient initial and follow-up encounters were audio recorded, transcribed and scored using the O12. Comparisons between the following O12 scores were performed: the Osteopathic Educational Institute’s 4th and 3rd year students; the Osteopathic Educational Institute’s student’s initial and follow-up patient encounters; the Osteopathic Educational Institute’s students and National Health Service physiotherapists.

Results

We analysed 35.5 h of transcribed data from 30 student-patient encounters (7 initial: 23 follow-up). An O12 score of 0.6% (range 0–10.4%) was calculated. No significant differences were found between year groups or encounter types. Significant differences were found compared to National Health Service physiotherapist (score = 24.4%): (U = 144, z = 4.25, p < 0.0005); although both scores are below the 60% threshold for competent SDM behaviour.

Conclusions

Undergraduate osteopaths did not appear to engage in competent SDM behaviours, implying traditional and paternalistic styles of decision making that align with results from other manual therapy professions. Students in this study did not practise competent SDM behaviours. Effective educational strategies are required to ensure SDM behaviours reach competent levels.

Artificial intelligence and machine learning in spine research

Artificial intelligence (AI) and machine learning (ML) techniques are revolutionizing several industrial and research fields like computer vision, autonomous driving, natural language processing, and speech recognition. These novel tools are already having a major impact in radiology, diagnostics, and many other fields in which the availability of automated solution may benefit the accuracy and repeatability of the execution of critical tasks. In this narrative review, we first present a brief description of the various techniques that are being developed nowadays, with special focus on those used in spine research. Then, we describe the applications of AI and ML to problems related to the spine which have been published so far, including the localization of vertebrae and discs in radiological images, image segmentation, computer-aided diagnosis, prediction of clinical outcomes and complications, decision support systems, content-based image retrieval, biomechanics, and motion analysis. Finally, we briefly discuss major ethical issues related to the use of AI in healthcare, namely, accountability, risk of biased decisions as well as data privacy and security, which are nowadays being debated in the scientific community and by regulatory agencies.