Current Assessment Methods Research Articles

Heart function grading evaluation based on heart sounds and convolutional neural networks.

Accurate and rapid cardiac function assessment is critical for disease diagnosis and treatment strategy. However, the current cardiac function assessment methods have their adaptability and limitations. Heart sounds (HS) can reflect changes in heart function. Therefore, HS signals were proposed to assess cardiac function, and a specially designed pruning convolutional neural network (CNN) was applied to recognize subjects' cardiac function at different levels in this paper. Firstly, the adaptive wavelet denoising algorithm and logistic regression based hidden semi-Markov model were utilized for signal denoising and segmentation. Then, the continuous wavelet transform (CWT) was employed to convert the preprocessed HS signals into spectra as input to the convolutional neural network, which can extract features automatically. Finally, the proposed method was compared with AlexNet, Resnet50, Xception, GhostNet and EfficientNet to verify the superiority of the proposed method. Through comprehensive comparison, the proposed approach achieves the best classification performance with an accuracy of 94.34%. The study indicates HS analysis is a non-invasive and effective method for cardiac function classification, which has broad research prospects.

Senior academics’ perceptions of undergraduate prosthodontics curriculum and teaching: a qualitative study

Introduction: Divergence in undergraduate teaching methods in prosthodontics is widely reported, and this could impact on graduate dentists’ competence and affect patient safety. Objectives: To explore the perspectives held by senior dental academics worldwide regarding the undergraduate prosthodontics curriculum, teaching and assessment methods, and teaching staff profile. Materials and methods: Twelve senior dental academics from seven countries participated in semi-structured interviews exploring their perspectives and opinions of the undergraduate prosthodontics curriculum, and current and best teaching and assessment methods. Interviews were undertaken virtually, video-recorded and auto-transcribed. Semantic thematic analysis was used for data analysis. Results: Academic professors, consultants and specialists were considered the most suitable staff members to supervise students during preclinical hands-on sessions due to their experience level. Additionally, participants mentioned the availability of suitable patients for treatment, dental schools’ curricula, and the level of students’ skills as factors influencing the start of clinical sessions in fixed prosthodontics. The course contents and the extent of teaching on dental implants were different between schools. Tailoring the curriculum according to what is expected from the graduating dentists and allowing students to observe dental implant cases before dealing with simple cases were suggestions made by the participants, to include an implant course at undergraduate level. Conclusions: Despite some differences in opinions and current practices in different institutions, barriers to the implementation of an ideal curriculum seemed to be similar in the different institutions. This study provided deeper understanding of the current divergence in prosthodontics teaching, which would allow for future improvement in the dental curriculum.

Comparison of Chronic Rheumatic Mitral Regurgitation Severity between Cardiac Magnetic Resonance Imaging and Echocardiography

Abstract Background and Purpose Traditionally, echocardiography has been used for assessing mitral regurgitation (MR) severity. However, existing qualitative, semi-quantitative and quantitative parameters suffer from several limitations. The shortcomings of the current echocardiographic methods for MR severity assessment are especially pronounced in the context of eccentric MR jets. Cardiac magnetic resonance (CMR) imaging is useful for assessing valvular lesions as it is now the gold standard for assessing left ventricular and left atrial volumes. Therefore, we sought to study and compare echocardiography with CMR for assessment of chronic rheumatic MR severity. Methods Twenty-two patients with chronic rheumatic MR who underwent both CMR and echocardiography were studied. For the echocardiography part of the study, the MR severity was assessed as per current guidelines. The CMR measurements were performed per standard guidelines by a single operator experienced in this technique. Results The mean age of the study population was 36.3±13.9 years and 81% were females. There was overall poor agreement for the assessment of MR severity using the quantitative parameters for MR assessment between echocardiography and CMR. Although the measurements for end diastolic volume index (EDVi), end systolic volume index (ESVi), regurgitant volume (RV) and regurgitant fraction (RF) showed moderate correlation, these parameters displayed poor agreement between the two tests. We noted discrepant findings in terms of classification of valve lesion severity in seven patients. Six patients were reclassified after CMR to severe MR and one to moderate MR based on quantitative parameters of regurgitant volume (RV) and regurgitant fraction (RF). Conclusion In patients with severe chronic rheumatic MR with eccentric jets, when MR quantification by echocardiography is inadequate, CMR derived quantitative volumetric parameters may be useful for accurate classification of the severity of mitral regurgitation.

