Characterizing Disease Progression in Parkinson's Disease from Videos of the Finger Tapping Test.

INTRODUCTION: Parkinson's disease (PD) is characterized by motor symptoms whose progression is typically assessed using clinical scales, namely the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Despite its reliability, the scale is bounded by a 5-point scale that limits its ability to track subtle changes in disease progression and is prone to subjective interpretations. We aimed to develop an automated system to objectively quantify motor symptoms in PD using Machine Learning (ML) algorithms to analyze videos and capture nuanced features of disease progression. METHODS: We analyzed videos of the Finger Tapping test, a component of the MDS-UPDRS, from 24 healthy controls and 66 PD patients using ML algorithms for hand pose estimation. We computed multiple movement features related to bradykinesia from videos and employed a novel tiered classification approach to predict disease severity that employed different features according to severity. We compared our video-based disease severity prediction approach against other approaches recently introduced in the literature. RESULTS: Traditional kinematics features such as amplitude and velocity changed linearly with disease severity, while other non-traditional features displayed non-linear trends. The proposed disease severity prediction approach demonstrated superior accuracy in detecting PD and distinguishing between different levels of disease severity when compared to existing approaches.

Freeing the Animal Model: A Modular, Wirelessly Powered, Implantable Electronic Platform.

SUMMARY: Fully implantable electronic devices in freely roaming animal models are useful in biomedical research, but their development is prohibitively resource intensive for many laboratories. The advent of miniaturized microcontrollers with onboard wireless data exchange capabilities has enabled cost-efficient development of myriad do-it-yourself electronic devices that are easily customizable with open-source software ( https://www.arduino.cc/ ). Likewise, the global proliferation of mobile devices has led to the development of low-cost miniaturized wireless power technology. The authors present a low-cost, rechargeable, and fully implantable electronic device comprising a commercially available, open-source, wirelessly powered microcontroller that is readily customizable with myriad readily available miniature sensors and actuators. The authors demonstrate the utility of this platform for chronic nerve stimulation in the freely roaming rat with intermittent wireless charging over 4 weeks. Device assembly was achieved within 2 hours and necessitated only basic soldering equipment. Component costs totaled $115 per device. Wireless data transfer and wireless recharging of device batteries was achieved within 30 minutes, and no harmful heat generation occurred during charging or discharging cycles, as measured by external thermography and internal device temperature monitoring. Wireless communication enabled triggered cathodic pulse stimulation of the facial nerve at various user-selected programmed frequencies (1, 5, and 10 Hz) for periods of 4 weeks or longer. This implantable electronic platform could be further miniaturized and expanded to study a vast array of biomedical research questions in live animal models. CLINICAL RELEVANCE STATEMENT: The clinical relevance of electrical stimulation in neural recovery remains controversial, and long-term neural stimulation in small animal models is challenging. We have developed a low-cost, fully implantable, wirelessly powered nerve stimulation device to facilitate further research in nerve stimulation in animal models.

Keratitis in patients with corneal foreign bodies: a cross-sectional study in Cali, Colombia / Ceratite em pacientes com corpos estranhos na córnea: um estudo transversal em Cali, Colômbia

ABSTRACT Purposes: To describe the clinical characteristics and factors associated with keratitis in patients with corneal foreign bodies in Colombia. Methods: This cross-sectional study was based on a clinical records review of patients who had corneal foreign bodies and were admitted to the emergency department between June 2018 and June 2019 in Cali, Colombia. The primary outcome was the presence of keratitis diagnosed based on clinical criteria. Univariate and multivariate logistic regression models were used to identify associated factors. Results: A total of 381 corneal foreign bodies in 372 patients were analyzed (median age, 40.0; interquartile range, 29.0-53.0 years; male, 94.7% (n=352). Ninety-five patients developed keratitis (24.9%, 95% confidence interval [CI] 20.8%-29.5%). In the multivariate analysis, age 30 years (odds ratio [OR] 2.15, 95% CI 1.06-4.36), finding of aqueous flare (OR 2.81, 95% CI 1.39-5.66]), and a foreign body in the peripheral cornea (OR 2.05, 95% CI 1.19-3.50] were associated with an increased risk for keratitis. Sex, time between injury and admission, and corneal edema were not related to keratitis (p>0.05). Conclusion: In Cali, Colombia, a high proportion of keratitis was reported in patients with corneal foreign body. Age, an aqueous flare, and a foreign body in the peripheral cornea were the factors associated with keratitis.

