BACK-to-MOVE: Machine learning and computer vision model automating clinical classification of non-specific low back pain for personalised management.

BACKGROUND: Low back pain (LBP) is a major global disability contributor with profound health and socio-economic implications. The predominant form is non-specific LBP (NSLBP), lacking treatable pathology. Active physical interventions tailored to individual needs and capabilities are crucial for its management. However, the intricate nature of NSLBP and complexity of clinical classification systems necessitating extensive clinical training, hinder customised treatment access. Recent advancements in machine learning and computer vision demonstrate promise in characterising NSLBP altered movement patters through wearable sensors and optical motion capture. This study aimed to develop and evaluate a machine learning model (i.e., 'BACK-to-MOVE') for NSLBP classification trained with expert clinical classification, spinal motion data from a standard video alongside patient-reported outcome measures (PROMs). METHODS: Synchronised video and three-dimensional (3D) motion data was collected during forward spinal flexion from 83 NSLBP patients. Two physiotherapists independently classified them as motor control impairment (MCI) or movement impairment (MI), with conflicts resolved by a third expert. The Convolutional Neural Networks (CNNs) architecture, HigherHRNet, was chosen for effective pose estimation from video data. The model was validated against 3D motion data (subset of 62) and trained on the freely available MS-COCO dataset for feature extraction. The Back-to-Move classifier underwent fine-tuning through feed-forward neural networks using labelled examples from the training dataset. Evaluation utilised 5-fold cross-validation to assess accuracy, specificity, sensitivity, and F1 measure. RESULTS: Pose estimation's Mean Square Error of 0.35 degrees against 3D motion data demonstrated strong criterion validity. Back-to-Move proficiently differentiated MI and MCI classes, yielding 93.98% accuracy, 96.49% sensitivity (MI detection), 88.46% specificity (MCI detection), and an F1 measure of .957. Incorporating PROMs curtailed classifier performance (accuracy: 68.67%, sensitivity: 91.23%, specificity: 18.52%, F1: .800). CONCLUSION: This study is the first to demonstrate automated clinical classification of NSLBP using computer vision and machine learning with standard video data, achieving accuracy comparable to expert consensus. Automated classification of NSLBP based on altered movement patters video-recorded during routine clinical examination could expedite personalised NSLBP rehabilitation management, circumventing existing healthcare constraints. This advancement holds significant promise for patients and healthcare services alike.

Correlation between the Severity of the Lumbar Degenerative Disease and Sagittal Spinopelvic Alignment / Correlação entre a gravidade da doença degenerativa lombar e o alinhamento espinopélvico

Abstract Objective To evaluate the impact of the severity of lumbar degenerative disease (LDD) on sagittal spinopelvic alignment. Methods In total, 130 patients (mean age: 57 years; 75% female) with LDD-associated low-back pain were prospectively included. The severity of the LDD was defined by the following findings on anteroposterior and lateral lumbar spine radiographs: osteophytosis; loss of of height of the intervertebral disc; terminal vertebral plate sclerosis; number of affected segments; deformities; and objective instability. The disease was classified as follows: grade 0-absence of signs of LDD in the lumbar spine; grade I - signs of LDD in up to two segments; grade II - three or more segments involved; grade III - association with scoliosis, spondylolisthesis, or laterolisthesis. Spinopelvic radiographic parameters, including pelvic incidence (PI), lumbar lordosis (LL), discrepancy between the PI and LL (PI-LL), pelvic tilt (PT), and sagittal vertical axis (SVA), were analyzed according to the LDD grades. Results The radiographic parameters differed according to the LDD grades; grade-III patients presented higher SVA (p= 0.001) and PT (p= 0.0005) values, denoting greater anterior inclination of the trunk and pelvic retroversion when compared to grade-0 andgrade-I subjects. In addition, grade-III patients had higher PI-LL values, which indicates loss of PI-related lordosis, than grade-I subjects (p= 0.04). Conclusion Patients with more severe LDD tend to present greater spinopelvic sagittal misalignment compared to patients with a milder disease.

