Objetivos: Avaliar a densidade radiográfica de três ossos do carpo - capitato, escafóide e hamato, em pacientes do sexo masculino e do sexo feminino, com idades entre 7 e 18 anos, por meio de um programa gerenciador de imagens - Adobe Photoshop - 6.0®. Métodos: Leituras das intensidades de cinza de cada imagem selecionada em cada osso e obtenção de um histograma referente aos valores de número de pixels da imagem analisada, valor médio dos tons de cinza, mediana e o desvio padrão da área selecionada na digitalização e tratamento estatístico destes dados. Resultados: As comparações entre médias de densidades dos ossos analisados para o sexo masculino, não apresentou médias estatisticamente diferentes somente para a comparação capitato x hamato, enquanto no sexo feminino as comparações entre ossos se mostraram estatisticamente desiguais; a comparação entre média de densidade de cada osso e idade cronológica apresentou dependência significativa somente para o osso hamato no sexo masculino; a comparação entre as médias de densidade dos ossos para os sexos masculino e feminino, mostrou não existir diferenças estatisticamente significativas entre ambos considerando-se os três ossos analisados. Conclusões: Para o sexo masculino na amostra analisada, houve dependência somente entre a média de densidade dos ossos capitato e hamato, enquanto para o sexo feminino não houve correlação de dependência entre os três ossos analisados; a comparação entre as densidades ósseas e a idade cronológica, indicou que somente o osso hamato apresenta grau de dependência significativo com a faixa etária no sexo masculino, enquanto no sexo feminino nenhum dos ossos apresentou grau de dependência significativo em relação à idade cronológica na amostra analisada; a densidade dos três ossos: hamato, capitato e escafóide, não apresentam diferenças significativas quando comparadas entre sexo masculino e feminino na mesma faixa etária. / Objectives: To evaluate the radiographic density of three carpal bones (hamate, capitate and scaphoid bones) in male and female patients aged 7 to 18 years by means of an image-editing software (Adobe Photoshop - 6.0®). Methods: Readings of gray intensities of each image selected in each bone and drawing of a histogram referring to the values of number of pixels of the analyzed image, mean value of the gray tons, median and standard deviation of the area demarcated in the digitized image and statistical analysis of data. Results: For the male patients, comparisons of the means of densities of the analyzed bones did not show statistically significant difference only for the hamate X capitate pair. For the female patients, comparisons among the bones appeared statistically different; comparison between the density means of each bone and the chronological age showed significant dependence only for the hamate bone in the male patients; comparison among the bone density means for the male and female patients showed no statistically significant difference between genders for the tree types of bone. Conclusions: In the evaluated population, for the male gender, there was dependence only between the density means of the capitate and hamate bones, while for the female gender there was no dependence correlation among the three bone types; comparison between the bone densities and the chronological age showed that only the hamate bone presented a significant degree of dependence with the age group in the male patients, while in the female patients none of the bone presented a significant degree of dependence in relation to the chronological age in the analyzed sample; the densities of the three bones (hamate, capitate and scaphoid bones) did no show statistically significant difference when compared between males and females belonging to the same age group.

