Towards a Comprehensive Solution for a Vision-based Digitized Neurological Examination

The ability to use digitally recorded and quantified neurological exam information is important to help healthcare systems deliver better care, in-person and via telehealth, as they compensate for a growing shortage of neurologists. Current neurological digital biomarker pipelines, however, are narrowed down to a specific neurological exam component or applied for assessing specific conditions. In this paper, we propose an accessible vision-based exam and documentation solution called Digitized Neurological Examination (DNE) to expand exam biomarker recording options and clinical applications using a smartphone/tablet. Through our DNE software, healthcare providers in clinical settings and people at home are enabled to video capture an examination while performing instructed neurological tests, including finger tapping, finger to finger, forearm roll, and stand-up and walk. Our modular design of the DNE software supports integrations of additional tests. The DNE extracts from the recorded examinations the 2D/3D human-body pose and quantifies kinematic and spatio-temporal features. The features are clinically relevant and allow clinicians to document and observe the quantified movements and the changes of these metrics over time. A web server and a user interface for recordings viewing and feature visualizations are available. DNE was evaluated on a collected dataset of 21 subjects containing normal and simulated-impaired movements. The overall accuracy of DNE is demonstrated by classifying the recorded movements using various machine learning models. Our tests show an accuracy beyond 90% for upper-limb tests and 80% for the stand-up and walk tests.

Evaluation of upper limb function with digitizing tablet-based tests: reliability and discriminative validity in healthy persons and patients with neurological disorders

PURPOSE

To evaluate discriminative validity, relative reliability and absolute reliability of four tablet-based tests for the evaluation of upper limb motor function in healthy persons and patients with neurological disorders.

METHODS

Cross-sectional study in 54 participants: 29 patients with upper limb movement impairment due to a neurological condition recruited from an inpatient rehabilitation centre and 25 healthy persons. Accuracy, speed and path length were analysed for four tablet-based tests: "Spiral drawings," "Tapping," "Follow the dot" and "Trace a star." The area under the receiver operating characteristic curve (AUC) was used to evaluate discriminative validity. Relative reliability was analysed with the intra-class correlation coefficient (ICC), and absolute reliability by limits of agreement (LoA) and minimal detectable difference (MDD).

RESULTS

All four tests showed excellent discriminative validity for the parameter accuracy (AUC 0.93-0.98). Tapping was the best test for discriminating patients from healthy persons. Test-retest reliability was good for accuracy in all tests (ICC = 0.76-0.88), but poor to moderate for speed and path length (ICC = 0.20-0.69). The MDD varied between 14% and 38%. Performance on the four tablet-based tests was stable between sessions, indicating that there was no learning effect.

CONCLUSION

The parameter accuracy showed excellent discriminative validity and reliability in all four tablet-based tests. Discriminative validity was excellent for all three parameters in the Tapping test. In the other tasks speed showed good to poor reliability, while the reliability of path-length was poor in all tasks. Results were comparable for the dominant and non-dominant hand. Tablet-based tests have the advantage that patients can use them for self-monitoring of upper limb motor function.Implications for rehabilitationFour tablet-based tests for the assessment of upper limb motor function in patients with upper limb neurological dysfunction were evaluated: "Spiral drawings", "Tapping", "Follow the dot" and "Trace a star". The parameter accuracy in these four tests had excellent discriminative validity and good reliability.Patients can perform the tests independently at home for self-monitoring of progress. This may increase patients' motivation to exercise at home.The results can be sent to physicians, enabling the earlier detection of deterioration, which may require medical attention.

Precision Medicine in Parkinson's Disease - Exploring Patient-Initiated Self-Tracking

Background:

Individually tailored healthcare, in the form of precision medicine, holds substantial potential for the future of medicine, especially for a complex disorder like Parkinson’s disease (PD). Patient self-tracking is an under-researched area in PD.

Objective:

This study aimed to explore patient-initiated self-tracking in PD and discuss it in the context of precision medicine.

Methods:

The first author used a smartphone app to capture finger-tapping data and also noted times for medication intakes.

Results:

Data were collected during four subsequent days. Only data from the first two days were complete enough to analyze, leading to the realization that the collection of data over a period of time can pose a significant burden to patients. From the first two days of data, a dip in finger function was observed around the time for the second medication dose of the day.

Conclusions:

Patient-initiated self-tracking enabled the first author to glean important insights about how her PD symptoms varied over the course of the day. Symptom tracking holds great potential in precision medicine and can, if shared in a clinical encounter, contribute to the learning of both patient and clinician. More work is needed to develop this field and extra focus needs to be given to balancing the burden of tracking for the patient against any expected benefit.