Resumo Objetivo Avaliar o impacto da graduação da doença degenerativa lombar (DDL) sobre o alinhamento sagital espinopélvico. Métodos Ao todo, 130 pacientes (dade média: 57 anos; 75% do sexo feminino) com dor lombar associada a DDL foram prospectivamente incluídos. A gravidade da DDL foi definida pelos seguintes achados nas radiografias anteroposterior e de perfil da coluna lombar: osteofitose; perda de altura do disco intervertebral; esclerose na placa vertebral terminal; número de segmentos afetados; deformidades; e instabilidade objetiva. Os pacientes foram graduados segundo a DDL da seguinte maneira: grau 0-ausência de sinais de DDL na coluna lombar; grau I - sinais de DDL em até dois segmentos; grau II - envolvimento em três ou mais segmentos; grau III - quando associada a escoliose, espondilolistese ou laterolistese. Parâmetros radiográficos espinopélvicos, como incidência pélvica (IP), lordose lombar (LL), discrepância entre a IP e a LL (IP-LL), versão pélvica (VP), e eixo vertical sagital (EVS) foram analisados de acordo com os graus de DDL. Resultados Houve diferença nos parâmetros radiográficos comparando-se os graus de DDL, com os pacientes de grau III apresentando maiores valores de EVS (p= 0,001) e VP (p= 0,0005), o que denota maior inclinação anterior do tronco e maior retroversão pélvica do que os pacientes de graus 0 e I. Pacientes de grau III também apresentaram maiores valores de IP-LL, o que denota perda da lordose relativa ao valor da IP, do que pacientes grau I (p= 0,04). Conclusão Pacientes com DDL mais grave demonstraram uma tendência a maior desalinhamento sagital espinopélvico comparados com pacientes com graus mais leves.

Diagnostic codes for low back pain, nomenclature or noise? A descriptive study of disease classification system coding of low back pain.

AIM: To compare and contrast the diagnostic codes for spinal causes of low back pain (LBP) in 3 disease classification systems (International Classification of Diseases [ICD]-10, International Classification of Primary Care [ICPC]-2 PLUS and Systematized Nomenclature of Medicine Clinical Terms - Australia [SNOMED CT-AU]) and consider how well they are aligned with the diagnostic approach recommended in contemporary clinical practice guidelines for LBP. METHOD: This was a descriptive study which included 3 disease classification systems: ICD-10, ICPC-2 PLUS and SNOMED CT-AU. Two independent authors extracted relevant LBP codes from each system and mapped the codes to 3 guideline-endorsed categories of spine-related diagnoses for LBP (specific spinal pathology, radicular syndromes, and non-specific LBP) and the various clinical conditions (sub-categories) within each of the 3 categories. RESULTS: ICD-10, ICPC-2 PLUS, and SNOMED CT-AU had 126, 118 and 100 codes for LBP, respectively. All systems provided codes that would cover the 3 guideline-endorsed categories of spine-related diagnoses for LBP. On the basis of contemporary guidelines, the authors developed lists of discrete sub-categories of specific spinal pathology (56 sub-categories), radicular syndromes (7 sub-categories), and non-specific LBP (10 sub-categories). Each of the classification systems was then mapped against these sub-categories to tally redundancy and determine exhaustiveness. However, no system covered all 73 sub-categories of LBP, and within each system, there was substantial redundancy with up to 22 codes for the same clinical condition. CONCLUSION: LBP diagnostic codes used in popular disease classification systems are out of touch with current approaches to diagnosis, as reflected in contemporary LBP guidelines. Our findings suggest these disease classification systems need revision, but precisely how they should be revised is unclear.

Classification of Geriatric Low Back Pain Based on Hip Characteristics With a 12-Month Longitudinal Exploration of Clinical Outcomes: Findings From Delaware Spine Studies.

OBJECTIVE: The purpose of this study is to identify geriatric chronic low back pain (LBP) subgroups based on the presence of potentially modifiable hip impairments, using Latent Variable Mixture Modeling (LVMM), and to examine the prospective relationship between these subgroups and key outcomes over time. METHODS: Baseline, 3-month, 6-month, and 12-month data were collected from a prospective cohort of 250 community-dwelling older adults with chronic LBP. Comprehensive hip (symptoms, strength, range of motion, and flexibility), LBP (intensity and disability), and mobility function (gait speed and 6-Minute Walk Test) examinations were performed at each timepoint. Baseline hip measures were included in LVMM; observed classes/subgroups were compared longitudinally on LBP and mobility function outcomes using mixed models. RESULTS: Regarding LVMM, a model with 3 classes/subgroup fit best. Broadly speaking, subgroups were differentiated best by hip strength and symptom presence: subgroup 1 = strong and nonsymptomatic, subgroup 2 = weak and nonsymptomatic, and subgroup 3 = weak and symptomatic (WS). Regarding longitudinal mixed models, all subgroups improved in most outcomes over time. Specifically, over 12 months, the nonsymptomatic subgroups had lower LBP intensity and disability levels compared with the WS subgroup, whereas the strong and nonsymptomatic subgroup had better mobility function than the 2 "weak" subgroups. CONCLUSION: These subgroup classifications may help in tailoring specific interventions in future trials. Special attention should be given to the WS subgroup given their consistently poor LBP and mobility function outcomes. IMPACT: Among older adults with chronic low back pain, there are 3 hip subgroups: "strong and nonsymptomatic," "weak and nonsymptomatic," and "weak and symptomatic." People in these subgroups demonstrate different outcomes and require different treatment; proper identification will result in tailored interventions designed to benefit individual patients. In particular, people in the WS subgroup deserve special attention, because their outcomes are consistently poorer than those in the other subgroups.