RESUMO Objetivo: Descrever as características clínicas e os fatores associados à presença de ceratite em pacientes com corpos estranhos na córnea em uma população colombiana. Métodos: Trata-se de um estudo transversal baseado na revisão dos registros clínicos de pacientes com corpos estranhos na córnea admitidos em um departamento de emergência em Cali, Colômbia, entre junho de 2018 e junho de 2019. O desfecho primário foi a presença de ceratite diagnosticada através de critérios clínicos. Foram utilizados modelos de regressão logística univariada e multivariada para identificar os fatores associados. Resultado: Neste estudo, foi analisado um total de 381 corpos estranhos na córnea em 372 pacientes (idade média: 40,0 anos, intervalo interquartil: 29,0-53,0; sexo masculino: 94,7% [352 casos]). Noventa e cinco casos desenvolveram ceratite (24,9%, intervalo de confiança de 95% — IC 95%: 20,8%-29,5%). Na análise multivariada, para idade ≤30 anos (razão de chances — RC: 2,15, IC 95%: 1,06-4,36), o achado de flare aquoso (RC: 2,81, IC 95%: 1,39-5,66]) e a presença de corpo estranho na periferia da córnea (RC: 2,05, IC 95%: 1,19-3,50) foram associados a um risco aumentado de ceratite. Sexo, tempo entre a lesão e a internação, e edema da córnea não foram relacionados à ceratite (p>0,05). Conclusão: Há uma proporção elevada de ceratite em casos de corpos estranhos na córnea em Cali, Colômbia. Os três fatores associados à ceratite foram a idade, o achado de flare aquoso e a presença de corpo estranho na periferia da córnea.

Keratitis in patients with corneal foreign bodies: a cross-sectional study in Cali, Colombia.

PURPOSES: To describe the clinical characteristics and factors associated with keratitis in patients with corneal foreign bodies in Colombia. METHODS: This cross-sectional study was based on a clinical records review of patients who had corneal foreign bodies and were admitted to the emergency department between June 2018 and June 2019 in Cali, Colombia. The primary outcome was the presence of keratitis diagnosed based on clinical criteria. Univariate and multivariate logistic regression models were used to identify associated factors. RESULTS: A total of 381 corneal foreign bodies in 372 patients were analyzed (median age, 40.0; interquartile range, 29.0-53.0 years; male, 94.7% (n=352). Ninety-five patients developed keratitis (24.9%, 95% confidence interval [CI] 20.8%-29.5%). In the multivariate analysis, age 30 years (odds ratio [OR] 2.15, 95% CI 1.06-4.36), finding of aqueous flare (OR 2.81, 95% CI 1.39-5.66]), and a foreign body in the peripheral cornea (OR 2.05, 95% CI 1.19-3.50] were associated with an increased risk for keratitis. Sex, time between injury and admission, and corneal edema were not related to keratitis (p>0.05). CONCLUSION: In Cali, Colombia, a high proportion of keratitis was reported in patients with corneal foreign body. Age, an aqueous flare, and a foreign body in the peripheral cornea were the factors associated with keratitis.

Analytical Validation of a Webcam-Based Assessment of Speech Kinematics: Digital Biomarker Evaluation following the V3 Framework.

Introduction: Kinematic analyses have recently revealed a strong potential to contribute to the assessment of neurological diseases. However, the validation of home-based kinematic assessments using consumer-grade video technology has yet to be performed. In line with best practices for digital biomarker development, we sought to validate webcam-based kinematic assessment against established, laboratory-based recording gold standards. We hypothesized that webcam-based kinematics would possess psychometric properties comparable to those obtained using the laboratory-based gold standards. Methods: We collected data from 21 healthy participants who repeated the phrase "buy Bobby a puppy" (BBP) at four different combinations of speaking rate and volume: Slow, Normal, Loud, and Fast. We recorded these samples twice back-to-back, simultaneously using (1) an electromagnetic articulography ("EMA"; NDI Wave) system, (2) a 3D camera (Intel RealSense), and (3) a 2D webcam for video recording via an in-house developed app. We focused on the extraction of kinematic features in this study, given their demonstrated value in detecting neurological impairments. We specifically extracted measures of speed/acceleration, range of motion (ROM), variability, and symmetry using the movements of the center of the lower lip during these tasks. Using these kinematic features, we derived measures of (1) agreement between recording methods, (2) test-retest reliability of each method, and (3) the validity of webcam recordings to capture expected changes in kinematics as a result of different speech conditions. Results: Kinematics measured using the webcam demonstrated good agreement with both the RealSense and EMA (ICC-A values often ≥0.70). Test-retest reliability, measured using the absolute agreement (2,1) formulation of the intraclass correlation coefficient (i.e., ICC-A), was often "moderate" to "strong" (i.e., ≥0.70) and similar between the webcam and EMA-based kinematic features. Finally, the webcam kinematics were typically as sensitive to differences in speech tasks as EMA and the 3D camera gold standards. Discussion and Conclusions: Our results suggested that webcam recordings display good psychometric properties, comparable to laboratory-based gold standards. This work paves the way for a large-scale clinical validation to continue the development of these promising technologies for the assessment of neurological diseases via home-based methods.

