Future Evaluation Research Articles

Disorder-specific versus transdiagnostic cognitive mechanisms in anxiety and depression: Machine-learning-based prediction of symptom severity

IntroductionPsychiatric evaluation of anxiety and depression is currently based on self-reported symptoms and their classification into discrete disorders. Yet the substantial overlap between these disorders as well as their within-disorder heterogeneity may contribute to the mediocre success rates of treatments. The proposed research examines a new framework for diagnosis that is based on alterations in underlying cognitive mechanisms. In line with the Research Domain Criteria (RDoC) approach, the current study directly compares disorder-specific and transdiagnostic cognitive patterns in predicting the severity of anxiety and depression symptoms. MethodsThe sample included 237 individuals exhibiting differing levels of anxiety and depression symptoms, as measured by the STAI-T and BDI-II. Random Forest regressors were used to analyze their performance on a battery of six computerized cognitive-behavioral tests targeting selective and spatial attention, expectancy, interpretation, memory, and cognitive control biases. ResultsUnique anxiety-specific biases were found, as well as shared anxious-depressed bias patterns. These cognitive biases exhibited relatively high fitting rates when predicting symptom severity (questionnaire scores common range 0–60, MAE = 6.03, RMSE = 7.53). Interpretation and expectancy biases exhibited the highest association with symptoms, above all other individual biases. LimitationsAlthough internal validation methods were applied, models may suffer from potential overfitting due to sample size limitations. ConclusionIn the context of the ongoing dispute regarding symptom-centered versus transdiagnostic approaches, the current study provides a unique comparison of these two views, yielding a novel intermediate approach. The results support the use of mechanism-based dimensional diagnosis for adding precision and objectivity to future psychiatric evaluations.

Machine Learning Model for Readmission Prediction of Patients With Heart Failure Based on Electronic Health Records: Protocol for a Quasi-Experimental Study for Impact Assessment.

Care for patients with heart failure (HF) causes a substantial load on health care systems where a prominent challenge is the elevated rate of readmissions within 30 days following initial discharge. Clinical professionals face high levels of uncertainty and subjectivity in the decision-making process on the optimal timing of discharge. Unwanted hospital stays generate costs and cause stress to patients and potentially have an impact on care outcomes. Recent studies have aimed to mitigate the uncertainty by developing and testing risk assessment tools and predictive models to identify patients at risk of readmission, often using novel methods such as machine learning (ML). This study aims to investigate how a developed clinical decision support (CDS) tool alters the decision-making processes of health care professionals in the specific context of discharging patients with HF, and if so, in which ways. Additionally, the aim is to capture the experiences of health care practitioners as they engage with the system's outputs to analyze usability aspects and obtain insights related to future implementation. A quasi-experimental design with randomized crossover assessment will be conducted with health care professionals on HF patients' scenarios in a region located in the South of Sweden. In total, 12 physicians and nurses will be randomized into control and test groups. The groups shall be provided with 20 scenarios of purposefully sampled patients. The clinicians will be asked to take decisions on the next action regarding a patient. The test group will be provided with the 10 scenarios containing patient data from electronic health records and an outcome from an ML-based CDS model on the risk level for readmission of the same patients. The control group will have 10 other scenarios without the CDS model output and containing only the patients' data from electronic medical records. The groups will switch roles for the next 10 scenarios. This study will collect data through interviews and observations. The key outcome measures are decision consistency, decision quality, work efficiency, perceived benefits of using the CDS model, reliability, validity, and confidence in the CDS model outcome, integrability in the routine workflow, ease of use, and intention to use. This study will be carried out in collaboration with Cambio Healthcare Systems. The project is part of the Center for Applied Intelligent Systems Research Health research profile, funded by the Knowledge Foundation (2021-2028). Ethical approval for this study was granted by the Swedish ethical review authority (2022-07287-02). The recruitment process of the clinicians and the patient scenario selection will start in September 2023 and last till March 2024. This study protocol will contribute to the development of future formative evaluation studies to test ML models with clinical professionals. PRR1-10.2196/52744.

New insights and potential biomarkers for intraventricular hemorrhage in extremely premature infant, case-control study.