Borderline personality disorder: Gender bias and diagnostic disparities

Borderline Personality Disorder (BPD) is a DSM-5 Cluster B mental health condition. One of the lesser understood mental health conditions, BPD is marked by a multi-symptom profile such as high levels of emotional dysregulation, distorted self-image, volatile and unstable relationships, emotional instability, and higher levels of suicidality. Symptoms are often intense and enduring, causing significant chaos and stress in an individual’s life as well as those closest to them. Because there is a significant overlap of symptomology and diagnosis with other psychiatric disorders, BPD was at one time a contested diagnosis, thus research and treatment options remained limited. Currently, BPD is one of the more widely researched conditions, which has informed evidenced-based treatment, however, individuals carrying the diagnosis report difficulty accessing treatment and difficulty feeling understood by mental healthcare providers. The development of BPD remains unclear, although consistent with other mental health conditions there is a genetic constituent, and with BPD in particular a history of trauma. This research manual will explore current evidence-based practices and assessment methods to inform best practices when working with BPD.

Increased human risk caused by cascading hazards - A framework.

Cascading hazards occur frequently. Unexpected casualties and losses of properties, or even impacts on the society and the environment may ensue from failure to anticipate the amplified risks induced by cascading hazards. Current risk assessment methods pay relatively less attention to quantifying the increased human risk related to "cascading" events. An improved framework for quantifying the human risk caused by cascading hazards is proposed in this paper. The framework considers the interactions among the cascading hazards and among the vulnerabilities of elements to these hazards. Its kernel is to scientifically anticipate and gear up for any new intensified hazards, which may otherwise lead to serious social aftermath. The framework is illustrated with a multi-hazard example close to the epicenter of the Wenchuan earthquake, which involved a chain of hazards including slope failures, a large debris flow, river damming, and flooding.

Assessment of the response to systemic treatment of colorectal liver metastases on cross-sectional imaging - a systematic review.

Colorectal cancer (CRC) is one of the most common malignancies in the world. Nowadays many treatments are available to help control CRC, including surgery, radiation therapy, interventional radiology, and drug treatments. A multidisciplinary approach and the role of radiologists is needed to assist the surgeon in the management thanks to emerging technology and strategies. The Response Evaluation Criteria in Solid Tumours (RECIST) has been created to objectify and standardize cancer response assessment. Thus, in this article specific presumptions and practical aspects of evaluating responses according to the RECIST 1.1 are discussed. Furthermore, examples of possible response to systemic treatment of colorectal liver metastases (CRLM), including tumour necrosis, apparent diffusion coefficient (ADC) values, tumour calcification, tumour fibrosis and intratumoural fat deposition observed on cross-sectional imaging, are described. Disappearing liver metastases (DLM) presents a therapeutic dilemma. The optimal management of DLM remains controversial due to the uncertainty of residual microscopic disease and effective long-term outcomes. The article provides an overview of the CRLM phenomenon and current possible assessment methods of the response to systemic treatment.

Machine Learning-Based Screening of Risk Factors and Prediction of Deep Vein Thrombosis and Pulmonary Embolism After Hip Arthroplasty.