3D Video Tracking Technology in the Assessment of Orofacial Impairments in Neurological Disease: Clinical Validation.

PURPOSE: This study sought to determine whether clinically interpretable kinematic features extracted automatically from three-dimensional (3D) videos were correlated with corresponding perceptual clinical orofacial ratings in individuals with orofacial impairments due to neurological disorders. METHOD: 45 participants (19 diagnosed with motor neuron diseases [MNDs] and 26 poststroke) performed two nonspeech tasks (mouth opening and lip spreading) and one speech task (repetition of a sentence "Buy Bobby a Puppy") while being video-recorded in a standardized lab setting. The color video recordings of participants were assessed by an expert clinician-a speech language pathologist-on the severity of three orofacial measures: symmetry, range of motion (ROM), and speed. Clinically interpretable 3D kinematic features, linked to symmetry, ROM, and speed, were automatically extracted from video recordings, using a deep facial landmark detection and tracking algorithm for each of the three tasks. Spearman correlations were used to identify features that were significantly correlated (p value < .05) with their corresponding clinical scores. Clinically significant kinematic features were then used in the subsequent multivariate regression models to predict the overall orofacial impairment severity score. RESULTS: Several kinematic features extracted from 3D video recordings were associated with their corresponding perceptual clinical scores, indicating clinical validity of these automatically derived measures. Different patterns of significant features were observed between MND and poststroke groups; these differences were aligned with clinical expectations in both cases. CONCLUSIONS: The results show that kinematic features extracted automatically from simple clinical tasks can capture characteristics used by clinicians during assessments. These findings support the clinical validity of video-based automatic extraction of kinematic features.

Embellishing Emotrics for a More Complete Emotion Analysis: Addition of the Nasolabial Fold.

Background: The nasolabial fold (NLF) greatly contributes to facial aesthetics; changes to NLF depth and vector are disfiguring in patients with facial paralysis (FP). NLF parameters are integral to clinician-graded outcomes, but automated programs currently lack NLF identification capabilities. Objective: To incorporate an automated NLF identification and quantification function into the facial landmark program, Emotrics, and to compare new Emotrics-derived NLF data to clinician-graded electronic facial paralysis assessment (eFACE) data for accuracy. Methods: Photographs of 135 patients with FP were marked bilaterally, using identification markers manually placed on each NLF. A machine learning model was trained to automatically localize the markers using these data. Once Emotrics accurately identified the NLF and its corresponding vector, photographs of 20 additional patients who underwent facial reanimation procedures were assessed by the algorithm. Results: The enhanced Emotrics algorithm successfully identified the NLF, and measured the vector from midline, in a series of patients with FP. NLF vector data closely matched corresponding eFACE parameters. Furthermore, changes in NLF presence and vector were detected following facial reanimation procedures. Conclusion: The Emotrics program now provides critical NLF data, providing objective parameters for clinicians interested in changing NLF dynamics after FP.

Video-Based Facial Movement Analysis in the Assessment of Bulbar Amyotrophic Lateral Sclerosis: Clinical Validation.