Despite advancements in neonatal care, germinal matrix-intraventricular hemorrhage impacts 20% of very preterm infants, exacerbating their neurological prognosis. Understanding its complex, multifactorial pathophysiology and rapid onset remains challenging. This study aims to link specific cord blood biomolecules at birth with post-natal germinal matrix-intraventricular hemorrhage onset. A monocentric, prospective case-control study was conducted at Rouen University Hospital from 2015 to 2020. Premature newborns ( < 30 gestational age) were included and cord blood was sampled in the delivery room. A retrospective matching procedure was held in 2021 to select samples for proteomic and metabolomic analysis of 370 biomolecules. 26 patients with germinal matrix-intraventricular hemorrhage cases and 60 controls were included. Clinical differences were minimal, except for higher invasive ventilation rates in the germinal matrix-intraventricular hemorrhage group. Germinal matrix-intraventricular hemorrhage newborns exhibited lower phosphatidylcholine levels and elevated levels of four proteins: BOC cell adhesion-associated protein, placental growth factor, Leukocyte-associated immunoglobulin-like receptor 2, and tumor necrosis factor-related apoptosis-inducing ligand receptor 2. This study identifies biomolecules that may be linked to subsequent germinal matrix-intraventricular hemorrhage, suggesting heightened vascular disruption risk as an independent factor. These results need further validation but could serve as early germinal matrix-intraventricular hemorrhage risk biomarkers for future evaluations. Decrease in certainphosphatidylcholines and increase in four proteins in cord blood at birthmay be linked to subsequent germinal matrix-intraventricular hemorrhagein premature newborns. The four proteins are BOC cell adhesion-associated protein, placental growth factor, leukocyte-associated immunoglobulin-like receptor 2, and TNF-related apoptosis-inducing ligand receptor 2. This biological imprint could point toward higher vascular disruption risk as an independent risk factor for this complication and with further validations, could be used for better stratification of premature newborns at birth.

SISTEM EVALUASI PELANGGARAN LALU LINTAS NTMC POLRI DENGAN ALGORITMA FUZZY LOGIC BERBASIS PYTHON

This research aims to build a traffic violation system using a fuzzy logic algorithm based on the Python language. By utilizing input components to receive traffic violation data and output components to produce traffic understanding level values. This method is used to process data based on traffic violations, system test results show the system's accuracy. To confirm the system's capabilities in traffic violations provides a baseline assessment of the level of accurate understanding of police law. The implications of this system show its potential as an effective detection tool for measuring existing legal violations from various levels of a person's understanding, especially in the legal field. Taking this research into account could provide a strong foundation for the development of similar systems in a variety of future comprehension evaluation contexts

SISTEM EVALUASI PELANGGARAN LALU LINTAS NTMC POLRI DENGAN ALGORITMA FUZZY LOGIC BERBASIS PYTHON

This research aims to build a traffic violation system using a fuzzy logic algorithm based on the Python language. By utilizing input components to receive traffic violation data and output components to produce traffic understanding level values. This method is used to process data based on traffic violations, system test results show the system's accuracy. To confirm the system's capabilities in traffic violations provides a baseline assessment of the level of accurate understanding of police law. The implications of this system show its potential as an effective detection tool for measuring existing legal violations from various levels of a person's understanding, especially in the legal field. Taking this research into account could provide a strong foundation for the development of similar systems in a variety of future comprehension evaluation contexts

A Brief Intervention to Teach Parents Naturalistic Language Facilitation Strategies.

This proof of concept study assessed the feasibility of a novel approach to teaching parents naturalistic language facilitation strategies in a single session. We investigated whether parents could learn to use the See and Say Sequence, which integrated responsive and language modeling strategies and measured the impacts that this intervention had on features of their input. Fourteen parent-child dyads participated in the study. Children ranged from 15 to 23 months of age and produced between three and 135 words. Five parents had concerns about their children's rate of language development. Parents were taught the See and Say Sequence during a brief single session (M = 18.98 min, SD = 2.65 min) using the Teach-Model-Coach-Review instructional process. We analyzed parents' use of the three See and Say Sequence components, total number of utterances, and mean turn length, as well as responsive and linguistic features of parent input before and after the brief intervention. Following intervention, parents significantly increased their use of the three See and Say Sequence components and decreased their total number of utterances and mean turn length. In addition, the use of the See and Say Sequence components substantially altered the overall composition of parent input. The results of this preliminary study demonstrate the feasibility of the See and Say Sequence in teaching responsive and language modeling strategies in a single session. We discuss the potential use and future evaluation of the See and Say Sequence as an option for early intervention service delivery.