Prophylactic anticoagulation is a standard strategy for patients undergoing total hip arthroplasty (THA) to prevent deep venous thromboembolism (DVT) and pulmonary embolism (PE). Nevertheless, some patients still experience these complications during their hospital stay. Current risk assessment methods like the Caprini and Geneva scores are not specifically designed for THA and may not accurately predict DVT or PE postoperatively. This study used machine learning techniques to establish models for early diagnosis of DVT and PE in patients undergoing THA. Data were collected from 1481 patients who received perioperative prophylactic anticoagulation. Model establishment and parameter tuning were performed using a training set and evaluated using a test set. Among the models, extreme gradient boosting (XGBoost) performed the best, with an area under the receiver operating characteristic curve (AUC) of 0.982, sensitivity of 0.913, and specificity of 0.998. The main features used in the XGBoost model were direct and indirect bilirubin, partial activation prothrombin time, prealbumin, creatinine, D-dimer, and C-reactive protein. Shapley Additive Explanations analysis was conducted to further analyze these features. This study presents a model for early diagnosis DVT or PE after THA and demonstrates bilirubin could be a potential predictor in the assessment of DVT or PE. Compared to traditional risk assessment, XGBoost has a high sensitivity and specificity to predict DVT and PE in the clinical setting. Furthermore, the results of this study were converted into a web calculator that can be used in clinical practice.

Dynamic HTA for digital health solutions: opportunities and challenges for patient-centered evaluation.

Germany's 2019 Digital Healthcare Act (Digitale-Versorgung-Gesetz, or DVG) created a number of opportunities for the digital transformation of the healthcare delivery system. Key among these was the creation of a reimbursement pathway for patient-centered digital health applications (digitale Gesundheitsanwendungen, or DiGA). Worldwide, this is the first structured pathway for "prescribable" health applications at scale. As of October 10, 2023, 49 DiGA were listed in the official directory maintained by Germany's Federal Institute for Drugs and Medical Devices (BfArM); these are prescribable by physicians and psychotherapists and reimbursed by the German statutory health insurance system for all its 73 million beneficiaries. Looking ahead, a major challenge facing DiGA manufacturers will be the generation of the evidence required for ongoing price negotiations and reimbursement. Current health technology assessment (HTA) methods will need to be adapted for DiGA. We describe the core issues that distinguish HTA in this setting: (i) explicit allowance for more flexible research designs, (ii) the nature of initial evidence generation, which can be delivered (in its final form) up to one year after becoming reimbursable, and (iii) the dynamic nature of both product development and product evaluation. We present the digital health applications in the German DiGA scheme as a case study and highlight the role of RWE in the successful evaluation of DiGA on an ongoing basis. When a DiGA is likely to be updated and assessed regularly, full-scale RCTs are infeasible; we therefore make the case for using real-world data and real-world evidence (RWE) for dynamic HTAs. Continous evaluation using RWD is a regulatory innovation that can help improve the quality of DiGAs on the market.

Precise detection and localization of R-peaks from ECG signals.

Heart rate variability (HRV) is derived from the R-R interval, which depends on the precise localization of R-peaks within an electrocardiogram (ECG) signal. However, current algorithm assessment methods prioritize the R-peak detection's sensitivity rather than the precision of pinpointing the exact R-peak positions. As a result, it is of great value to develop an R-peak detection algorithm with high-precision R-peak localization. This paper introduces a novel R-peak localization algorithm that involves modifications to the well-established Pan-Tompkins (PT) algorithm. The algorithm was implemented as follows. First, the raw ECG signal $ X\left(i\right) $ was band-pass filtered (5-35 Hz) to obtain a preprocessed signal $ Y\left(i\right) $. Second, $ Y\left(i\right) $ was squared to enhance the QRS complex, followed by a 5 Hz low-pass filter to obtain the QRS envelope, which was transformed into a window signal $ W\left(i\right) $ by dynamic threshold with a minimum width of 200 ms to mark the QRS complex. Third, $ Y\left(i\right) $ was used to generate QRS template $ T\left(n\right) $ automatically, and then the R-peak was identified by a template matching process to find the maximum absolute value of all cross-correlation values between $ T\left(n\right) $ and $ Y\left(i\right) $. The proposed algorithm achieved a sensitivity (SE) of 99.78%, a positive prediction value (PPV) of 99.78% and data error rate (DER) of 0.44% in R-peak localization for the MIT-BIH Arrhythmia database. The annotated-detected error (ADE), which represents the error between the annotated R-peak location and the detected R-peak location, was 8.35 ms for the MIT-BIH Arrhythmia database. These results outperformed the results obtained using the classical Pan-Tompkins algorithm which yielded an SE of 98.87%, a PPV of 99.14%, a DER of 1.98% and an ADE of 21.65 ms for the MIT-BIH Arrhythmia database. It can be concluded that the algorithm can precisely detect the location of R-peaks and may have the potential to enhance clinical applications of HRV analysis.