SyfteSyftet med studien var att undersöka komplexitetsnivåns (stillastående handledsskott och handledsskott i rörelse) och träffpunktsplaceringens inverkan på skottsprecisionen hos damelitinnebandyspelare på seniornivå. Vidare syftade studien till att undersöka om det fanns någon inlärningseffekt vid upprepade skott mot samma träffpunkt.MetodÅtta testdeltagare deltog där två test med olika komplexitetsnivåer utfördes. Första testet utfördes som ett stillastående handledsskott (SH) medan det andra testet utfördes som handledsskott i rörelse (HR). Varje deltagare utförde 40 skott per test fördelat på fyra träffpunkter (Tp). Dessa befann sig i målets övre och nedre del. Testerna filmades och analyserades där skottens x- och y-koordinat fastställdes. Testvärdena analyserades sedan i SPSS där Paired-Sample t-test användes samt Pearsons korrelationsanalys.ResultatDet fanns en signifikant skillnad i skottprecision avseende avstånd från träffpunkterna mellan SH och HR (t = -6,68, p = 0,0068). Det förekom en signifikant skillnad i skottprecision vid HR mellan den närmaste och den bortre övre Tp (t = 3,58, p = 0,0090), övriga Tp i närmaste och bortre hörn i de vardera testen uppvisade inga signifikanta skillnader (alla p > 0,05). Inget signifikant samband fanns avseende inlärningseffekt vid SH eller HR (p > 0,05).SlutsatserSkottprecisionen påverkades av komplexitetsnivåerna som fanns mellan SH och HR. Resultatet kan användas av spelare och tränare då spelarna kan utveckla skottprecisionen i rörelsemoment och att skjuta i målets närmaste övre del. Det inträffade ingen inlärning genom att utföra 10 skott mot samma Tp vilket gör att spelarna kan behöva fler rörelseupprepningar för att få en kortvarig inlärning. / Purpose The purpose of the study was to investigate the level of complexity in stationary wrist shot and wrist shot in motion at female elite floorball players. Furthermore, the study aimed to investigate the impact of the placement of the target and investigate whether there was any learning effect in repeated shots at the same target.Methods Eight participants took part of the study were two tests was performed with different complexity level. The first test was performed as a stationary wrist shot (SH) while test two was performed as a wrist shot in motion (HR). In total, each participant performed 40 shots per test divided in four hit targets (Tp). These were placed in the upper and lower part of the goal. The tests were recorded and analyzed afterwards where the x- and y-coordinates of the shots were determined. The test values were then analyzed in SPSS where Paired-Sample t-test was used and Pearsons correlation analysis.Results There was a significant difference in shot precision between HR and SH (t = -6,68, p = 0,0068). There was a significant difference in shot precision in HR between the nearest upper target and the far upper target (t = 3,58, p = 0,0090). The other nearest and farther targets in each test showed no significant difference (p > 0,05). There was no significant learning effect in SH or HR (p > 0,05).Conclusions Shot accuracy was affected by the complexity levels that existed between SH and HR. The result can be used by players and coaches as players can develop shot precision in movement moments and to shoot in the nearest upper target. No learning occurred by performing 10 shots at the same target which means that players may need more movement repetitions to achieve a short learning effect.

Background: Consumer smartwatches have gained attention as mobile health (mHealth) tools able to detect atrial fibrillation (AF) using photoplethysmography (PPG) or a short strip of electrocardiogram (ECG). PPG has limited accuracy due to the movement artifacts, whereas ECG cannot be used continuously, is usually displayed as a single-lead signal and is limited in asymptomatic cases. Objective: DoubleCheck-AF is a validation study of a wrist-worn device dedicated to providing both continuous PPG-based rhythm monitoring and instant 6-lead ECG with no wires. We evaluated its ability to differentiate between AF and sinus rhythm (SR) with particular emphasis on the challenge of frequent premature beats. Methods and Results: We performed a prospective, non-randomized study of 344 participants including 121 patients in AF. To challenge the specificity of the device two control groups were selected: 95 patients in stable SR and 128 patients in SR with frequent premature ventricular or atrial contractions (PVCs/PACs). All ECG tracings were labeled by two independent diagnosis-blinded cardiologists as “AF,” “SR” or “Cannot be concluded.” In case of disagreement, a third cardiologist was consulted. A simultaneously recorded ECG of Holter monitor served as a reference. It revealed a high burden of ectopy in the corresponding control group: 6.2 PVCs/PACs per minute, bigeminy/trigeminy episodes in 24.2% (31/128) and runs of ≥3 beats in 9.4% (12/128) of patients. AF detection with PPG-based algorithm, ECG of the wearable and combination of both yielded sensitivity and specificity of 94.2 and 96.9%; 99.2 and 99.1%; 94.2 and 99.6%, respectively. All seven false-positive PPGbased cases were from the frequent PVCs/PACs group compared to none from the stable SR group (P < 0.001). In the majority of these cases (6/7) cardiologists were able to correct the diagnosis to SR with the help of the ECG of the device (P = 0.012). Conclusions: This is the first wearable combining PPG-based AF detection algorithm for screening of AF together with an instant 6-lead ECG with no wires for manual rhythm confirmation. The system maintained high specificity despite a remarkable amount of frequent single or multiple premature contractions

No description available.