Impact of Traditional and New Media on Smoking Intentions and Behaviors: Secondary Analysis of Tasmania's Tobacco Control Mass Media Campaign Program, 2019-2021.

Tasmania, the smallest state by population in Australia, has a comprehensive tobacco control mass media campaign program that includes traditional (eg, television) and "new" channels (eg, social media), run by Quit Tasmania. The campaign targets adult smokers, in particular men aged 18-44 years, and people from low socioeconomic areas. This study assesses the impact of the 2019-2021 campaign program on smokers' awareness of the campaign program, use of Quitline, and smoking-related intentions and behaviors. We used a tracking survey (conducted 8 times per year, immediately following a burst of campaign activity) to assess campaign recall and recognition, intentions to quit, and behavioral actions taken in response to the campaigns. The sample size was approximately 125 participants at each survey wave, giving a total sample size of 2000 participants over the 2 years. We merged these data with metrics including television target audience rating points, digital and Facebook (Meta) analytics, and Quitline activity data, and conducted regression and time-series modeling. Over the evaluation period, unprompted recall of any Quit Tasmania campaign was 18%, while prompted recognition of the most recent campaign was 50%. Over half (52%) of those who recognized a Quit Tasmania campaign reported that they had performed or considered a quitting-related behavioral action in response to the campaign. In the regression analyses, we found having different creatives within a single campaign burst was associated with higher campaign recall and recognition and an increase in the strength of behavioral actions taken. Higher target audience rating points were associated with higher campaign recall (but not recognition) and an increase in quit intentions, but not an increase in behavioral actions taken. Higher Facebook advertisement reach was associated with lower recall among survey participants, but recognition was higher when digital channels were used. The time-series analyses showed no systematic trends in Quitline activity over the evaluation period, but Quitline activity was higher when Facebook reach and advertisement spending were higher. Our evaluation suggests that a variety of creatives should be used simultaneously and supports the continued use of traditional broadcast channels, including television. However, the impact of television on awareness and behavior may be weakening. Future campaign evaluations should closely monitor the effectiveness of television as a result. We are also one of the first studies to explicitly examine the impact of digital and social media, finding some evidence that they influence quitting-related outcomes. While this evidence is promising for campaign implementation, future evaluations should consider adopting rigorous methods to further investigate this relationship.

A Combination of Three Scales for Measuring User-Perceived Usability of a Clinical Information System: Which Approach Produces the Most Informative Results?

Introduction: For the first time in Iran, a kidney stone clinical information system (CIS) has been designed to manage and calculate and visualize patients’ kidney stone risk profiles. Nevertheless, the usability of this system has not been evaluated yet. Medically, this study aims to evaluate the user-perceived usability of the kidney stone CIS. Technically, the current study aims to determine which user-perceived usability testing approach produces the most informative results about the usability of this system.Material and Methods: Three questionnaires, including system usability scale (SUS), software usability measurement inventory (SUMI), and post-study system usability questionnaire, were applied to carry out the study. A total of 15 users of the kidney stone CIS participated.Results: The findings revealed that the system is of medium usability. Moreover, of the three methods used, the SUMI echoes the comments of the end-users. Despite the medium usability of the system, it was comprehensive in terms of proper data collection and storage, as well as reporting. The interface design, the lack of appropriate guidance, the time-consuming data entry, and the slow reporting system were aspects needed improvement.Conclusion: Using a combination of tools is recommended for usability evaluation. Since there is much space in the Global and each sub-scale, whereby measures may improve with SUMI, this research recommends its use for future evaluation of the kidney stone CIS.

Are Chinese live hog futures useful hedging tools?

ABSTRACT China’s newly listed live hog futures provide a standardized risk management tool for the hog market. Our paper provides the first systematic and quantitative evaluation of live hog futures’ hedging ability based on various traditional static and dynamic hedging models and an innovative quantile hedging model. Consistent results confirm that live hog futures are useful hedging tools. Specifically, the in-sample results of multiple traditional models show that the hedging ratios are around 0.4 and hedging effectiveness is 0.13. Out-of-sample hedging effectiveness increases significantly to 0.22. Quantile hedging results show more significant risk-management ability in bearish and average futures markets. We further compare live hog futures’ hedging effectiveness and market performance to other commodities. The comparison shows that the live hog futures market has modest hedging effectiveness and underperforms in liquidity, volatility, and basis. Following the empirical results, it is recommended to encourage hedging transactions, simplify trading processes, and enable night trading to enhance liquidity, lower volatility, and eventually improve hedging ability.