Mental Overload Assessment Method Considering the Effects of Performance Shaping Factors

The assessment of mental overload is essential as mental overload has been proved to be a critical cause of many accidents. Mental overload is affected by various performance shaping factors (PSFs), and harsh PSFs will either increase the task demand or decrease the overload threshold, which is rarely considered in the current mental overload assessment method. This research proposes a VACP-based mental overload assessment model which considers the effects of PSFs. In the VACP model, mental overload can be identified when the sum of the task demand values of every unit task is greater than the given threshold. In human reliability analysis, PSFs are mainly used as weighting factors to modify basic human error probability. In our research, by virtue of the quantitative relationship between human error and mental workload, the weighting factors of PSFs are converted to modify the task demand values and threshold for VACP activities. Furthermore, Bayesian Network (BN) is used to model the influence of PSFs and to calculate the probability of mental overload. The proposed method is applied to an accident involving a helicopter crash that occurred in Maryland, and the results show that, in comparison with the VACP method, the proposed method can more effectively identify the state of mental overload and provide a more rational explanation of the process of the accident.

What are the current diabetic foot assessment methods in private podiatry practices in Flanders, Belgium: an exploratory mixed method study

BackgroundDiabetic foot assessments detect patients at risk for developing a diabetes-related foot ulceration and can significantly reduce the risk of amputation. In order to organize this assessment effectively, diabetic foot assessment guidelines are required according to the International Working Group of the Diabetic Foot. However, these international guidelines have not been adapted into a national guideline for podiatrists in Flanders, Belgium. This study aims to identify the methods and guidelines currently used to assess the diabetic foot in private podiatry practices in Flanders, Belgium and to explore the podiatrists’ opinions on developing a national diabetic foot assessment guideline.MethodsThis exploratory mixed method study was composed of an anonymous online survey comprising of open- and closed-ended questions followed by 1:1 online semi-structured interviews. Participants were recruited via e-mail and a closed private Facebook group of podiatry alumni. Data was analyzed using SPSS statistics and thematic analysis described by Braun and Clarke.ResultsThis study showed that the vascular assessment of the diabetic foot exists solely of a medical history and palpation of the pedal pulses. Non-invasive tests such as doppler, toe brachial pressure index or ankle brachial pressure index are seldom used. Only 66% reported to use a guideline for the diabetic foot assessment. There was a variety of reported guidelines and risk stratification systems in use in private podiatry practices in Flanders, Belgium.ConclusionNon-invasive tests such as the doppler, ankle brachial pressure index or toe brachial pressure index are rarely used for the vascular assessment of the diabetic foot. Diabetic foot assessment guidelines and risk stratification systems to identify patients at risk for developing a diabetic foot ulcer were not frequently used. International guidelines of the International Working Group of the Diabetic Foot have not yet been implemented in private podiatry practices in Flanders, Belgium. This exploratory research has provided useful information for future research studies.