Work-related musculoskeletal disorders constitutes a substantial burden for society, generating individual suffering and financial costs. Quantifying the musculoskeletal stress and establishing exposure-response relationships is an important step in facing this problem. Observational methods for assessing exposure in the field of ergonomics have shown poor results, and the technical measurement methods that exists are often complicated to use which limits their scope to scientific purposes. This work describes the development of a prototype measurement system aimed to simplify ambulatory measurements of musculoskeletal load, specifically aimed at the wrist and hand. Wearable sensors including Inertial Measurement Units (IMU:s) and Electromyography (EMG) were connected to a smartphone and used for measuring wrist movement and forearm muscle activity. Data sampled in the smartphone was stored online in a cloud database, and a webapplication was developed to visualize work-load exposure. Testing under controlled conditions indicated that muscular rest can be measured and classified according to suggested risk thresholds. Accurate angular measurements were difficult to implement because of lacking inter-sensor alignment in the horizontal plane, as well as uncertainties in the Bluetooth protocol. Future work should focus on the IMU:s and look to further develop a method of correcting the relative angle error, as well as investigating accurate time synchronization of the two sensors.Alternatively, deriving angular velocities directly from the IMU gyroscopes could be investigated.

Introduction: Dexterity impairments are common and disabling. Measuring the extent of these impairments is important for care and service provision. Despite this, dexterity is poorly operationalized in the management of persons with hand and wrist conditions (HWC). Thesis purpose: To understand: 1) how dexterity is defined in the management of persons with HWC and 2) how therapists working with persons with HWC perceive/understand the concept and measurement of dexterity and use of performance-based outcome measures of dexterity (PBOMD). Methods: In study one, Interpretive Description was used to understand the perceptions and measurement practices of occupational therapists working with persons with HWC in Singapore. Study two involved a content analysis of the literature outlining the constructs measured by PBOMD that were validated for use in persons with HWC. Results: Both studies highlighted the lack of conceptual clarity around ‘dexterity’ that is reflected in therapists’ and tool developers’ discourse. Many of the therapists we interviewed, perceive PBOMD to lack clinical value. Studies from this thesis suggest that identified PBOMD do not adequately cover dexterity. Conclusion: Findings highlight the challenges surrounding the construct of dexterity and provide clinical practice recommendations. / Thesis / Master of Science Rehabilitation Science (MSc) / Dexterity is the ability to do tasks, successfully, quickly and accurately. Loss of dexterity is common and affects our ability to do our tasks of daily life and work. Unfortunately, there is a lack of agreement on the best way to measure dexterity. Our study aims to explore what dexterity means to health professionals. We focused on occupational therapists seeing persons with hand and arm injuries. In the first study, we interviewed therapists to understand how they measured dexterity. In the second study, we searched for dexterity tests used with persons with hand injuries. Then, we compared the tests we found to dexterity theories. We found that dexterity is measured in different ways. Therapists faced many barriers to using dexterity tests. Current dexterity tests are an incomplete reflection of a person’s dexterity. The information gained from these studies could be used to inform future research on the measurement of dexterity.

