Multimodal Prediction of 3- and 12-Month Outcomes in ICU Patients with Acute Disorders of Consciousness

BACKGROUND

In intensive care unit (ICU) patients with coma and other disorders of consciousness (DoC), outcome prediction is key to decision-making regarding prognostication, neurorehabilitation, and management of family expectations. Current prediction algorithms are largely based on chronic DoC, whereas multimodal data from acute DoC are scarce. Therefore, the Consciousness in Neurocritical Care Cohort Study Using Electroencephalography and Functional Magnetic Resonance Imaging (i.e. CONNECT-ME; ClinicalTrials.gov identifier: NCT02644265) investigates ICU patients with acute DoC due to traumatic and nontraumatic brain injuries, using electroencephalography (EEG) (resting-state and passive paradigms), functional magnetic resonance imaging (fMRI) (resting-state) and systematic clinical examinations.

METHODS

We previously presented results for a subset of patients (n = 87) concerning prediction of consciousness levels in the ICU. Now we report 3- and 12-month outcomes in an extended cohort (n = 123). Favorable outcome was defined as a modified Rankin Scale score ≤ 3, a cerebral performance category score ≤ 2, and a Glasgow Outcome Scale Extended score ≥ 4. EEG features included visual grading, automated spectral categorization, and support vector machine consciousness classifier. fMRI features included functional connectivity measures from six resting-state networks. Random forest and support vector machine were applied to EEG and fMRI features to predict outcomes. Here, random forest results are presented as areas under the curve (AUC) of receiver operating characteristic curves or accuracy. Cox proportional regression with in-hospital death as a competing risk was used to assess independent clinical predictors of time to favorable outcome.

RESULTS

Between April 2016 and July 2021, we enrolled 123 patients (mean age 51 years, 42% women). Of 82 (66%) ICU survivors, 3- and 12-month outcomes were available for 79 (96%) and 77 (94%), respectively. EEG features predicted both 3-month (AUC 0.79 [95% confidence interval (CI) 0.77-0.82]) and 12-month (AUC 0.74 [95% CI 0.71-0.77]) outcomes. fMRI features appeared to predict 3-month outcome (accuracy 0.69-0.78) both alone and when combined with some EEG features (accuracies 0.73-0.84) but not 12-month outcome (larger sample sizes needed). Independent clinical predictors of time to favorable outcome were younger age (hazard ratio [HR] 1.04 [95% CI 1.02-1.06]), traumatic brain injury (HR 1.94 [95% CI 1.04-3.61]), command-following abilities at admission (HR 2.70 [95% CI 1.40-5.23]), initial brain imaging without severe pathological findings (HR 2.42 [95% CI 1.12-5.22]), improving consciousness in the ICU (HR 5.76 [95% CI 2.41-15.51]), and favorable visual-graded EEG (HR 2.47 [95% CI 1.46-4.19]).

CONCLUSIONS

Our results indicate that EEG and fMRI features and readily available clinical data predict short-term outcome of patients with acute DoC and that EEG also predicts 12-month outcome after ICU discharge.

Work-up times in an integrated brain cancer pathway

INTRODUCTION

The integrated brain cancer pathway (IBCP) aims to ensure fast-track diagnostics and treatment for brain cancers in Denmark. This paper focuses on the referral pattern and the time frame of key pathway elements during the first two years following implementation of the IBCP in a regional neurology department.

MATERIAL AND METHODS

All patients (n = 241) enrolled in the IBCP during the two-year period were included. Times from admission to completion of the key elements of the IBCP were used. The referral manner and changes in total neurology work-up time over eight quarters were assessed.

RESULTS

The monthly patient enrollment decreased over the eight quarters studied. Primary care physicians accounted for nearly half of referrals, while one-third were referred from other hospital departments. The mean time from admission to end of diagnostic work-up fell from three days (0-10 days) to two days (0-6 days). Within 24 hours of admission, all patients were seen by a specialist in neurology, 90% had an electrocardiogram and 93% had the required blood-work performed. 94% of the included patients had magnetic resonance imaging of the cerebrum performed.

CONCLUSION

The diagnostic process which was accelerated in the study-period and the total work-up time were generally low throughout. Key work-up items are currently being completed timely. Further improvements are possible. The enrollment rate has fallen to what we expect will be a steady level.

FUNDING

This study was funded by a grant from the Danish Ministry of Health and Interior Affairs 2009 and the Helen Rude Foundation and was approved by the Danish Data Protection Agency.

TRIAL REGISTRATION

not relevant.

A brain cancer pathway in clinical practice

INTRODUCTION

Danish healthcare seeks to improve cancer survival through improved diagnostics, rapid treatment and increased focus on cancer prevention and early help-seeking. In neuro-oncology, this has resulted in the Integrated Brain Cancer Pathway (IBCP). The paper explores how the pathway works in the initial phase in a clinical setting with emphasis on pathway criteria.

MATERIAL AND METHODS

All patients admitted during the first two-year period to a regional neurology department in Denmark and fulfilling the IBCP inclusion criteria were included. Data regarding onset symptoms, diagnosis and time for diagnostic work-up were obtained and supplemented by a retrospective review of patient records. Sensitivities, specificities and positive predictive values of the inclusion criteria were calculated with magnetic resonance imaging scan of the cerebrum as index of validity.

RESULTS

The strength of the pathway inclusion criteria was determined largely by the number of criteria fulfilled and by the type of predominant symptoms. The criteria identified the majority of patients with symptomatic brain malignancy and were also highly predictive of general structural brain lesions.

CONCLUSION

The introduction of the pathway is a major step forward in the efforts to optimize brain cancer patients' illness trajectory.

FUNDING

This study was funded by a grant from the Danish Ministry of Health and Interior Affairs 2009 and the Helen Rude Foundation and has been approved by the Danish Data Protection Agency.

TRIAL REGISTRATION

not relevant.

[Intra- and interobserver variation in capsule endoscopy reviews]

INTRODUCTION

It is unclear which professional groups can and should perform reviews of capsule endoscopy (CE) exams of the GI tract. We investigate whether a junior doctor or an endoscopy nurse can review CE films with the same diagnostic results as a specialist.

MATERIAL AND METHODS

An endoscopy nurse and a junior doctor, both with no CE experience, reviewed 30 CE films twice and noted their findings. A distinction was made between clinically important and non-important findings. An endoscopy specialist and the Given Imaging Review Service reviewed the films once each, and their findings were used as the study's gold standard. Time consumption, intra- and interobserver agreement, sensitivity and specificity were assessed.

RESULTS

The junior doctor improved in speed from 1st to 2nd review, but the nurse did not. Both performed poorly compared with Given Imaging Review Service regarding diagnostic accuracy. The junior doctor improved in diagnostic accuracy from 1st to 2nd review, while the nurse did not. The nurse showed a decrease in sensitivity from 1st to 2nd review from 89% to 62%, whereas the junior doctor's sensitivity increased from 48% to 62%. Both missed many pathological findings and their results were not reproducible.

CONCLUSION

The nurse and junior doctor did not obtain the same diagnostic results as the gold standard. The results raise questions of whether nurses or junior doctors should perform capsule endoscopy reviews.