Machine Learning Diagnosis and Prediction for Cervical Myelopathy

Summary

DESIGN: Ambispective cohort study (retrospective + prospective). AIMS: The overall aim of this research study is to create two predictive machine learning models that are based on radiological, clinical and biochemical variables, which allows spine surgeons to diagnose CSM earlier and more accurately, as well as allowing them to give patients highly individualised and accurate predictive information regarding treatment outcomes.

OUTCOME MEASURES: For the prospective arm of the study the independent variables will be patient characteristics, clinical, radiological and biochemical markers. Dependent variables are mJOA and JOACMEQ scores. For the retrospective arm of the study the independent variables will be patient characteristics, co-morbidities and symptomology, outcome variable will be radiological confirmation on cervical myelopathy.

POPULATION: Patients with cervical myelopathy over 18 years old (19 years and above included), treated at Imperial College NHS Healthcare Trust for CM with full capacity to consent and assessed for cervical myelopathy symptoms at Community MSK Hounslow and Richmond Community Healthcare NHS Trust (catchment area of ICHT neurosurgery).

ELIGIBILITY: Over 18 years old, with full capacity to consent. TREATMENT: Cervical myelopathy diagnosis and/or conservative and/or surgical management of disease DURATION: 18 months

Conditions

• Cervical Myelopathy

Interventions

OTHER

The questionnaire "Cervical myelopathy treatment outcome questionnaire"

Information gathered through clinical examination and questionnaires performed retrospectively over the phone, pre-operation and at 3- and 6-months post-operation. The questionnaire "Cervical myelopathy treatment outcome questionnaire" attached records information relating to co-morbidities and symptomology. The examination will be a thorough neurological examination in addition to a focused cardiovascular examination. Biochemical blood markers from existing blood markers or from GP records, which have been or would have been performed regardless of this trial. Radiological findings will be taken from routine MRI and cervical spine X-rays performed as part of the CSM diagnostic work-up

OTHER

The retrospective questionnaire "CSM early diagnosis questionnaire"

To identify early clinical predictors of cervical myelopathy diagnosis based on individual patient-reported symptoms by using a questionnaire and patient characteristics as well as co-morbities, as well as clinical examination findings provided by community musculoskeletal teams.

OTHER

JOACMEQ questionnaire and mJOA

Used for prospective cohort via telephone at 3, 6 and 12-months post-operatively to assess treatment outcomes.

Sponsors & Collaborators

• Imperial College Healthcare NHS Trust

  lead OTHER

Principal Investigators

• Santhosh G. Thavarajasingam, BSc · Imperial College London

• Mahmoud El-Khatib, BSc · Imperial College London

• Mark Rea, BSc · Imperial College London

• Diana Keeling, BSc Msc · Community MSK Hounslow and Richmond Community Healthcare NHS Trust

Eligibility

Min Age

19 Years

Sex

ALL

Healthy Volunteers

Yes

Timeline & Regulatory

Start

2021-10-31

Primary Completion

2022-05-31

Completion

2022-12-31