Integrated Visual Assessment Method for Infestation by Lebbek Borer (Xystrocera globosa) in Rain Trees of Singapore

"Background: In Singapore, determining the level of infestation by lebbek borer (Xystrocera globosa)(Olivier, 1795)[Coleoptera: Cerambycidae] is the crucial first step in control of this pestra in rain tree (Albizia saman [Jacq.] Merr.)[Fabales: Fabaceae]. Current assessment methods rely on symptoms such as canopy colour, defoliation, dieback, and actual estimation of borer population via counting of larvae or exit holes created by adults. Currently, there is a lack of systematic approach to integrate different tree health indicators and symptoms to quantify infestation level. This gap poses challenges in assessment of treatment efficacy as managers could not quantitatively determine whether infestation level has changed following treatment. Thus, this study aimed to develop a visual assessment method that can integrate all mentioned symptoms to quantify infestation level. Methods: We surveyed a total of 388 rain trees and used principal component analysis (PCA) to investigate the correlation between X. globosa infestation and different borer infestation symptoms. Borer Infestation Score (BIS) formula was developed based on the linear combinations of the statistically significant principal component. Results: Infestation level was strongly associated with bark peeling, exit holes, and proximity of bark peeling and/or exit holes to trunk base and weakly associated with defoliation, dieback, and canopy colour. Developed BIS formula generated numerical values that distinguished between noninfested and infested trees, reflected infestation level in surveyed areas and temporal progression of infestation. Conclusions: Described integrated visual assessment method can be executed quickly on field. BIS formula generates quantitative scores easy to be interpreted, tracked, and compared.

ASSESSMENT REFORMS IN THE FOURTH INDUSTRIAL REVOLUTION: PERSPECTIVES OF HIGHER EDUCATION STUDENTS

The fourth industrial revolution has transformed the nature of jobs by the vast introduction of breakthrough technologies and triggered a change in education assessment practices. Going to university is one of the ways for learners to gain relevant skills to get the right job. Universities provide students with access to skills and knowledge to be useful in their communities and expand their capabilities. This study explored the students’ perspectives on changing nature of assessment in higher education. Students shared perspectives on the current assessment method, the relevance of assessment and how they would like to be assessed in the future. A total of 111 students studying under ICCR scholarship in Gujarat state participated in the study by filling out the questionnaire survey form. Results demonstrate that to date the prominent assessment method is pen and paper, however, the students found it useful when assessed progressively using research, project /experiential learning, coaching and mentorship and incubation in comparison to pen and paper-based assessment. Based upon study findings, the study proposes curricula change and the adoption of new assessment practices that can reflect the need of the fourth industrial revolution.

Introducing A Reflective Framework for the Assessment and Recognition of Microcredentials

Assessment and recognition are key aspects of microcredentials, and other courses offered on massive open online course (MOOC) platforms. Microcredentials are designed to address the needs of employers and learners looking for units of study at a higher education level aligned with the requirements of labour markets. This paper reviews current methods for assessment and recognition used in MOOCs and microcredentials, proposing a framework with seven aspects and two checklists for use at planning and design stages. The framework is based on a review of 27 documents and a synthesis process. It provides a tool for microcredential producers to check whether the best ID verification, assessment, recognition, and quality assurance approaches are in place, enabling them to reflect on, and possibly improve, their choices.

Innovative Technologies in the Monitoring of the Age-Related Cataract

Literature review is devoted to modern high-technology instrumental methods of the lens evaluation, which have been developed to improve efficiency of the diagnostics and management of cataract in ophthalmological clinical practice. The slit-lamp examination of lens and retroillumination images are used for subjective assessment of cataract according to LOCS III grading system. Currently objective methods of lens evaluation have practical value and provide information about early age-related changes of crystalline lens with the quantitative assessment of the severity of opacities including the optical and ultrasound examinations. Optical methods include densitometry using Scheimpflug images obtained from applications to quantify the localization of lens opacities and their progression rate. Another method is the intensity distribution analysis of the wave front of the optical aberrations according to grading cataract severity with the objective scatter index (OSI) obtained by double-pass technology. Moreover the optical quantitative assessment of lens opacities is carried out by the Shack—Hartmann wave front sensor to identify the grade of nuclear opalescence (N-type) with the Lens Opacities Classification System III. This method is very helpful in nuclear cataract. Swept source optical coherent tomography (SS-OCT) with variable length of wave and high frequency detector is used for the density measurements of nuclear and cortical opacities of lens imaging in micro- and macro dimensional scale. Ultrasound biomicroscopy is the most informative ultrasonic diagnostic method for the evaluation of acoustic density and early age-related changes of lens. Current high-informative methods of quantitative assessment of the optical density of lens are helpful in determination of indications for surgery, the optimization of phacoemulsification settings and prevention of intraoperative complications. The use of high-technologic methods demonstrated the effectiveness of eye drops 0,005 % pirenoxine in early lens opacities management.