PURPOSE: Facial movement analysis during facial gestures and speech provides clinically useful information for assessing bulbar amyotrophic lateral sclerosis (ALS). However, current kinematic methods have limited clinical application due to the equipment costs. Recent advancements in consumer-grade hardware and machine/deep learning made it possible to estimate facial movements from videos. This study aimed to establish the clinical validity of a video-based facial analysis for disease staging classification and estimation of clinical scores. METHOD: Fifteen individuals with ALS and 11 controls participated in this study. Participants with ALS were stratified into early and late bulbar ALS groups based on their speaking rate. Participants were recorded with a three-dimensional (3D) camera (color + depth) while repeating a simple sentence 10 times. The lips and jaw movements were estimated, and features related to sentence duration and facial movements were used to train a machine learning model for multiclass classification and to predict the Amyotrophic Lateral Sclerosis Functional Rating Scale-Revised (ALSFRS-R) bulbar subscore and speaking rate. RESULTS: The classification model successfully separated healthy controls, the early ALS group, and the late ALS group with an overall accuracy of 96.1%. Video-based features demonstrated a high ability to estimate the speaking rate (adjusted R 2 = .82) and a moderate ability to predict the ALSFRS-R bulbar subscore (adjusted R 2 = .55). CONCLUSIONS: The proposed approach based on a 3D camera and machine learning algorithms represents an easy-to-use and inexpensive system that can be included as part of a clinical assessment of bulbar ALS to integrate facial movement analysis with other clinical data seamlessly.

Automated Spontaneity Assessment after Smile Reanimation: A Machine Learning Approach.

BACKGROUND: Recreation of a spontaneous, emotional smile remains a paramount goal of smile reanimation surgery. However, optimal techniques to reliably restore spontaneity remain unknown. Dual automated machine-learning tools were used to develop an objective tool to analyze spontaneous smiling. The feasibility of this tool was tested in a sample of functional free muscle transfers. METHODS: Validated humorous videos were used to elicit spontaneous smiles. Automated facial landmark recognition (Emotrics) and emotion detection software (Affdex) were used to analyze video clips of spontaneous smiling in nine normal subjects and 39 facial reanimation cases. Emotionality quotient was used to quantify the ability of spontaneous smiles to express joy. RESULTS: The software could analyze spontaneous smiling in all subjects. Spontaneous smiles of normal subjects exhibited median 100 percent joy and 0 percent negative emotion (emotional quotient score, +100/0). Spontaneous smiles of facial palsy patients after smile reanimation, using cross-facial nerve graft, masseteric nerve, and dual innervation, yielded median emotional quotient scores of +82/0, 0/-48, and +10/-24 respectively (joy, p = 0.006; negative emotion, p = 0.034). CONCLUSIONS: Computer vision software can objectively quantify spontaneous smiling outcomes. Of the retrospective sample of cases reviewed in this study, cross-facial nerve graft-innervated gracilis functional free muscle transfer achieved a greater degree of emotionality during spontaneous smiling than masseteric or dually innervated transfer. Quantification of spontaneous smiling from standard video clips could facilitate future, blinded, multicenter trials with sufficient long-term follow-up to definitively establish the rates of spontaneity from a range of reanimation procedures. CLINICAL QUESTION/LEVEL OF EVIDENCE: Diagnostic, IV.

Validating Automatic Diadochokinesis Analysis Methods Across Dysarthria Severity and Syllable Task in Amyotrophic Lateral Sclerosis.

PURPOSE: Oral diadochokinesis (DDK) is a standard dysarthria assessment task. To extract automatic and semi-automatic DDK measurements, numerous DDK analysis algorithms based on acoustic signal processing are available, including amplitude based, spectral based, and hybrid. However, these algorithms have been predominantly validated in individuals with no perceptible to mild dysarthria. The behavior of these algorithms across dysarthria severity is largely unknown. Likewise, these algorithms have not been tested equally for various syllable types. The goal of this study was to evaluate the performance of five common DDK algorithms as a function of dysarthria severity, considering syllable types. METHOD: We analyzed 282 DDK recordings of /ba/, /pa/, and /ta/ from 145 participants with amyotrophic lateral sclerosis. Recordings were stratified into mild, moderate, or severe dysarthria groups based on individual performance on the Speech Intelligibility Test. Analysis included manual and automatic estimation of the number of syllables, DDK rate, and cycle-to-cycle temporal variability (cTV). Validation metrics included Bland-Altman mixed-effects limits of agreement between manual and automatic syllable counts, recall and precision between manual and automatic syllable boundary detection, and Kendall's tau-b correlations between manual and algorithm-detected DDK rate and cTV. RESULTS: The amplitude-based algorithm (absolute energy) yielded the strongest correlations with manual analysis across all severity groups for DDK rate (τ b = 0.7-0.84) and cTV (τ b = 0.7-0.84) and the narrowest limits of agreement (-5.92 to 7.12 syllable difference). Moreover, this algorithm also provided the highest mean recall and precision across severity groups for /ba/ and /pa/, but with significantly more variation for/ta/. CONCLUSIONS: Algorithms based on signal energy analysis appeared to be the most robust for DDK analysis across dysarthria severity and syllable types; however, it remains prone to error against severe dysarthria and alveolar syllable context. Further development is needed to address this important issue.