Distinguishing chronic low back pain in young adults with mild to moderate pain and disability using trunk compliance.

Chronic low back pain (cLBP) rates among younger individuals are rising. Although pain and disability are often less severe, underlying changes in trunk behavior may be responsible for recurrence. We examine the biomarker capacity of a simple Trunk Compliance Index (TCI) to distinguish individuals with and without cLBP. A random subset (n = 49) of the RELIEF RCT were matched to healthy controls for sex, age, height and weight. We measured TCI (as displacement/ weight-normalized perturbation force) using anthropometrically-matched, suddenly-applied pulling perturbations to the trunk segment, randomized across three planes of motion (antero-posterior, medio-lateral, and rotational). Mean differences between cLBP, sex and perturbation direction were assessed with repeated-measures analysis of variance. Discriminatory accuracy of TCI was assessed using Receiver Operator Characteristic (ROC) analysis. Baseline characteristics between groups were equivalent (x̅ [range]): sex (57% female / group), age (23.0 [18-45], 22.8 [18-45]), height, cm (173.0 [156.5-205], 171.3 [121.2-197], weight, kg (71.8 [44.5-116.6], 71.7 [46.8-117.5]) with cLBP associated with significantly lower TCI for 5 of 6 directions (range mean difference, - 5.35: - 1.49, range 95% CI [- 6.46: - 2.18 to - 4.35: - 0.30]. Classification via ROC showed that composite TCI had high discriminatory potential (area under curve [95% CI], 0.90 [0.84-0.96]), driven by TCI from antero-posterior perturbations (area under curve [95% CI], 0.99 [0.97-1.00]). Consistent reductions in TCI suggests global changes in trunk mechanics that may go undetected in classic clinical examination. Evaluation of TCI in younger adults with mild pain and disability may serve as a biomarker for chronicity, leading to improved preventative measures in cLBP.Trial Registration and Funding RELIEF is registered with clinicaltrials.gov (NCT01854892) and funded by the NIH National Center for Complementary & Integrative Health (R01AT006978).

Distribution and imaging characteristics of spina bifida occulta in young people with low back pain: a retrospective cross-sectional study.

PURPOSE: Spina bifida occulta (SBO) is one of the most common congenital spinal deformities. Although many studies have demonstrated the influence of lumbosacral dysplasia on low back pain (LBP) in young athletes, there have been few studies on SBO among young people in other occupations. The purpose of this study is to investigate the distribution of SBO in young people with LBP and to classify SBO from the perspective of lamina development. METHODS: The X-ray films of 148 young patients with LBP were analyzed to quantify the distribution of SBO and classify abnormal laminae. RESULTS: Of the 148 patients, 93 (61.49%) had SBO: 83 cases involved S1 alone, 2 involved L5-S1, 5 involved S1-2, 2 involved S1-4, and 1 involved L4-S4. According to the degree of the defect, the patients with SBO were divided on the basis of five grades: 9 patients with grade I, 53 with grade II, 23 with grade III, and 8 with grade IV. The cases were classified by the shape of the laminae into 4 types: 15 cases of type a, 11 cases of type b, 37 cases of type c, and 30 cases of type d. CONCLUSION: Among the young people with LBP that we surveyed, SBO is the most common lumbosacral dysplasia, which frequently involves the S1 segment. Most laminae in SBO are in the developmental stage of the spinous process, and an abnormal laminar growth direction and laminar stenosis are the most common laminar morphologies in SBO.

How Does the Measurement of Disability in Low Back Pain Map Unto the International Classification of Functioning, Disability and Health?: A Scoping Review of the Manual Medicine Literature.