Machine learning-based identification and classification of physical fatigue levels: A novel method based on a wearable insole device

Construction is known for being a labor-intensive and risky industry. Within various occupational settings such as construction, physical fatigue is an underlying health condition that may lead to musculoskeletal disorders and fall-related injuries. Identifying a worker's physical fatigue could enable safety managers to mitigate fatigue-related injuries and improve workplace operations. However, current physical fatigue assessment and identification methods include subjective, physiological, biomechanical, and computer vision approaches, which may be unreliable, intrusive, and require extensive post-processing, thus, rendering them impractical for continuous monitoring of workers' movements and automated identification of physical fatigue. Given the above, this study aims to utilize a wearable insole device to identify and classify physical fatigue levels in construction workers. Ten asymptomatic subjects were recruited to perform a fatiguing manual rebar tying activity in a laboratory setting. Borg's rating of perceived exertion (RPE) was applied as a subjective measure for collecting the levels of physical fatigue of each subject. Three sub-classification problems for identifying physical fatigue levels (i.e., PFL1, PFL2, and PFL3) were assessed. Numerous features were evaluated from the collected data samples after data segmentation. The classification performance of supervised machine learning algorithms was evaluated at a sliding window of 2.56 s. Our results from 10-fold cross-validation show an accuracy of 86% for the Random Forest (RF) algorithm, indicating the best performance among other algorithms. In addition, precision, recall, specificity, and F1-score metrics of the RF algorithm were between 52.63% and 82.62%, 52.63%–84.32%, 89.60%–92.33%, and 52.63%–83.46%, respectively. These results indicate that data samples such as acceleration and plantar pressure acquired from a wearable insole device are reliable for identifying and classifying physical fatigue levels in construction workers. In summary, this study would contribute to providing a proactive physical fatigue assessment method and guidelines for early identification of physical fatigue in construction.

Physical Activity Levels during Therapeutic Camp Activities in Youth with Disabilities in the United States

Youth with developmental disabilities (DD) face challenges that may impact their participation in physical activity. One of the biggest challenges is the availability of opportunities to engage in activities that are adapted for youth with DD. In addition, due to challenges with current physical activity assessment methods for youth with DD, the activity levels during modified activities remain unclear. The purpose of this investigation was to determine the activity levels of youth with DD during structured and unstructured activities offered during a therapeutic camp. This camp was a five-day, overnight experience in an outdoor camp center in the southeastern region of the U.S. Youth (n = 29; 14.6 ± 3.9 years) with more than one DD and with varying abilities wore accelerometers while they engaged in 13 activities of varying categories (functional/gross motor, game, sociodramatic, fine motor, free play) and contexts (ropes, horses, outdoor adventure, music and movement, yoga, come on down, sports and games, theatre, cabin challenge, arts, cooking, mad science, free play). Activity level varied by activity category and context and the intensity level of the majority of the camp activities was classified as either sedentary or light. There was a time course effect on activity; most activities resulted in a gradual decline over the session, except for cooking, sports and games, and free play. This therapeutic camp provided an opportunity for youth to engage in physical activity that would be classified as light intensity. The activities available at this camp were designed to address specific goals and objectives and provided enrichment opportunities (e.g., life skills, social skills) for youth to obtain multiple skills while using movement as a framework to deliver the content.

Abductor Digiti Minimi and Anterior Interosseous to Ulnar Motor Nerve Transfer: The Super Turbocharge End-to-Side Transfer.