A Comparative Study of Autologous and Acellular Dermal Matrix Static Cheek Slings in Corrective Surgery for Facial Palsy.

BACKGROUND: Facial palsy causes devastating disability due to loss of facial function as well as social and psychological impairment. Cheek slings are a secondary technique that provide static support to the midface. This study aimed to describe our technique and compare a traditional sling material (tensor fascia lata) with a porcine-derived acellular dermal matrix alternative (Strattice). METHODS: A 5-year case-control retrospective review of consecutive static cheek slings in a tertiary cancer and facial palsy center was performed. Demographic data, risk factors, and complications were collected and compared. Improvement in static smile position was assessed by Emotrics (Massachusetts Eye and Ear Infirmary, Boston, MA) at 3 months. Long-term sling failure was assessed by need for reoperation. RESULTS: The study group comprised 41 patients on which 33 autogenous fascia lata slings and 12 Strattice slings were performed. Medium-term improvement in static smile position was similar between the 2 groups (judged by the Emotrics software), as was complication rate (P = 0.496). Need for revision due to stretching was higher in the Strattice group but did not achieve significance (P = 0.087). Mean follow-up was 38.02 ± 19.17 months. Twelve of 41 patients were deceased at study conclusion. CONCLUSIONS: Fascia lata and Strattice slings provide satisfactory results in restoring symmetry at rest and functional oral competence. Our results suggest that Strattice is a safe sling material with an acceptable risk profile and comparable medium-term maintenance of tensile strength to fascia lata, and should be considered where life expectancy, donor site morbidity, and procedure length are important considerations.

Value Assessment Frameworks in Latin America: "Il buono, il brutto e il cattivo".

OBJECTIVES: Using a taxonomy previously developed, we assessed the strengths and limitations of available value assessment frameworks (VAF) in Latin America. METHODS: Systematic review of peer-reviewed journals, gray literature review, and surveys to ISPOR Latin America Industry Committee members were done to identify and select current VAF. Once selected, independent reviewers, organized by pairs, assessed each framework's input, methodology, and outputs. RESULTS: We assessed 7 of 9 VAF in the region, excluding 2 that were not currently in use. The review included 1 framework developed by a regional entity, and 6 country frameworks for either price assessment or to inform reimbursement. Most of these frameworks had a clear definition of the purpose (6 of 7) but could provide more details on the conceptual approach, including perspectives, methods for obtaining preferences, and the ability to incorporate multiple value dimensions (2 of 7). Most lacked information about inclusions/exclusions of elements included in the framework, and whether it assumes a base case comparator and how it is selected. The description of the evaluation of data sources and their scientific validity was inconsistently reported (3 of 7). Few included an assessment of the intervention's effect on total costs of treating a defined population (2 of 7), or a description of how uncertainty could be incorporated (3 of 7). Finally, potential conflicts of interest among those creating the framework are not sufficiently addressed (0 of 7). CONCLUSIONS: In the 7 frameworks assessed in Latin America, there are opportunities to improve dimensions, methods, and scope. Addressing these issues will strengthen these VAF for policy and clinical decision making.

Reliability Between In-Person and Still Photograph Assessment of Facial Function in Facial Paralysis Using the eFACE Facial Grading System.