ABSTRACT: The objective of this study was to catalog items from instruments used to measure functioning, disability, and contextual factors in patients with low back pain treated with manual medicine (manipulation and mobilization) according to the International Classification of Functioning, Disability and Health. This catalog will be used to inform the development of an International Classification of Functioning, Disability and Health-based assessment schedule for low back pain patients treated with manual medicine. In this scoping review, we systematically searched MEDLINE, Embase, PsycINFO, and CINAHL. We identified instruments (questionnaires, clinical tests, single questions) used to measure functioning, disability, and contextual factors, extracted the relevant items, and then linked these items to the International Classification of Functioning, Disability and Health. We included 95 articles and identified 1510 meaningful concepts. All but 70 items were linked to the International Classification of Functioning, Disability and Health. Of the concepts linked to the International Classification of Functioning, Disability and Health, body functions accounted for 34.7%, body structures accounted for 0%, activities and participation accounted for 41%, environmental factors accounted for 3.6%, and personal factors accounted for 16%. Most items used to measure functioning and disability in low back pain patient treated with manual medicine focus on body functions, as well as activities and participation. The lack of measures that address environmental factors warrants further investigation.

Physical function characteristics in Japanese high school volleyball players with low back pain: A case-controlled study.

Low back pain (LBP) is a typical symptom in volleyball players, yet associated physical function factors have not been identified. This study purpose is to determine the relationship between LBP and physical function factors in order to identify potential factors for the management of LBP.Participants were 123 male and female volleyball players of 15- to 17-year-olds who, completed a questionnaire regarding demographic details, presence of LBP, and years of volleyball experience. Participants were divided into 2 groups based on the presence of current LBP and evaluated on physical function tests. The results of the questionnaire response and physical function test were compared between the 2 groups. Data were analyzed using a multivariate logistic regression analysis with presence and absence of current LBP as the explanatory variable.11.4% of all participants reported current LBP. Physical function factors associated with current LBP were a positive modified Thomas test, years of volleyball experience and reduced range of motion of shoulder horizontal abduction on the dominant hand side.The associations between physical function factors and LBP found in this survey suggest that attention should be given to more experienced players with decreased flexibility of hip and shoulder flexors on the dominant side in order to manage LBP in high school volleyball players.

Different types of low back pain in relation to pre- and post-natal maternal depressive symptoms.

BACKGROUND: Low back pain (LBP) is a common musculoskeletal problem during pregnancy, with an estimated prevalence ranging from 30-78% (Mota MJ et al. J Back Musculoskelet Rehabil 28(2):351-7,2015 and Abebe E et al. J Med Sc Tech 3(3). 37-44,2014). Women reporting LBP are at increased risk of developing perinatal depression. Pregnancy-related LBP is highly heterogeneous and can be divided into lumbar pain (LP), posterior pelvic pain (PPP), and combined pain (CP). Therefore, the purpose of this study was to investigate the associations between LBP and perinatal depressive symptoms. METHODS: This was a retrospective case-control study conducted from January 2016 to April 2019. A total of 484 pregnant women were enrolled in this study: a case group of 242 pregnant women who were diagnosed with LBP and an age-matched control group of 242 pregnant women without LBP. The Edinburgh Postnatal Depression Scale (EPDS), LBP characteristics, and questionnaires about pregnancy that included demographic, parity, work, comorbidity, and previous pregnancy data were completed and compared between the case group and the control group. RESULTS: A total of 68 of 242 (28.1%) women experienced PPP, 142 (58.7%) had lumbar pain(LP), and 32 (13.2%) had combined pain. Furthermore, 26.5% of women with prenatal depression in the LP subgroup remained depressed 6 months postnatally, while the percentages for women in the PPP subgroup and CP subgroup were just 10.6% and 15.6%, respectively. The percentage of women who recovered anytime between delivery and six months postnatally in the PPP subgroup was significantly higher than that in the LP subgroup (31.7% vs. 14.7%, P < 0.001). CONCLUSIONS: There is a difference in the prevalence of prenatal, postnatal, and perinatal depressive symptoms among pregnant women with different types of LBP. It is necessary to screen prenatal and postnatal depression separately and differentiate the types of LBP during pregnancy. Attention to these factors may help to outline better management strategies to improve maternal health.

Significant Association between the T2 Values of Vertebral Cartilage Endplates and Pfirrmann Grading.