Challenges in developing therapies in fragile X syndrome: how the FXLEARN trial can guide research.

Fragile X syndrome (FXS), the most common inherited cause of intellectual disability and the single-gene cause of autism, is caused by decreased expression of the fragile X messenger ribonucleoprotein protein (FMRP), a ribosomal-associated RNA-binding protein involved in translational repression. Extensive preclinical work in several FXS animal models supported the therapeutic potential of decreasing metabotropic glutamate receptor (mGluR) signaling to correct translation of proteins related to synaptic plasticity; however, multiple clinical trials failed to show conclusive evidence of efficacy. In this issue of the JCI, Berry-Kravis and colleagues conducted the FXLEARN clinical trial to address experimental design concerns from previous trials. Unfortunately, despite treatment of young children with combined pharmacological and learning interventions for a prolonged period, no efficacy of blocking mGluR activity was observed. Future systematic evaluation of potential therapeutic approaches should evaluate consistency between human and animal pathophysiological mechanisms, utilize innovative clinical trial design from FXLEARN, and incorporate translatable biomarkers.

Effectiveness, cost-effectiveness and return on investment of individual placement and support compared with traditional vocational rehabilitation for individuals with severe mental illness in the Netherlands: a nationwide implementation study

ObjectivesTo assess the effectiveness, cost-effectiveness and return on investment of individual placement and support (IPS) implemented through a reimbursement strategy on a nationwide scale compared with traditional vocational rehabilitation (TVR)...

Design, protocol and baseline data of Nurturing Healthy Teachers, a cluster non-randomized controlled trial to improve the health, well-being, and food security of preschool and elementary school teachers in Houston, Texas

BackgroundWe present the conceptual framework, design, and study measures of Nurturing Healthy Teachers, a quasi-experimental study to examine the short- and long-term effectiveness of the Nurturing Healthy Teachers (NHT) nutrition intervention on food insecurity, dietary behaviors, mental health and cardiometabolic health among preschool and elementary school teachers. MethodsA convenience sample of 28 elementary schools with pre-kindergarten and elementary classrooms were recruited in Houston, Texas. Nurturing Healthy Teacher intervention includes Brighter Bites, an evidence-based coordinated school health program that combines access to fresh produce and nutrition education, and Create Healthy Futures, a web-based nutrition education program that targets nutrition knowledge, self-efficacy, mindfulness, and social support to create healthy habits among teachers. The primary outcome is food insecurity. Secondary outcomes include diet quality, mental health, and cardiometabolic health. Metabolic markers and skin carotenoid levels were assessed using in-person assessments, while all other measures were obtained via questionnaire. ResultsAt baseline, most of the participants were female, 63 % identified as Hispanic, were highly educated, and had a mean age of 42.6 years. Overall, 50 % of teachers were classified as being obese and 20 % had high cholesterol. At baseline teachers had a mean HbA1c (%) of 5.6 %.Moderate to severe depression was experienced by 18 % of teachers and 23 % of teachers experienced moderate to severe anxiety. ConclusionsThe results of this study will inform next steps towards future implementation and evaluation of teacher-focused interventions.

Utilising existing data for a pilot social return on investment analysis of the family wellbeing empowerment program: A justification and framework

Demand is growing in the public, private, and philanthropic sectors for economic and quantifiable outcome data to guide decisions regarding the allocation of resources. This paper explores the challenges and opportunities in economically evaluating an Aboriginal Social and Emotional Wellbeing intervention, emphasising the value of utilising existing data. Driven by local and national Indigenous research priorities, the study involved a pilot Social Return on Investment analysis of the Aboriginal Family Wellbeing empowerment program. Underpinned by a collaborative mixed-methods approach, designed to mitigate data limitations and bolster trustworthiness, the analysis was undertaken across four stages, including a literature review to identify impacts and create a theory of change; co-design of an impacts framework; a targeted literature review to inform impact quantification and attribution; and calculation of the Social Return on Investment results. Results indicate that for every Australian dollar of investment in delivering Family Wellbeing between 2001 and 2021 in the Yarrabah Aboriginal community, A$4.60 of benefits were produced for participants and the community. The return is expected to be higher if important community and cultural impacts of the program were included in the monetisation. Data limitations and implications for future mixed methods economic evaluation of social interventions are explored.