Importance: Assessing facial function using high-quality photographs would improve long-term and objective outcomes tracking in facial palsy, facilitate automated facial grading using artificial intelligence algorithms, and allow for remote follow up. Objective: To determine agreement between in-person and photographic electronic facial function scale (eFACE) assessments, and evaluate inter-rater reliability of photographic eFACE evaluation. Design, Setting, and Participants: Retrospective review of eFACE scores from in-person interviews and standardized photographs using the Massachusetts Eye and Ear (MEE) Standard Facial Palsy Dataset. Main Outcomes and Measures: eFACE total scores and subset scores determined by two experienced facial reanimation surgeons in person and from photographs. Results: Intraclass correlation coefficients for eFACE scores were 0.96 (95% CI 0.94 to 0.97) for total scores, 0.99 (95% CI 0.989 to 0.995) for static scores, 0.82 (95% CI 0.74 to 0.88) for dynamic scores, and 0.98 (95% CI 0.97 to 0.99) for synkinesis scores. Photographic and in-person scores had a mean difference of -0.64 (95% CI -2.05 to 0.77; p = 0.37) for total score, -1.58 (95% CI -4.22 to 1.05; p = 0.24) for the static subset, 0.14 (95% CI -1.70 to 1.97; p = 0.88) for the dynamic subset, and -1.11 (95% CI -3.09 to 0.86; p = 0.26) for the synkinetic subset. Bland-Altman analysis showed no trend for increasing differences in total score or subset scores. Conclusions: eFACE assessment obtained via photographs exhibits excellent inter-rater reliability and strong agreement with in-person assessment, demonstrating facial symmetry in facial palsy patients can be monitored using standardized frontal photographs.

A New Dataset for Facial Motion Analysis in Individuals With Neurological Disorders.

We present the first public dataset with videos of oro-facial gestures performed by individuals with oro-facial impairment due to neurological disorders, such as amyotrophic lateral sclerosis (ALS) and stroke. Perceptual clinical scores from trained clinicians are provided as metadata. Manual annotation of facial landmarks is also provided for a subset of over 3300 frames. Through extensive experiments with multiple facial landmark detection algorithms, including state-of-the-art convolutional neural network (CNN) models, we demonstrated the presence of bias in the landmark localization accuracy of pre-trained face alignment approaches in our participant groups. The pre-trained models produced higher errors in the two clinical groups compared to age-matched healthy control subjects. We also investigated how this bias changes when the existing models are fine-tuned using data from the target population. The release of this dataset aims to propel the development of face alignment algorithms robust to the presence of oro-facial impairment, support the automatic analysis and recognition of oro-facial gestures, enhance the automatic identification of neurological diseases, as well as the estimation of disease severity from videos and images.

The Auto-eFACE: Machine Learning-Enhanced Program Yields Automated Facial Palsy Assessment Tool.

BACKGROUND: Facial palsy assessment is nonstandardized. Clinician-graded scales are limited by subjectivity and observer bias. Computer-aided grading would be desirable to achieve conformity in facial palsy assessment and to compare the effectiveness of treatments. This research compares the clinician-graded eFACE scale to machine learning-derived automated assessments (auto-eFACE). METHODS: The Massachusetts Eye and Ear Infirmary Standard Facial Palsy Dataset was employed. Clinician-graded eFACE assessment was performed on 160 photographs. A Python script was used to automatically generate auto-eFACE scores on the same photographs. eFACE and auto-eFACE scores were compared for normal, flaccidly paralyzed, and synkinetic faces. RESULTS: Auto-eFACE and eFACE scores differentiated normal faces from those with facial palsy. Auto-eFACE produced significantly lower scores than eFACE for normal faces (93.83 ± 4.37 versus 100.00 ± 1.58; p = 0.01). Review of photographs revealed minor facial asymmetries in normal faces that clinicians tend to disregard. Auto-eFACE reported better facial symmetry in patients with flaccid paralysis (59.96 ± 5.80) and severe synkinesis (62.35 ± 9.35) than clinician-graded eFACE (52.20 ± 3.39 and 54.22 ± 5.35, respectively; p = 0.080 and p = 0.080, respectively); this result trended toward significance. CONCLUSIONS: Auto-eFACE scores can be obtained automatically using a freely available machine learning-based computer software. Automated scores predicted more asymmetry in normal patients, and less asymmetry in patients with flaccid palsy and synkinesis, compared to clinician grading. Auto-eFACE is a quick and easy-to-use assessment tool that holds promise for standardization of facial palsy outcome measures and may eliminate observer bias seen in clinician-graded scales. CLINICAL QUESTION/LEVEL OF EVIDENCE: Diagnostic, III.

Toward an Automatic System for Computer-Aided Assessment in Facial Palsy.

