Degenerative Cervical Myelopathy: Towards a Personalized Approach

The role of comprehensive rehabilitation in the care of degenerative cervical myelopathy

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

To find out if comprehensive rehabilitation itself can improve daily performance in persons with DCM.

SETTING

The spinal department of a rehabilitation hospital.

METHODS

Data from 116 DCM inpatients who underwent comprehensive rehabilitation after spinal surgery were retrospectively analyzed. The definitions of the calculated outcome variables made possible analyses that distinguished the effect of rehabilitation from that of spinal surgery. Paired t-tests were used to compare admission with discharge outcomes and functional gains. Spearman's correlations were used to assess relationships between performance gain during rehabilitation and between time from surgery to rehabilitation.

RESULTS

The Spinal Cord Injury Ability Realization Measurement Index (SCI-ARMI) increased during rehabilitation from 57 (24) to 78 (19) (p < 0.001). The Spinal Cord Independence Measure 3rd version (SCIM III) gain attributed to neurological improvement (dSCIM-IIIn) was 6.3 (9.2), and that attributed to rehabilitation (dSCIM-IIIr) 16 (18.5) (p < 0.001). dSCIM-IIIr showed a rather weak negative correlation with time from spinal surgery to rehabilitation (r = -0.42, p < 0.001).

CONCLUSIONS

The study showed, for the first time, that comprehensive rehabilitation can achieve considerable functional improvement for persons with DCM of any degree, beyond that of spinal surgery. Combined with previously published evidence, this indicates that comprehensive rehabilitation can be considered for persons with DCM of any functional degree, before surgery.

Degenerative cervical myelopathy: establishing severity thresholds for neuromotor dysfunction in the aging spine using the NIH Toolbox Assessment Scale

Degenerative cervical myelopathy (DCM) is a leading cause of age-related non-traumatic spinal cord disorders resulting from chronic degeneration of the cervical spine. While traditional clinical assessments rely on patient-reported measures, this study used the NIH Toolbox Motor Battery (NIHTBm) as an objective, quantitative measure to determine DCM severity. The objective is to define NIHTBm cutoff values that can accurately classify the severity of DCM neuromotor dysfunction. A case-controlled pilot study of patients with DCM and age-matched controls. The focus was an in-depth quantitative motor assessment using the NIHTBm to understand the severity of neuromotor deficits due to degenerative spine disease. Motor assessments, dexterity, grip strength, balance, and gait speed were measured in 45 DCM patients and 37 age-matched healthy subjects (HC). Receiver operating curve (ROC) analysis determined cutoff values for mild and moderate-to-severe myelopathy which were validated by comparing motor assessment scores with disability scores. The ROC curves identified thresholds for mild dexterity impairment (T-score range 38.4 - 33.5, AUC 0.77), moderate-to-severe dexterity impairment (< 33.5, AUC 0.70), mild grip strength impairment (47.4 - 32.0, AUC 0.80), moderate-to-severe grip strength impairment (< 32.0, AUC 0.75), mild balance impairment (36.4 - 33.0, AUC 0.61), and moderate-to-severe balance impairment (< 33.0, AUC 0.78). Mild gait speed impairment was defined as 0.78-0.6 m/sec (AUC 0.65), while moderate-to-severe gait speed impairment was < 0.6 m/sec (AUC 0.65). The NIHTB motor score cutoff points correlated negatively with the DCM neck disability index (NDI) and showed balance and dexterity measures as independent indicators of DCM dysfunction. The use of NIHTB allows for precise delineation of DCM severity by establishing cutoff values corresponding to mild and moderate-to-severe myelopathy. The use of NIHTB in DCM allows enhanced clinical precision, enabling clinicians to better pinpoint specific motor deficits in DCM and other neurological disorders with motor deficits, including stroke and traumatic brain injury (TBI). Furthermore, the utility of objective assessment, NIHTB, allows us to gain a better understanding of the heterogeneity of DCM, which will enhance treatment strategies. This study serves as a foundation for future research to facilitate the discovery of innovative treatment strategies for DCM and other neurological conditions.