OBJECTIVE: The T2 value of lumbar cartilage endplates was measured using the T2 mapping imaging technique, aiming to explore the correlation between the T2 value and Pfirrmann grading of intervertebral discs. METHODS: A total of 130 patients with lumbar spine MR examination due to persistent low back pain were enrolled, including 71 men and 59 women (age: 21-63 years). Lumbar Modic changes and Schmorl nodules were recognized by conventional T1WI and T2WI images in 49 patients, and these patients were excluded from the study. A total of 81 patients were enrolled in this study, including 45 men (45.16 ± 12.20 years) and 36 women (43.33 ± 11.27 years). Pfirrmann (Pm) grading of each lumbar disc was performed based on conventional T2WI median sagittal images and the position of cartilage endplates (CEP) was determined by IDEAL-SPGR images. Meanwhile, the T2 mapping technique was used to obtain T2 values of cartilage endplates. The T2 values of CEP corresponding to different Pm grade discs were compared, and the correlation between the T2 value and the Pm grade of intervertebral discs was analyzed. RESULTS: The T2 values of cephalic and caudal CEP of L1-2 in Pm grades I-II, Pm grades III, and Pm grades IV-V were 61.96 ± 5.89 ms, 54.45 ± 3.29 ms, 42.47 ± 3.69 ms and 64.35 ± 5.93 ms, 55.28 ± 3.97 ms, 44.75 ± 2.12 ms, respectively. For cephalic and caudal CEP of L2-3 , the T2 values in Pm grades I-II, Pm grades III, and Pm grades IV-V were 62.96 ± 6.93 ms, 55.19 ± 4.02 ms, 48.67 ± 4.56 ms and 65.51 ± 6.49 ms, 57.16 ± 5.55 ms, 52.05 ± 4.20 ms, respectively. The T2 values of cephalic and caudal CEP from L3-4 to L5 -S1 in Pm grades I-II, Pm grades III, and Pm grades IV-V were (63.72 ± 5.76 ms, 53.96 ± 6.52 ms, 48.05 ± 5.00 ms), (65.46 ± 6.37 ms, 55.70 ± 7.50 ms, 48.10 ± 3.27 ms); (66.34 ± 7.68 ms, 56.76 ± 9.48 ms, 47.80 ± 4.33 ms), (64.44 ± 4.65 ms, 59.30 ± 8.80 ms, 47.30 ± 5.78 ms), (65.32 ± 5.11 ms, 55.33 ± 6.65 ms, 48.18 ± 5.37 ms), and (63.47 ± 4.92 ms, 50.32 ± 8.86 ms, 44.77 ± 4.69 ms), respectively. There were significant differences in T2 values of cartilage endplates between the Pm grades I-II, III, and IV-V of intervertebral discs (P = 0.000). T2 values corresponding to Pm I-II grades were higher than those in Pm III grade, while T2 values in Pm grades IV-V were lowest. The T2 value of the L4-5 , L5 -S1 segment endplates was highly correlated with the Pm grades (r = -0.711, -0.721, -0.796, -0.745; P = 0.000) and that of L1-2 , L2-3 endplates were moderately correlated (r = -0.542, -0.562, -0.637, -0.612; P = 0.000). CONCLUSION: The T2 values of cartilage endplates revealed varying degrees of degeneration of intervertebral discs, and more severe degeneration corresponded to lower T2 values. Measurement of changes in the T2 value through cartilage endplates can be useful for the diagnosis of early intervertebral disc degeneration and the prevention of disc degeneration.

Characteristics of Low Back Pain in Pregnancy, Risk Factors, and Its Effects on Quality of Life.

BACKGROUND: Low back pain is a common problem experienced during pregnancy, negatively affecting quality of life. AIMS: The study aimed to determine the prevalence and risk factors of low back pain during pregnancy and its effects on the quality of life. DESIGN: This was a descriptive and cross-sectional study. SETTINGS: Its setting was the Kastamonu State Hospital Obstetrics and Gynecology clinics. PARTICIPANTS/SUBJECTS: The study consisted of 400 pregnant women. METHODS: The sample consisted of 400 pregnant women. Data were collected using an introductory information form, a back pain evaluation form, the Visual Analog Scale (VAS), and the Oswestry Disability Index (ODI). RESULTS: In terms of back pain, 75.3% of the participants experienced back pain during their current pregnancy. The mean VAS score for back pain during their current pregnancy was 4.91±1.88. Low back pain was generally experienced in the third trimester (85.5%) and in the lumbar area (45.5%). Factors associated with low back pain included income status, trimester, gestational weight gain, frequent urinary tract infections, a hunchback posture, having experienced low back pain during previous pregnancies, and a history of low back pain. The mean percentage score on the ODI, which assesses the effect of low back pain on functional status, was 31.87% ± 15.56%, and for the majority of the participants (45.7%), low back pain was found to slightly limit their activities of daily living. CONCLUSIONS: The prevalence of low back pain in pregnancy is quite high, and low back pain slightly limits women's activities of daily living.

A Practical Sensor-Based Methodology for the Quantitative Assessment and Classification of Chronic Non Specific Low Back Patients (NSLBP) in Clinical Settings.

