Prognosis in functional and recognised pathophysiological neurological disorders - a shared basis

Using artificial intelligence to predict patient outcomes from patient-reported outcome measures: a scoping review

PURPOSE

This scoping review aims to identify and summarise artificial intelligence (AI) methods applied to patient-reported outcome measures (PROMs) for prediction of patient outcomes, such as survival, quality of life, or treatment decisions.

INTRODUCTION

AI models have been successfully applied to predict outcomes for patients using mainly clinically focused data. However, systematic guidance for utilising AI and PROMs for patient outcome predictions is lacking. This leads to inconsistency of model development and evaluation, limited practical implications, and poor translation to clinical practice.

MATERIALS AND METHODS

This review was conducted across Web of Science, IEEE Xplore, ACM, Digital Library, Cochrane Central Register of Controlled Trials, Medline and Embase databases. Adapted search terms identified published research using AI models with patient-reported data for outcome predictions. Papers using PROMs data as input variables in AI models for prediction of patient outcomes were included.

RESULTS

Three thousand and seventy-seven records were screened, 94 of which were included in the analysis. AI models applied to PROMs data for outcome predictions are most commonly used in orthopaedics and oncology. Poor reporting of model hyperparameters and inconsistent techniques of handling class imbalance and missingness in data were found. The absence of external model validation, participants' ethnicity information and stakeholders involvement was common.

CONCLUSION

The results highlight inconsistencies in conducting and reporting of AI research involving PROMs in patients' outcomes predictions, which reduces the reproducibility of the studies. Recommendations for external validation and stakeholders' involvement are given to increase the opportunities for applying AI models in clinical practice.

Integrated model of care for functional movement disorder: targeting brain, mind and body

PURPOSE

To describe the therapy approaches and clinical outcomes of an integrated care model for patients with functional movement disorder (FMD).

MATERIALS AND METHODS

A retrospective chart review was conducted for all treated individuals with a primary diagnosis of FMD between January 2020 and July 2022. Patients received time-limited integrated therapy (n = 21) (i.e., simultaneous therapy delivered by psychiatry, neurology and physiotherapy), physiotherapy (n = 18) or virtual physiotherapy alone (n = 9). Primary outcomes included the Simplified-Functional Movement Disorders Rating Scale (S-FMDRS) and Clinical Global Impression-Improvement scale (CGI-I) collected at baseline and post-intervention.

RESULTS

Forty-eight patients completed treatment (42% male; mean age, 48.5 ± 16.6 years, median symptom duration 30 months). The most common presentations were gait disorder, tremor and mixed hyperkinetic FMD. Common comorbidities included pain and fatigue. Three-quarters of patients had a comorbid psychiatric diagnosis. There was a significant reduction in S-FMDRS score following therapy (71%, p < 0.0001) and 69% had "much" or "very much" improved on the CGI-I. There was no difference between therapy groups. Attendance rates were high for both in-person (94%) and virtual (97%) visits.

CONCLUSIONS

These findings support that a time-limited integrated model of care is feasible and effective in treating patients with FMD.

Lessons from a Neurologist After 25 Years of Functional Neurological Disorder Subspeciality Practice

The idea that a neurologist would do an 'FND clinic' or that functional neurological disorder (FND) could be a subspecialty of neurology would have been outlandish even 20 years ago but has become a reality in many places around the world. In this personal review, I reflect on 25 years of being a neurologist with an interest in FND, initially as a research fellow and later as a consultant/attending. I review lessons from diagnosis and management in the hope that they may assist other neurologists embarking on a similar career as well as other health professionals whose roles overlap.

Work difficulties, work restrictions, and disability benefits in people with functional seizures: A survey study

Purpose

Functional seizures (FS) cause significant long-term disability and clinicians offer differing views on proper work restrictions and qualifications for disability benefits in this population. We assess the views and perspectives of experienced disability and work limitations in people living with functional seizures.

Methods

Between (4/29/2020-1/13/2021) an open-access 21-item internet survey was conducted via FNDHope.org; allowing for people living with self-reported functional seizures to remark on topics of work difficulties, work restrictions, qualifications for disability benefits, and driving. Demographic information was collected, and univariate and multivariate logistic regressions were used to evaluate potential predictors of current employment status.

Results

One hundred eighteen (118) responses were received, of which 92 (84.4%) completed > 50% of the survey; they were predominantly (92%) female. Most respondents (88%) reported some personal difficulty at work and nearly all (99%) believed that others with FS would experience difficulties in the workplace. A majority (71%) felt that work restrictions should apply to people living with active FS, at least in certain lines of work. Most (64%) felt people with FS should qualify for disability benefits; however, 35% stated work accommodations or a new job compatible with FS was more appropriate. Of those who felt people with FS should qualify for disability, 60% thought recipients should remain eligible for disability while symptomatic and 38% felt benefits should be lifelong. In univariate and multivariate logistic regressions, older age was predictive of unemployment (univariate OR 0.95 ± 0.02, 95% CI 0.92-0.98, p-value 0.002).

Conclusion

Our results suggest that work difficulties are common in people with FS, with older age being a predictor of unemployment. A majority of people with FS support work restrictions for those with their disorder, at least in some lines of work. In comparison to a prior study of clinicians, a higher percentage of people with FS supported work restrictions. These results may help facilitate productive discussions between people with FS, providers, and policymakers regarding appropriate work and disability limitations.

Diagnosis of Functional Weakness and Functional Gait Disorders in Children and Adolescents

Functional neurological disorder is neurological dysfunction not primarily explained by pathophysiologic or structural abnormalities and can present in children and adolescents with limb weakness, gait abnormality, non-epileptic seizures or sensory changes. In this review article we focus primarily on the diagnosis of functional limb weakness and functional gait disorders, and how to differentiate functional neurological disorders from structural or pathologic neurological presentations of weakness or gait disturbance. Detailed history and attentive observation of a patient outside of the formal neurological examination can be pertinent to identifying inconsistency and incongruency in keeping with functional neurological presentations. Understanding of structural and physiologic neurological pathology is required to identify non-anatomical and non-pathological features consistent with a diagnosis of functional neurological disorder. Diagnosis is made on recognition of positive clinical features of a functional disorder on examination and is not based primarily on exclusion of a pathologic neurological disorder. Specific tests can be performed to elicit pathognomonic findings supportive of a diagnosis of functional limb weakness and gait disorders.