Machine Learning and Symptom Patterns in Degenerative Cervical Myelopathy: Web-Based Survey Study

BACKGROUND

Degenerative cervical myelopathy (DCM), a progressive spinal cord injury caused by spinal cord compression from degenerative pathology, often presents with neck pain, sensorimotor dysfunction in the upper or lower limbs, gait disturbance, and bladder or bowel dysfunction. Its symptomatology is very heterogeneous, making early detection as well as the measurement or understanding of the underlying factors and their consequences challenging. Increasingly, evidence suggests that DCM may consist of subgroups of the disease, which are yet to be defined.

OBJECTIVE

This study aimed to explore whether machine learning can identify clinically meaningful groups of patients based solely on clinical features.

METHODS

A survey was conducted wherein participants were asked to specify the clinical features they had experienced, their principal presenting complaint, and time to diagnosis as well as demographic information, including disease severity, age, and sex. K-means clustering was used to divide respondents into clusters according to their clinical features using the Euclidean distance measure and the Hartigan-Wong algorithm. The clinical significance of groups was subsequently explored by comparing their time to presentation, time with disease severity, and other demographics.

RESULTS

After a review of both ancillary and cluster data, it was determined by consensus that the optimal number of DCM response groups was 3. In Cluster 1, there were 40 respondents, and the ratio of male to female participants was 13:21. In Cluster 2, there were 92 respondents, with a male to female participant ratio of 27:65. Cluster 3 had 57 respondents, with a male to female participant ratio of 9:48. A total of 6 people did not report biological sex in Cluster 1. The mean age in this Cluster was 56.2 (SD 10.5) years; in Cluster 2, it was 54.7 (SD 9.63) years; and in Cluster 3, it was 51.8 (SD 8.4) years. Patients across clusters significantly differed in the total number of clinical features reported, with more clinical features in Cluster 3 and the least clinical features in Cluster 1 (Kruskal-Wallis rank sum test: χ22=159.46; P<.001). There was no relationship between the pattern of clinical features and severity. There were also no differences between clusters regarding time since diagnosis and time with DCM.

CONCLUSIONS

Using machine learning and patient-reported experience, 3 groups of patients with DCM were defined, which were different in the number of clinical features but not in the severity of DCM or time with DCM. Although a clearer biological basis for the clusters may have been missed, the findings are consistent with the emerging observation that DCM is a heterogeneous disease, difficult to diagnose or stratify. There is a place for machine learning methods to efficiently assist with pattern recognition. However, the challenge lies in creating quality data sets necessary to derive benefit from such approaches.

Elderly Patients Show Substantial Improvement in Health-Related Quality of Life After Surgery for Degenerative Cervical Myelopathy Despite Medical Frailty: An Ambispective Analysis of a Multicenter, International Data Set

BACKGROUND AND OBJECTIVES

We assessed the relationship between Modified Frailty Index-5 (mFI-5) and neurological outcomes, as well as health-related quality of life (HRQoL) measures, in elderly patients with degenerative cervical myelopathy (DCM) after surgery.

METHODS

Data from 3 major DCM trials (the Arbeitsgemeinschaft für Osteosynthesefragen Spine Cervical Spondylotic Myelopathy-North America, Cervical Spondylotic Myelopathy-International, and CSM-PROTECT studies) were combined, involving 1047 subjects with moderate to severe myelopathy. Patients older than 60 years with 6-month and 1-year postoperative data were analyzed. Neurological outcome was assessed using the modified Japanese Orthopaedic Association score, while HRQoL was measured using the 36-Item Short Form Health Survey (SF-36) (both Physical Component Summary [SF-36 PCS] and Mental Component Summary [SF-36 MCS] scores) and the Neck Disability Index. Frail (mFI ≥2) and nonfrail (mFI = 0-1) cohorts were compared using univariate paired statistics.