Anterior interosseous nerve to ulnar motor nerve supercharged end-to-side (SETS) nerve transfer to restore intrinsic function is a recently adopted nerve transfer in severe ulnar neuropathy. Its success is predicated on the critical threshold number of axons innervating the intrinsic muscles. Given the relative expendability of the abductor digiti minimi (ADM) muscle and the critical function of the other intrinsic muscles, the authors modified their SETS transfer to redirect axons from the ADM to turbocharge the ulnar motor nerve to innervate the more critical intrinsic muscles. They refer to this procedure as a super turbocharged end-to-side (STETS) procedure. The ADM has been used previously as a muscle/tendon transfer for thumb opposition and more recently as a nerve transfer to reinnervate the thenar branch of the median nerve. Although current methods of assessment of reinnervation are likely unable to differentiate between contributions from the anterior interosseous nerve SETS versus ADM STETS transfer, this technique follows the fundamentals of modern nerve surgery, where directing the maximum number of nerve fibers in a timely fashion to the most critical target is paramount for the best functional recovery. The authors suggest that the STETS technique may optimize outcomes in ulnar neuropathy without additional patient morbidity.

A BIM-based two-stage fuzzy inference system for safety risk prediction in building construction projects

Building information modeling (BIM) can be recognized as the most promising technology that was introduced to the construction sector in the recent past. The current BIM-based safety risk assessment methods ignore data uncertainty. Hence, this study integrates BIM with fuzzy set theory for safety risk prediction. A Fuzzy Inference System (FIS) was developed based on the causality of safety incidents. The FIS extracts construction project data from BIM models while automatically assessing each potential safety hazard and project’s total risk. The proposed method was demonstrated by using a building project in which the safety risk was predicted as low. Safety records of the above project revealed that no safety incidents were recorded in this project. The proposed method can indicate the safety risks level at various stages of a construction project and help to enhance the safety of construction workers on a construction site.

Evaluation of COVID on cognitive performance using a mobile application (DANA)

AbstractBackgroundThe neurocognitive impact of having COVID is receiving greater awareness, with greater COVID severity potentially conferring risk of more negative cognitive outcomes. Current cognitive assessment methods are limited by factors, such as time and location, which can be mitigated by the use of mobile applications. We aimed to assess the relationship between COVID severity and cognitive performance at baseline and over time using a mobile cognitive assessment.MethodParticipants in the analytic sample included 27 COVID‐positive (COVID+) Johns Hopkins Post‐acute Covid Team patients who received care in the intensive care unit (COVID+/ICU+; n = 6) or in other units (COVID+/ICU‐; n = 21). Another 23 participants from a separate study investigating the use of mobile cognitive applications in older adults were included as non‐COVID controls (COVID‐). Cognition was assessed via cognitive efficiency (CE) scores, a derived measure of speed and accuracy, for the Procedural Reaction Time (PRT) task of the Digital Automated Neurobehavioral Assessment (DANA) mobile application. Participants with missing or unavailable PRT assessment data were excluded from the analytic sample. PRT CE scores between COVID‐, COVID+/ICU‐, and COVID+/ICU+ participants were analyzed at baseline using ANOVA, as well as longitudinally over a six‐week period.Result Table 1 presents demographic characteristics. At baseline, average PRT CE scores were highest among the COVID‐ group (mean = 86.55; standard deviation = 17.06), followed by the COVID+/ICU+ group (mean = 80.41; standard deviation = 15.83), and then the COVID+/ICU‐ group (mean = 76.93; standard deviation = 14.03). There was no significant difference in average baseline PRT CE scores between the three groups (p = 0.135). Those in the COVID‐ group and COVID+/ICU‐ group appeared to achieve higher PRT CE scores over the six‐week assessment period, while those in the COVID+/ICU+ group did not improve relative to their baseline (Figure 1a&b).ConclusionWe observed qualitative differences in the rate of recovery for cognitive performance between participants with COVID who did and did not require ICU admission. Given the limited sample size and other potential confounding factors, further analyses with additional data collected are needed in order to more rigorously compare cognitive performance cross‐sectionally and longitudinally between COVID groups.