Leveraging the Potential of the African Continental Free Trade Area: Logistics Challenges and Development Paths for Future Value Chains in Africa

Background: With a rapidly growing young population, the African continent provides a high but barely exploited economic potential. Creating an African free trade zone is one of the African Union’s major initiatives to increase prosperity. Even though the AfCFTA has already come into force, its potential has not yet been fully exploited. This study investigates the logistics challenges associated with the AfCFTA and potential solutions and development paths for future value chains. Methods: The study builds upon a two-stage research process. First, applying the Nominal Group Technique with a group of 19 industry experts, current challenges and strategies to deal with them are conducted, and statements about potential development paths emerging from the AfCFTA are synthesized. Second, a questionnaire among additional industry experts is done to assess the results of the first stage. Results: The article sheds light on the barely untapped field of logistics challenges hindering the AfCFTA to leverage its potential. Strategy fields to address current challenges are explained, and the first indications of how the AfCFTA will shape supply chains in the mid-term are outlined. Conclusions: The article underlines the importance of logistics in the development of pan-African value chains and highlights potential development paths that may arise in the medium term. It also emphasizes the growing need for cooperation between politics, business, and research to overcome current logistics challenges and leverage the potential of the AfCFTA.

Lessons learned from an occupational therapy programme needs assessment

Background: A needs assessment identifies the differences between actual and ideal situations to facilitate the development of a new programme or improve existing services.Objectives: This article shares our experiences conducting the needs assessment in a context where people had limited or no understanding of the need being assessed.Method: Adhering to a three-phase model – comprising pre-assessment, assessment, and post-assessment – we employed diverse data collection methods, including quantitative survey, qualitative interviews, and environmental scan.Results: The findings underscored the necessity of expanding rehabilitation services in Ethiopia, with a shift from a purely medical focus to addressing issues associated with daily functioning and community engagement. These issues align closely with the core expertise and responsibilities of occupational therapists. Participants expressed support for the introduction of occupational therapy in Ethiopia and willingness to incorporate the practice of occupational therapists in their settings. The challenges encountered were how to ask about occupational therapy when it is not well known by members of the local population and how to introduce the profession without biasing participants’ responses.Conclusion: Conducting a needs assessment was critical to developing occupational therapy services in Ethiopia. We welcome others to learn from our experiences.Contribution: This manuscript details the assessment process and delves into the challenges we encountered and lessons learned. It extends methodological suggestions to inform future evaluations and contributes valuable insights to the broader discourse on needs assessment and programme development in a context where people have limited awareness of services, such as occupational therapy.

Transforming homeownership: an innovative financing model with a future value approach

Purpose This study aims to address the critical need for innovative financing solutions in the global housing sector, focusing specifically on Malaysia’s distinct housing finance system encompassing both conventional and Islamic loans. The primary objective is to develop a transformative housing finance model that addresses affordability challenges and reshapes the Malaysian housing landscape. Design/methodology/approach The study presents an alternate housing finance model for Malaysia, integrating lower monthly payments and reduced household debt. Key variables include house price appreciation rates, interest rates, initial guarantee fees and loan-to-value ratios. Inspired by the Help to Buy (HTB) scheme, the model aligns with proven global initiatives for enhanced affordability, balancing payment amounts, loan interest rates and acceptable price thresholds. Findings The study’s findings promise to address affordability disparities and reshape Malaysia’s housing finance landscape. The emphasis is on introducing a structured repayment plan that offers a sustainable path to homeownership, particularly for low-income families. Incorporating the future value adaptation concept, inspired by reverse mortgages and Islamic finance, enhances adaptability, ensuring long-term sustainability despite economic shifts. Practical implications The proposed model promotes widespread access to homeownership, offering practical solutions for policymakers to improve affordability, prompting adaptable risk management strategies for financial institutions and empowering potential homebuyers with increased flexibility. Originality/value The study introduces a transformative housing finance model for Malaysia, merging elements from reverse mortgages, Islamic finance and the HTB scheme, offering potential applicability to similar systems globally.