Importance: Quantitative assessment of facial function is challenging, and subjective grading scales such as House-Brackmann, Sunnybrook, and eFACE have well-recognized limitations. Machine learning (ML) approaches to facial landmark localization carry great clinical potential as they enable high-throughput automated quantification of relevant facial metrics from photographs and videos. However, the translation from research settings to clinical application still requires important improvements. Objective: To develop a novel ML algorithm for fast and accurate localization of facial landmarks in photographs of facial palsy patients and utilize this technology as part of an automated computer-aided diagnosis system. Design, Setting, and Participants: Portrait photographs of 8 expressions obtained from 200 facial palsy patients and 10 healthy participants were manually annotated by localizing 68 facial landmarks in each photograph and by 3 trained clinicians using a custom graphical user interface. A novel ML model for automated facial landmark localization was trained using this disease-specific database. Algorithm accuracy was compared with manual markings and the output of a model trained using a larger database consisting only of healthy subjects. Main Outcomes and Measurements: Root mean square error normalized by the interocular distance (NRMSE) of facial landmark localization between prediction of ML algorithm and manually localized landmarks. Results: Publicly available algorithms for facial landmark localization provide poor localization accuracy when applied to photographs of patients compared with photographs of healthy controls (NRMSE, 8.56 ± 2.16 vs. 7.09 ± 2.34, p ≪ 0.01). We found significant improvement in facial landmark localization accuracy for the facial palsy patient population when using a model trained with a relatively small number photographs (1440) of patients compared with a model trained using several thousand more images of healthy faces (NRMSE, 6.03 ± 2.43 vs. 8.56 ± 2.16, p ≪ 0.01). Conclusions and Relevance: Retraining a computer vision facial landmark detection model with fewer than 1600 annotated images of patients significantly improved landmark detection performance in frontal view photographs of this population. The new annotated database and facial landmark localization model represent the first steps toward an automatic system for computer-aided assessment in facial palsy. Level of Evidence: 4.

Implementing Health Technology Assessments in Latin America: Looking at the Past, Mirroring the Future. A Perspective from the ISPOR Health Technology Assessment Roundtable in Latin America.

OBJECTIVES: In the last two decades, several countries in Latin America (LA) have shown an interest in developing health technology assessments (HTAs), but the process has not been uniform and has often been challenged by the health systems characteristics and the political or economic idiosyncrasies of these countries. METHODS: This article summarizes the discussions held by the participants at the 40th ISPOR HTA Council Roundtable for LA. An additional literature review was carried out to support some of the concepts included. RESULTS: This article includes a brief description of the implementation of HTA over the last 30 years and then a conceptual analysis using examples of the broader use of HTA to support procurement decisions and risk-sharing agreements, which might play a future role in healthcare priority-setting in LA. CONCLUSIONS: Formerly, HTA processes and methods played important although mostly isolated roles (with drug licensing or reimbursement being examples of this). Nowadays, with more and more innovative technologies and the establishment of value frameworks to support the priority setting in healthcare, HTA features a promising panorama for the health systems sustainability.

The spectrum of facial palsy: The MEEI facial palsy photo and video standard set.

OBJECTIVES: Facial palsy causes variable facial disfigurement ranging from subtle asymmetry to crippling deformity. There is no existing standard database to serve as a resource for facial palsy education and research. We present a standardized set of facial photographs and videos representing the entire spectrum of flaccid and nonflaccid (aberrantly regenerated or synkinetic) facial palsy. To demonstrate the utility of the dataset, we describe the relationship between level of facial function and perceived emotion expression as determined by an automated emotion detection, machine learning-based algorithm. METHODS: Photographs and videos of patients with both flaccid and nonflaccid facial palsy were prospectively gathered. The degree of facial palsy was quantified using eFACE, House-Brackmann, and Sunnybrook scales. Perceived emotion during a standard video of facial movements was determined using an automated, machine learning algorithm. RESULTS: Sixty participants were enrolled and categorized by eFACE score across the range of facial function. Patients with complete flaccid facial palsy (eFACE <60) had a significant loss of perceived joy compared to the nonflaccid and normal groups. Additionally, patients with only moderate flaccid and nonflaccid facial palsy had a significant increase in perceived negative emotion (contempt) when compared to the normal group. CONCLUSION: We provide this open-source database to assist in comparing current and future scales of facial function as well as facilitate comprehensive investigation of the entire spectrum of facial palsy. The automated machine learning-based algorithm detected negative emotions at moderate levels of facial palsy and suggested a threshold severity of flaccid facial palsy beyond which joy was not perceived. LEVEL OF EVIDENCE: NA Laryngoscope, 130:32-37, 2020.