The effect of continuous levodopa treatment during the afternoon hours

OBJECTIVE

The aim of this retrospective study was to investigate whether patients with Parkinson's disease, who are treated with levodopa-carbidopa intestinal gel (LCIG), clinically worsen during the afternoon hours and if so, to evaluate whether this occurs in all LCIG-treated patients or in a subgroup of patients.

METHODS

Three published studies were identified and included in the analysis. All studies provided individual response data assessed on the treatment response scale (TRS), and patients were treated with continuous LCIG. Ninety-eight patients from the three studies fulfilled the criteria. t tests were performed to find differences on the TRS values between the morning and the afternoon hours, linear mixed effect models were fitted on the afternoon hours' evaluations to find trends of wearing-off, and patients were classified into three TRS categories (meaningful increase in TRS, meaningful decrease in TRS, non-meaningful increase or decrease).

RESULTS

In all three studies, significant statistical differences were found between the morning TRS values and the afternoon TRS values (P-value <=0.001 in all studies). The linear mixed effect models had significant negative coefficients for time in two studies, and 48 out of 98 patients (49%) showed a meaningful decrease in TRS during the afternoon hours.

CONCLUSION

The results from all studies were consistent, both in the proportion of patients in the three groups and in the value of TRS decrease in the afternoon hours. Based on these findings, there seems to be a group of patients with predictable "off" behavior in the later parts of the day.

Vision-based assessment of parkinsonism and levodopa-induced dyskinesia with pose estimation

BACKGROUND

Despite the effectiveness of levodopa for treatment of Parkinson's disease (PD), prolonged usage leads to development of motor complications, most notably levodopa-induced dyskinesia (LID). Persons with PD and their physicians must regularly modify treatment regimens and timing for optimal relief of symptoms. While standardized clinical rating scales exist for assessing the severity of PD symptoms, they must be administered by a trained medical professional and are inherently subjective. Computer vision is an attractive, non-contact, potential solution for automated assessment of PD, made possible by recent advances in computational power and deep learning algorithms. The objective of this paper was to evaluate the feasibility of vision-based assessment of parkinsonism and LID using pose estimation.

METHODS

Nine participants with PD and LID completed a levodopa infusion protocol, where symptoms were assessed at regular intervals using the Unified Dyskinesia Rating Scale (UDysRS) and Unified Parkinson's Disease Rating Scale (UPDRS). Movement trajectories of individual joints were extracted from videos of PD assessment using Convolutional Pose Machines, a pose estimation algorithm built with deep learning. Features of the movement trajectories (e.g. kinematic, frequency) were used to train random forests to detect and estimate the severity of parkinsonism and LID. Communication and drinking tasks were used to assess LID, while leg agility and toe tapping tasks were used to assess parkinsonism. Feature sets from tasks were also combined to predict total UDysRS and UPDRS Part III scores.

RESULTS

For LID, the communication task yielded the best results (detection: AUC = 0.930, severity estimation: r = 0.661). For parkinsonism, leg agility had better results for severity estimation (r = 0.618), while toe tapping was better for detection (AUC = 0.773). UDysRS and UPDRS Part III scores were predicted with r = 0.741 and 0.530, respectively.

CONCLUSION

The proposed system provides insight into the potential of computer vision and deep learning for clinical application in PD and demonstrates promising performance for the future translation of deep learning to PD clinical practices. Convenient and objective assessment of PD symptoms will facilitate more frequent touchpoints between patients and clinicians, leading to better tailoring of treatment and quality of care.

Reliability of Lagged Poincaré Plot Parameters in Ultrashort Heart Rate Variability Series: Application on Affective Sounds

The number of studies about ultrashort cardiovascular time series is increasing because of the demand for mobile applications in telemedicine and e-health monitoring. However, the current literature still needs a proper validation of heartbeat nonlinear dynamics assessment from ultrashort time series. This paper reports on the reliability of the Lagged Poincaré Plot (LPP) parameters-calculated from ultrashort cardiovascular time series. Reliability is studied on simulated as well as on real RR series. Simulated RR series are generated and LPP parameters estimated for ultrashort time series (from 15 to 60 s) are compared to those estimated from 1 h. All LPP parameters estimated from time series longer than 35 s presented a Spearman's correlation coefficient higher than 0.99. RR series acquired from 32 healthy subjects during 5-min resting state sessions are used to test the LPP approach in experimental data. The usefulness of ultrashort term parameters in real data is accomplished also studying their ability to discriminate positive and negative valence of auditory stimuli taken from the International Affective Digitized Sound System (IADS) dataset. The achieved accuracies in the recognition of elicitation along the valence dimension, using only the LPP parameters, were of 77.78% for 1 min 28 s series, and of 79.17% for 35 s series.