Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task

Conventional neuropsychological tests do not represent the complex and dynamic situations encountered in daily life. Immersive virtual reality simulations can be used to simulate dynamic and interactive situations in a controlled setting. Adding eye tracking to such simulations may provide highly detailed outcome measures, and has great potential for neuropsychological assessment. Here, participants (83 stroke patients and 103 healthy controls) we instructed to find either 3 or 7 items from a shopping list in a virtual super market environment while eye movements were being recorded. Using Logistic Regression and Support Vector Machine models, we aimed to predict the task of the participant and whether they belonged to the stroke or the control group. With a limited number of eye movement features, our models achieved an average Area Under the Curve (AUC) of .76 in predicting whether each participant was assigned a short or long shopping list (3 or 7 items). Identifying participant as either stroke patients and controls led to an AUC of .64. In both classification tasks, the frequency with which aisles were revisited was the most dissociating feature. As such, eye movement data obtained from a virtual reality simulation contain a rich set of signatures for detecting cognitive deficits, opening the door to potential clinical applications.

The journey is just as important as the destination-Digital neuropsychological assessment provides performance stability measures in patients with acquired brain injury

BACKGROUND

Cognitive performances on neuropsychological paper-and-pencil tests are generally evaluated quantitatively by examining a final score (e.g., total duration). Digital tests allow for a quantitative evaluation of "how" a patient attained a final score, which opens the possibility to assess more subtle cognitive impairment even when final scores are evaluated as normal. We assessed performance stability (i.e., the number of fluctuations in test performance) to investigate (1) differences in performance stability between patients with acquired brain injury (ABI) and healthy controls; (2) the added value of performance stability measures in patients with ABI; and (3) the relation between performance stability and cognitive complaints in daily life in patients with ABI.

METHODS

We administered three digital neuropsychological tests (Rey Auditory Verbal Learning Test, Trail Making Test, Stroop Colour and Word Test) and the Cognitive Complaints-Participation (CoCo-P) inventory in patients with ABI (n = 161) and healthy controls (n = 91).

RESULTS

Patients with ABI fluctuated more in their performance on all tests, when compared to healthy controls. Furthermore, 4-15% of patients who performed inside normal range on the conventional final scores were outside normal range on the performance stability measures. The performance stability measures, nor the conventional final scores, were associated with cognitive complaints in daily life.

CONCLUSIONS

Stability in test performance of patients was clearly dissociable from healthy controls, and may assess additional cognitive weaknesses which might not be observed or objectified with paper-and-pencil tests. More research is needed for developing measures better associated with cognitive complaints.

Cognitive complaints in brain tumor patients and their relatives' perspectives

Background

Cognitive deficits have been frequently assessed in brain tumor patients. However, self-reported cognitive complaints have received little attention so far. Cognitive complaints are important as they often interfere with participation in society. In this study, cognitive complaints were systematically assessed in brain tumor patients. As patients' experiences and relatives' estimations may vary, the level of agreement was investigated.

Methods

Brain tumor outpatients (n = 47) and relatives (n = 42) completed the inventory Cognitive Complaints-Participation, assessing cognitive complaints across 10 daily life activities and cognitive domains (total, memory, executive, attention). Cognitive complaints scores were compared between patients with different clinical characteristics (tumor type, number of treatments, the absence/presence of epilepsy). Complaints difference scores in patient-relative pairs were calculated to explore the level of agreement using intraclass correlations (ICC). Furthermore, we explored whether the level of agreement was related to (1) the magnitude of cognitive complaints in patient-relative pairs and (2) patients' cognitive functioning (assessed with the Montreal Cognitive Assessment).

Results

Patients and relatives reported most cognitive complaints during work/education (100%) and social contacts (88.1%). Patients with different clinical characteristics reported comparable cognitive complaints scores. Overall, the level of agreement in patient-relative pairs was moderate-good (ICC 0.73-0.86). Although in 24% of the pairs, there was a substantial disagreement. The level of agreement was not related to the magnitude of complaints in patient-relative pairs or patients' cognitive functioning.

Conclusion

Both the perspectives of brain tumor patients and their relatives' on cognitive complaints are important. Clinicians could encourage communication to reach mutual understanding.