The successful clinical application of patient-specific personalized medicine for the management of low back patients remains elusive. This study aimed to classify chronic nonspecific low back pain (NSLBP) patients using our previously developed and validated wearable inertial sensor (SHARIF-HMIS) for the assessment of trunk kinematic parameters. One hundred NSLBP patients consented to perform repetitive flexural movements in five different planes of motion (PLM): 0° in the sagittal plane, as well as 15° and 30° lateral rotation to the right and left, respectively. They were divided into three subgroups based on the STarT Back Screening Tool. The sensor was placed on the trunk of each patient. An ANOVA mixed model was conducted on the maximum and average angular velocity, linear acceleration and maximum jerk, respectively. The effect of the three-way interaction of Subgroup by direction by PLM on the mean trunk acceleration was significant. Subgrouping by STarT had no main effect on the kinematic indices in the sagittal plane, although significant effects were observed in the asymmetric directions. A significant difference was also identified during pre-rotation in the transverse plane, where the velocity and acceleration decreased while the jerk increased with increasing asymmetry. The acceleration during trunk flexion was significantly higher than that during extension, in contrast to the velocity, which was higher in extension. A Linear Discriminant Analysis, utilized for classification purposes, demonstrated that 51% of the total performance classifying the three STarT subgroups (65% for high risk) occurred at a position of 15° of rotation to the right during extension. Greater discrimination (67%) was obtained in the classification of the high risk vs. low-medium risk. This study provided a smart "sensor-based" practical methodology for quantitatively assessing and classifying NSLBP patients in clinical settings. The outcomes may also be utilized by leveraging cost-effective inertial sensors, already available in today's smartphones, as objective tools for various health applications towards personalized precision medicine.

A classification-based approach to low back pain in primary care - protocol for a benchmarking controlled trial.

BACKGROUND: Guidelines recommend a biopsychosocial framework for low back pain (LBP) management and the avoidance of inappropriate imaging. In clinical practice, care strategies are often inconsistent with evidence and guidelines, even though LBP is the most common disabling health condition worldwide. Unhelpful beliefs, attitudes and inappropriate imaging are common. LBP is understood to be a complex biopsychosocial phenomenon with many known multidimensional risk factors (symptom- and lifestyle-related, psychological and social) for persistent or prolonged disability, which should be identified and addressed by treatment. The STarT Back Tool (SBT) was developed for early identification of individual risk factors of LBP to enable targeted care. Stratified care according SBT has been shown to improve the effectiveness of care in a primary care setting. A biopsychosocially-oriented patient education booklet, which includes imaging guidelines and information, is one possible way to increase patients' understanding of LBP and to reduce inappropriate imaging. Premeditated pathways, education of professionals, written material, and electronic patient registry support in health care organizations could help implement evidence-based care. METHODS: We will use a Benchmarking Controlled Trial (BCT) design in our study. We will prospectively collect data from three health care regions before and after the implementation of a classification-based approach to LBP in primary care. The primary outcome will be change in PROMIS (Patient-Reported Outcomes Measurement Information System) (short form 20a) over 12-month follow-up. DISCUSSION: The implementation of a classification-based biopsychosocial approach can potentially improve the care of LBP patients, reduce inappropriate imaging without increasing health-care costs, and decrease indirect costs by reducing work disability. Using the BCT we will be able to evaluate the effectiveness of the improvement strategy for the entire care pathway. TRIAL REGISTRATION: ISRCTN,ISRCTN13273552, retrospectively registered 13/05/2019.

Mapping patient reported outcome measures for low back pain to the International Classification of Functioning, Disability and Health using random forests.

BACKGROUND: There is need for feasible and efficient concepts to document patients functioning impairment according to the International Classification of Functioning, Disability and Health (ICF) without imposing additional burden to clinical practice. AIM: The aim of this study was to develop and validate an automatic linking approach that translates information derived from patient reported outcome measures (PROMs) into the ICF. DESIGN: Proof-of-concept study. SETTING: Participants completed both the Roland-Morris disability questionnaire and the Pain Disability Index and were interviewed using the activity and participation component of the ICF brief core set for low back pain. POPULATION: A total of 244 patients with light to moderate chronic low back pain (cLBP); additionally, 19 patients with higher levels of pain were recruited and assessed for validation purposes. METHODS: Based on information extracted from the PROMs and considering the factors age and gender, random forest models that predicted the presence or absence of an impairment at the specific ICF category were computed and validated. RESULTS: Accuracy of the models was found to be acceptable for the most relevant ICF brief core set categories for low back pain if applied at the population level. CONCLUSIONS: The presented approach can be assumed valid if applied at large on population level. The results are of relevance for the further development of automatic linking programs that would allow the ICF-based classification of functioning properties within the International Classification of Diseases (ICD-11) for any health condition. CLINICAL REHABILITATION IMPACT: The presented approach eases the documentation of patients' functioning impairment according to the standardized ICF.