Methodology for Developing an IoT-based Parking Space Counter System using XNO

The Blockchain-IoT integration is treated as the future technological value by many adopters despite the cost or complexity involved. But, there are technological advancements brought in by communities that make solutions affordable and simple to the fact that they can be used in applications such as parking space counters. This research portrays use of XNO which is a digital currency in an alternative way to keep track of available parking spaces via IoT nodes installed at entry and exit points of parking lots. The available parking spaces data using this approach can be displayed on LED boards at the entry point of the parking lots and on a website for remote status view. An add-on for this research is the issue of entry tickets with timestamp and unique ID by using the block data during asset transfer. This research can be further enhanced for collection of parking fees by the help of IoT nodes at the exit points of the parking lots.

Economic evaluation of the removal of hydropower dams

Stricter environmental regulations (e.g. the EU’s Water Framework Directive) will entail many environmental improvement measures in waters that have been affected by hydropower, and dam removals are becoming a more common measure. This paper reviews economic evaluations of dam removals, primarily drawing on studies in the USA, and identifies key, frequently recurring, issues that future evaluations will likely need to consider. The paper also reports on an ex-ante evaluation of the recent removal of the Marieberg Hydropower Plant in the Mörrum River in Sweden. An environmental valuation survey carried out as a key part of this evaluation was conducted as a replication of a previous study, where the policy context was different but the expected ecological outcome similar. The replication study produced comparable results to those of the previous study.

Expected-mean gamma-incremental reinforcement learning algorithm for robot path planning

Recently, researchers have been extensively exploring the immense potential of Q-Star. However, the available resources lack comprehensive information on this topic. Despite this, a Q-table, an uncomplicated lookup table containing actions and states, is often seen as a mere data structure for tracking. This overlooks the vast amount of knowledge that can be derived from it through visualization. The Q-learning algorithm utilizes this table to update values and determine the highest anticipated rewards for actions in each state. However, instead of relying solely on complex reward functions for algorithm development, leveraging the existing knowledge within the Q-table would be highly beneficial. Incorporating this valuable information into the algorithmic framework can minimize the need to develop intricate reward functions. This paper proposes an expected-mean gamma-incremental Q approach to tackle the challenges of convergence speed in an uninformed search reinforcement learning (RL) algorithm and the issue of path optimality in path planning problems. The gamma-incremental RL method revolves around adjusting the weight of the future value by considering the level of exploration. It enables the robot to receive preference feedback, either near-term reward or long-term reward, based on the frequency of the visited state. Meanwhile, the expected-mean technique uses the information of the robot's turning actions to update the Q-target. By consistently incorporating valuable insights from the Q-table, the algorithm can gradually enhance its understanding of the available information, resulting in more efficient decision-making. The experiment results indicate that the proposed algorithm accelerates the convergence rate, outperforming the baseline Q-learning by up to 2 times. It addresses the challenge of robot path planning by prioritizing promising solutions, resulting in near-optimal outcomes with higher total rewards and enhanced learning stability.

The value of saccade metrics and VOR gain in detecting a vestibular stroke.

A normal video Head Impulse Test is the gold standard in the emergency department to rule-in patients with an acute vestibular syndrome and a stroke. We aimed to compare the diagnostic accuracy of vHIT metrics regarding the vestibulo-ocular reflex gain and the corrective saccades in detecting vestibular strokes. Prospective cross-sectional study (convenience sample) of patients presenting with acute vestibular syndrome in the emergency department of a tertiary referral centre between February 2015 and May 2020. We screened 1677 patients and enrolled 76 patients fulfilling the inclusion criteria of acute vestibular syndrome. All patients underwent video head impulse test with automated and manual data analysis. A delayed MRI served as a gold standard for vestibular stroke confirmation. Out of 76 patients, 52 were diagnosed with acute unilateral vestibulopathy and 24 with vestibular strokes. The overall accuracy of detecting stroke with an automated vestibulo-ocular reflex gain was 86.8%, compared to 77.6% for cumulative saccade amplitude and automatic saccade mean peak velocity measured by an expert and 71% for cumulative saccade amplitude and saccade mean peak velocity measured automatically. Gain misclassified 13.1% of the patients as false positive or false negative, manual cumulative saccade amplitude and saccade mean peak velocity 22.3%, and automated cumulative saccade amplitude and saccade mean peak velocity 28.9% respectively. We found a better accuracy of video head impulse test for the diagnosis of vestibular strokes when using the vestibulo-ocular reflex gain than using saccade metrics. Nevertheless, saccades provide an additional and important information for video head impulse test evaluation. The automated saccade detection algorithm is not yet perfect compared to expert analysis, but it may become a valuable tool for future non-expert video head impulse test evaluations.