RESULTS

The final analysis included 261 patients (62.5% male), with a mean age of 71 years (95% CI 70.7-72). Frail patients (mFI ≥2) had lower baseline modified Japanese Orthopaedic Association scores (10.45 vs 11.96, P < .001), SF-36 PCS scores (32.01 vs 36.51, P < .001), and SF-36 MCS scores (39.32 vs 45.24, P < .001). At 6-month follow-up, SF-36 MCS improved by a mean (SD) of 7.19 (12.89) points in frail vs 2.91 (11.11) points in the nonfrail group (P = .016). At 1 year after surgery, frail patients showed greater improvement in both SF-36 PCS and SF-36 MCS composite scores compared with nonfrail patients (7.81 vs 4.49, P = .038, and 7.93 vs 3.01, P = .007, respectively). Bivariate regression analysis revealed that higher mFI-5 scores correlated with more substantial improvement in overall mental status at 6 months and 1 year (P = .024 and P = .009, respectively).

CONCLUSION

mFI-5 is a clinically helpful signature to reflect the HRQoL status among elderly patients with DCM. Despite preoperative medical frailty, elderly patients with DCM experience significant HRQoL improvement after surgery. These findings enable clinicians to identify elderly patients with modifiable comorbidities and provide informed counseling on anticipated outcomes.

LEVEL OF EVIDENCE

II.

Predictive Value of Preoperative Short Form-36 Survey Scale for Postoperative Axial Neck Pain in Patients With Degenerative Cervical Myelopathy

STUDY DESIGN

Prospective observational study.

OBJECTIVE

To evaluate the predictive value of the preoperative Short Form-36 survey (SF-36) scale for postoperative axial neck pain (ANP) in patients with degenerative cervical myelopathy (DCM) who underwent anterior cervical decompression and fusion (ACDF) surgery.

METHODS

This study enrolled patients with DCM who underwent ACDF surgery at author's Hospital between May 2010 and June 2016.

RESULTS

Out of 126 eligible patients, 122 completed the 3-month follow-up and 117 completed the 1-year follow-up. The results showed that the preoperative social functioning (SF) subscale score of the SF-36 scale was significantly lower in patients with moderate-to-severe postoperative ANP than in those with no or mild postoperative ANP at both follow-up timepoints (P < .05). ACDF at C4-5 level resulted in a higher ANP rate than ACDF at C5-6 or C6-7 level, both at 3-month (P = .019) and 1-year (P = .004) follow-up. Multivariate logistic regression analysis confirmed that the preoperative social functioning subscale score was an independent risk factor for moderate-to-severe postoperative ANP at 3 months and 1 year after surgery, and preoperative NRS was an independent risk factor at 1-year follow-up. No other demographic, clinical, or radiographic factors were found to be associated with postoperative ANP severity (P < .05).

CONCLUSIONS

Preoperative social functioning subscale score of SF-36 scale might be a favorable predictive tool for postoperative ANP in DCM patients who underwent ACDF surgery.

Classification of expert-level therapeutic decisions for degenerative cervical myelopathy using ensemble machine learning algorithms

Background

Therapeutic decisions for degenerative cervical myelopathy (DCM) are complex and should consider various factors. We aimed to develop machine learning (ML) models for classifying expert-level therapeutic decisions in patients with DCM.

Methods

This retrospective cross-sectional study included patients diagnosed with DCM, and the diagnosis of DCM was confirmed clinically and radiologically. The target outcomes were defined as conservative treatment, anterior surgical approaches (ASA), and posterior surgical approaches (PSA). We performed the following classifications using ML algorithms: multiclass, one-versus-rest, and one-versus-one. Two ensemble ML algorithms were used: random forest (RF) and extreme gradient boosting (XGB). The area under the receiver operating characteristic curve (AUC-ROC) was the primary metric. We also identified the variable importance for each classification.

Results

In total, 304 patients were included (109 conservative, 66 ASA, 125 PSA, and 4 combined surgeries). For multiclass classification, the AUC-ROC of RF and XGB models were 0.91 and 0.92, respectively. In addition, ML models showed AUC-ROC values of >0.9 for all types of binary classifications. Variable importance analysis revealed that the modified Japanese Orthopaedic Association score and central motor conduction time were the two most important variables for distinguishing between conservative and surgical treatments. When classifying ASA and PSA, the number of involved levels, age, and body mass index were important contributing factors.

Conclusion

ML-based classification of DCM therapeutic options is valid and feasible. This study can be a basis for establishing generalizable ML-based surgical decision models for DCM. Further studies are needed with a large multicenter database.