Initial classification of low back and leg pain based on objective functional testing: a pilot study of machine learning applied to diagnostics.

OBJECTIVE: The five-repetition sit-to-stand (5R-STS) test was designed to capture objective functional impairment and thus provided an adjunctive dimension in patient assessment. The clinical interpretability and confounders of the 5R-STS remain poorly understood. In clinical use, it became apparent that 5R-STS performance may differ between patients with lumbar disk herniation (LDH), lumbar spinal stenosis (LSS) with or without low-grade spondylolisthesis, and chronic low back pain (CLBP). We seek to evaluate the extent of diagnostic information contained within 5R-STS testing. METHODS: Patients were classified into gold standard diagnostic categories based on history, physical examination, and imaging. Crude and adjusted comparisons of 5R-STS performance were carried out among the three diagnostic categories. Subsequently, a machine learning algorithm was trained to classify patients into the three categories using only 5R-STS test time and patient age, gender, height, and weight. RESULTS: From two prospective studies, 262 patients were included. Significant differences in crude and adjusted test times were observed among the three diagnostic categories. At internal validation, classification accuracy was 96.2% (95% CI 87.099.5%). Classification sensitivity was 95.7%, 100%, and 100% for LDH, LSS, and CLBP, respectively. Similarly, classification specificity was 100%, 95.7%, and 100% for the three diagnostic categories. CONCLUSION: 5R-STS performance differs according to the etiology of back and leg pain, even after adjustment for demographic covariates. In combination with machine learning algorithms, OFI can be used to infer the etiology of spinal back and leg pain with accuracy comparable to other diagnostic tests used in clinical examination. These slides can be retrieved under Electronic Supplementary Material.

Exploring conceptual preprocessing for developing prognostic models: a case study in low back pain patients.

OBJECTIVES: A conceptually oriented preprocessing of a large number of potential prognostic factors may improve the development of a prognostic model. This study investigated whether various forms of conceptually oriented preprocessing or the preselection of established factors was superior to using all factors as input. STUDY DESIGN AND SETTING: We made use of an existing project that developed two conceptually oriented subgroupings of low back pain patients. Based on the prediction of six outcome variables by seven statistical methods, this type of preprocessing was compared with medical experts' preselection of established factors, as well as using all 112 available baseline factors. RESULTS: Subgrouping of patients was associated with low prognostic capacity. Applying a Lasso-based variable selection to all factors or to domain-specific principal component scores performed best. The preselection of established factors showed a good compromise between model complexity and prognostic capacity. CONCLUSION: The prognostic capacity is hard to improve by means of a conceptually oriented preprocessing when compared to purely statistical approaches. However, a careful selection of already established factors combined in a simple linear model should be considered as an option when constructing a new prognostic rule based on a large number of potential prognostic factors.

AAPT Diagnostic Criteria for Chronic Low Back Pain.

Chronic low back pain (CLBP) conditions are highly prevalent and constitute the leading cause of disability worldwide. The Analgesic, Anesthetic, and Addiction Clinical Trial Translations Innovations Opportunities and Networks (ACTTION) public-private partnership with the US Food and Drug Administration and the American Pain Society (APS), have combined to create the ACTTION-APS Pain Taxonomy (AAPT). The AAPT initiative convened a working group to develop diagnostic criteria for CLBP. The working group identified 3 distinct low back pain conditions which result in a vast public health burden across the lifespan. This article focuses on: 1) the axial predominant syndrome of chronic musculoskeletal low back pain, 2) the lateralized, distally-radiating syndrome of chronic lumbosacral radicular pain 3) and neurogenic claudication associated with lumbar spinal stenosis. This classification of CLBP is organized according to the AAPT multidimensional framework, specifically 1) core diagnostic criteria; 2) common features; 3) common medical and psychiatric comorbidities; 4) neurobiological, psychosocial, and functional consequences; and 5) putative neurobiological and psychosocial mechanisms, risk factors, and protective factors. PERSPECTIVE: An evidence-based classification of CLBP conditions was constructed for the AAPT initiative. This multidimensional diagnostic framework includes: 1) core diagnostic criteria; 2) common features; 3) medical and psychiatric comorbidities; 4) neurobiological, psychosocial, and functional consequences; and 5) putative neurobiological and psychosocial mechanisms, risk factors, and protective factors.

Concerns related to the accurate identification of anterior derangement syndrome in mechanical diagnosis and therapy for low back pain: A case report.