Implantable wireless device for study of entrapment neuropathy.

BACKGROUND: Disease processes causing increased neural compartment pressure may induce transient or permanent neural dysfunction. Surgical decompression can prevent and reverse such nerve damage. Owing to insufficient evidence from controlled studies, the efficacy and optimal timing of decompression surgery remains poorly characterized for several entrapment syndromes. NEW METHOD: We describe the design, manufacture, and validation of a device for study of entrapment neuropathy in a small animal model. This device applies graded extrinsic pressure to a peripheral nerve and wirelessly transmits applied pressure levels in real-time. We implanted the device in rats applying low (under 100 mmHg), intermediate (200-300 mmHg) and high (above 300 mmHg) pressures to induce entrapment neuropathy of the facial nerve to mimic Bell's palsy. Facial nerve function was quantitatively assessed by tracking whisker displacements before, during, and after compression. RESULTS: At low pressure, no functional loss was observed. At intermediate pressure, partial functional loss developed with return of normal function several days after decompression. High pressure demonstrated complete functional loss with incomplete recovery following decompression. Histology demonstrated uninjured, Sunderland grade III, and Sunderland grade V injury in nerves exposed to low, medium, and high pressure, respectively. COMPARISON WITH EXISTING METHODS: Existing animal models of entrapment neuropathy are limited by inability to measure and titrate applied pressure over time. CONCLUSIONS: Described is a miniaturized, wireless, fully implantable device for study of entrapment neuropathy in a murine model, which may be broadly employed to induce various degrees of neural dysfunction and functional recovery in live animal models.

Spontaneity Assessment in Dually Innervated Gracilis Smile Reanimation Surgery.

IMPORTANCE: Surgeons have sought to optimize outcomes of smile reanimation surgery by combining inputs from nerve-to-masseter and cross-face nerve grafts. An objective assessment tool could help surgeons evaluate outcomes to determine the optimal neural sources for smile reanimation. OBJECTIVE: To evaluate the use of a novel video time-stamping method and standard outcome measurement tools to assess outcomes of facial reanimation surgery using various innervation strategies. DESIGN, SETTING, AND PARTICIPANTS: Cohort study assessing the outcomes of dually innervated gracilis free muscle transfers vs single-source innervated gracilis transfer performed at a tertiary care facial nerve center between 2007 and 2017 using a novel, video time-stamping spontaneity assessment method. The statistical analyses were performed in 2018. INTERVENTIONS: Dually innervated gracilis free muscle transfers or single-source innervated gracilis transfer. MAIN OUTCOMES AND MEASURES: Spontaneous smiling was assessed by clinicians and quantified using blinded time-stamped video recordings of smiling elicited while viewing humorous video clips. RESULTS: This retrospective cohort study included 25 patients (12 men and 13 women; median [range] age, 38.4 [29.3-46.0] years) treated with dually innervated gracilis free functional muscle graft for unilateral facial palsy between 2007 and 2017. Smile spontaneity assessment was performed in 17 patients and was compared with assessment performed in 24 patients treated with single-source innervated gracilis transfer (ie, nerve-to-masseter-driven or cross-face nerve graft-driven gracilis [n = 13]) (demographic data not available for NTM and CFNG cohorts). The use of time-stamped video assessment revealed that spontaneous synchronous oral commissure movement in a median percentage of smiles was 33% in patients with dually innervated gracilis (interquartile range [IQR], 0%-71%), 20% of smiles in patients with nerve-to-masseter-driven gracilis (IQR, 0%-50%), and 75% of smiles in patients with cross-face nerve graft-driven gracilis (IQR, 0%-100%). Clinicians graded smile spontaneity in dually innervated cases as absent in 40% (n = 6 of 15), trace in 33% (n = 5 of 15) and present in 27% (n = 4 of 15). No association was demonstrated between clinician-reported spontaneity and objectively measured synchronicity. CONCLUSIONS AND RELEVANCE: Dually innervated gracilis free muscle transfers may improve smile spontaneity compared with masseteric nerve-driven transfers but not to the level of cross-face nerve graft-driven gracilis transfers. Quantifying spontaneity is notoriously difficult, and most authors rely on clinical assessment. Our results suggest that clinicians may rate presence of spontaneity higher than objective measures, highlighting the importance of standardized assessment techniques. LEVEL OF EVIDENCE: 4.