Digital neuropsychological assessment: Feasibility and applicability in patients with acquired brain injury

INTRODUCTION

Digital neuropsychological assessment (d-NPA) has several advantages over paper-and-pencil tests in neuropsychological assessment, such as a more standardized stimulus presentation and response acquisition. We investigated (1) the feasibility and user-experience of a d-NPA in patients with acquired brain injury (ABI) and healthy controls; (2) the applicability of conventional paper-and-pencil norms on digital tests; and (3) whether familiarity with a tablet would affect test performance on a tablet.

METHOD

We administered a d-NPA in stroke patients (n = 59), traumatic brain injury patients (n = 61) and healthy controls (n = 159). The neuropsychological tests were presented on a tablet and participants used a pencil stylus to respond. We examined the completion rate to assess the feasibility, and a semi-structured interview was conducted to examine the user-experience. The applicability of conventional norms was examined by the number of healthy controls performing <10^th percentile, which was expected to be no more than 10%. The effect of tablet familiarity on test performance was examined with a regression-based model.

RESULTS

Overall, 94% of patients completed the d-NPA. The d-NPA was considered pleasant by patients and healthy controls. Conventional norms that exist for paper-and-pencil tests were not applicable on the digital version of the tests, as up to 34% of healthy controls showed an abnormal performance on half of the tests. Tablet familiarity did not affect test performance on a tablet, indicating that participants who were more experienced with working with a tablet did not perform better on digital tests.

CONCLUSIONS

The administration of a d-NPA is feasible in patients with ABI. Familiarity with a tablet did not impact test performance, which is particularly important in neuropsychological assessment. Future research should focus on developing norms in order to implement a d-NPA in clinical practice.

An overview of screening instruments for cognition and behavior in patients with ALS: selecting the appropriate tool for clinical practice

Objective: Patients with amyotrophic lateral sclerosis (ALS) not only show motor deficits, but may also have cognitive and/or behavioral impairments. Recognizing these impairments is crucial as they are associated with lower quality of life, shorter survival, and increased caregiver burden. Therefore, ALS-specific neuropsychological screening instruments have been developed that can account for motor and speech difficulties. This study provides an overview and comparison of these screeners. Methods: A systematic review was conducted using Medline and Embase. Articles describing cognitive/behavioral screening instruments assessed in ALS patients were included. Screening instruments were compared on multiple factors, such as domains, adaptability, required time, and validation. Results: We included 99 articles, reporting on nine cognitive screeners (i.e. ACE-R, ALS-BCA, ALS-CBS, ECAS, FAB, MMSE, MoCA, PSSFTS, and UCSF-SB), of which five ALS-specific. Furthermore, eight behavioral screeners (i.e. ALS-FTD-Q, AES, BBI, DAS, FBI, FrSBe, MiND-B, and NPI) were reported on, of which three ALS-specific. Conclusion: Considering the broad range of cognitive domains, adaptability, and satisfying validity, the ALS-CBS and ECAS appear to be the most suitable screeners to detect cognitive and behavioral changes in ALS. The BBI appears to be the best option to screen for behavioral changes in ALS, since all relevant domains are assessed, motor-related problems are considered, and has a satisfactory validity. The MiND-B and ALS-FTD-Q are promising as well. In general, all screening instruments would benefit from additional validation research to gain greater insights into test characteristics and to aid clinicians in selecting screening tools for use in clinical practice.

CoCo - participation: The development and clinical use of a novel inventory measuring cognitive complaints in daily life

Cognitive difficulties can be subtle and only come to light when patients return home from inpatient care and start to participate in society. Subjective cognitive complaints often interfere with participation, hence capturing cognitive complaints systematically is important. We developed a patient- and relative-reported measure to assess cognitive complaints during daily life activities across the memory, attention and executive domain for patients with acquired brain injury (ABI). The inventory Cognitive Complaints - Participation (CoCo-P) was created based on a literature review, consultations with experts, semi-structured interviews with patients, and a quantitative study. The inventory was administered to patients with ABI (n = 46), their relatives (n = 33) and healthy controls (n = 102) to finalize the inventory. We examined the reported complaints per daily life activity and cognitive domain of patients and healthy controls, and we compared the patients' and relatives' reports. The majority of patients (87-96%) experienced cognitive complaints, mostly related to attention, at work/education, during leisure activities, and in contact with family/friends and community. Patients reported more cognitive complaints than relatives. The CoCo-P seems appropriate to capture cognitive complaints in daily life in patients with mild ABI. Additional research is needed in terms of reliability and validity.