Background: In Mechanical Diagnosis and Therapy (MDT), patients with low back pain (LBP) are classified into subgroups to guide a management strategy. A common subgroup where symptoms improve with lumbar extension is labeled posterior derangement syndrome. A less common subgroup where symptoms improve with lumbar flexion is labeled anterior derangement syndrome. Case Presentation: The patient was a 23-year-old woman with intermittent LBP and discomfort over the left lower extremity was initially diagnosis with posterior derangement syndrome. At the initial and second consultations, postural correction and home exercises with lumbar extension were prescribed. However, at the third consultation, sustained lumbar extension revealed worsening of symptoms and function, which resulted in a revised diagnosis of anterior derangement syndrome. Complete recovery was achieved using exercises with lumbar flexion over 6 weeks. Outcomes: The patient wore the LUMOback in daily life, which is a wearable device measuring pelvic angle and acceleration, for 1 week before the initial MDT consultation and for 6 weeks until discharge. The posture scores (%) is the proportion of time in a week with neutral pelvic tilt. In this patient, the posture score decreased greater than a minimum detectable change of 11.7% when MDT classification changed to anterior derangement. Conclusions: This case report indicates the importance of sustained loading to identify the correct derangement syndrome, and follow-up sessions to confirm or reject the initial diagnosis by monitoring symptom and functional changes carefully. Habitual posture may be associated with reduction and aggravation of symptoms.

Association between changes in function among patients with lumbar impairments classified according to the STarT Back Screening Tool and managed by McKenzie credentialed physiotherapists.

PURPOSE: To examine the association between functional status (FS) scores using a Patient Reported Outcome Measure (PROM) for patients with non-specific low back pain classified according to psychosocial risk using the STarT Back Screening Tool and managed by physiotherapists credentialed in McKenzie methods. METHODS: Participants (n = 705) completed FS and STarT surveys at intake and discharge. Prevalence of STarT risk classifications and change in STarT risk was calculated. Regression models were developed to examine associations between baseline and change in STarT risk categories, and FS outcomes at discharge from rehabilitation services. RESULTS: FS outcomes at discharge was not significantly different (p-values > 0.10) across baseline STarT risk subgroups after controlling for model covariates. Seventy-eight and 91.5% of medium and high-risk patients respectively decreased STarT risk. When compared with subjects whose STarT risk decreased, there was no significant difference in subjects whose STarT risk remained low. For subjects whose risk remained medium/high, or whose risk worsened, FS outcome scores were statistically significant (p < 0.001) and clinically relevant (-15.76 and -23.42 points respectively) compared to patients whose STarT risk decreased. CONCLUSIONS: Baseline STarT psychosocial risk stratifications should be interpreted cautiously to estimate the likelihood of good or poor FS outcomes at discharge from physiotherapy practice in the US when patients are managed by clinicians credentialed in McKenzie methods. Decreased STarT risk was associated with clinically important improvements in FS outcomes scores at discharge from McKenzie directed physiotherapy care.

Examination of a Subgroup of Patients With Chronic Low Back Pain Likely to Benefit More From Pilates-Based Exercises Compared to an Educational Booklet.

OBJECTIVE: To investigate whether 2 previously published classification approaches, the updated treatment-based classification system and a Pilates subgroup defined by a preliminary clinical prediction rule, could identify patients with chronic low back pain who would benefit more from Pilates exercises compared to an educational booklet. DESIGN: Secondary analysis of a randomized controlled trial. METHODS: Two hundred twenty-two patients received advice and were randomly allocated to a group that received an educational booklet with no additional treatment (n = 74) or a group that received Pilates-based exercise treatment (n = 148) 2 or 3 times a week. At baseline, using a treatment-based classification system, patients were classified as having a good prognosis (positive movement control) or a poor prognosis. Similarly, using the Pilates clinical prediction rule, patients were classified as having a good prognosis (positive) or a poor prognosis (negative). The analysis was conducted using linear regression models to analyze the interaction between subgroup characteristics and treatment effect size, with changes in pain and disability from baseline to 6 weeks after randomization as dependent variables. RESULTS: None of the interaction terms for pain and disability were statistically significant. The treatment effect of Pilates versus an educational booklet was similar in all subgroups. CONCLUSION: The treatment-based classification system and the Pilates clinical prediction rule did not differentiate subgroups of patients with chronic low back pain who were more or less likely to benefit more from Pilates compared to an educational booklet. J Orthop Sports Phys Ther 2020;50(4):189-197. Epub 23 Aug 2019. doi:10.2519/jospt.2019.8839.