[ES] Las neuropatías periféricas son patologías que deterioran los nervios situados fuera del sistema nervioso central y que afectan significativamente las funciones sensoriomotoras. Existen varias alternativas terapéuticas, entre ellas las órtesis. Estos dispositivos se encargan de proteger la musculatura, corregir alteraciones y asistir la función de la extremidad afectada. Su efectividad está demostrada; sin embargo, depende directamente del adecuado cumplimiento del protocolo de uso. El objetivo principal de esta tesis fue identificar los criterios ergonómicos aplicables al desarrollo de órtesis que incrementen la adherencia al tratamiento en pacientes con neuropatías radial, cubital y mediana. Con este fin, se evaluó la posibilidad de optimizar las propiedades terapéuticas a partir de la inclusión de agentes electrofísicos en el dispositivo. Para ello, se llevó a cabo una revisión sistemática y metaanálisis de la evidencia disponible en los en los últimos cuarenta años en torno a la efectividad de las principales modalidades aplicadas. Se determinó que algunas modalidades cuando se aplican conjuntamente a una órtesis se ven favorecidas. No obstante, ninguno de los resultados de la revisión puede considerarse clínicamente significativos. Posteriormente, se planteó un protocolo de co-creación que incluyó las principales fases de un proceso de diseño con la participación de usuarios de órtesis. La primera fase, Perspectiva de Usuarios, contó con 100 sujetos con neuropatías periféricas. Se obtuvo información tanto para la identificación de necesidades y preferencias como para la clasificación de los aspectos que intervienen en la adherencia. Se emplearon modelos lineales y no lineales, como el modelo de Kano. Se encontró que este modelo permite una identificación más precisa acerca de qué atributos tienen más importancia y del grado de influencia de éstos en la adherencia. Asimismo, se comprobó que la satisfacción es una medida indirecta de la importancia y constituye un adecuado predictor de la adherencia a órtesis. Por el contrario, la importancia explícita no cuenta con la misma fiabilidad. La segunda fase, Diseño Participativo, incluyó a 9 personas voluntarias que evaluaron las propuestas de órtesis y brindaron recomendaciones de diseño. En la tercera fase, Modelado y Prototipado, se produjeron una serie de iteraciones de diseño, dando lugar a un nuevo desarrollo de órtesis. En la cuarta fase, Validación, se comprobó la funcionalidad y usabilidad de la órtesis con 11 sujetos sanos a través de un estudio con electromiografía de superficie. Con ello se demostró que la inclusión de un mecanismo deformable en el diseño del muelle articular permite una óptima asistencia motora en condiciones normales. Por último, en la fase de Desarrollo Final, se fabricó un prototipo funcional de órtesis radial teniendo en cuenta las oportunidades de mejora identificadas. / [CA] Les neuropaties perifèriques són patologies que deterioren els nervis situats fora del sistema nerviós central i que afecten significativament les funcions sensorimotrius. Hi ha diverses alternatives terapèutiques, entre elles les òrtesis. Aquests dispositius s'encarreguen de protegir la musculatura, corregir alteracions i assistir la funció de l'extremitat afectada. La seva efectivitat està demostrada; no obstant això, depèn directament del correcte compliment del protocol d'ús. L'objectiu principal d'aquesta tesi va ser identificar els criteris ergonòmics aplicables al desenvolupament d'ortesis que incrementen l'adherència al tractament en pacients amb neuropaties radial, cubital i mitjana. Amb aquest fi, es va avaluar la possibilitat d'optimitzar les propietats terapèutiques a partir de la inclusió d'agents electrofísics en el dispositiu. Per a això, es va dur a terme una revisió sistemàtica i metaanàlisi de l'evidència disponible en els últims 40 anys entorn de l'efectivitat de les principals modalitats aplicades. Es va determinar que algunes modalitats, quan s'apliquen conjuntament a una òrtesi, es veuen beneficiades. No obstant això, cap dels resultats de la revisió va ser clínicament significatiu. Posteriorment, es va plantejar un protocol de co-creació que va incloure les principals fases d'un procés de disseny amb la participació d'usuaris d'ortesis. La primera fase, Perspectiva d'Usuaris, va comptar amb 100 subjectes amb neuropaties perifèriques. Es va obtenir informació tant per a la identificació de necessitats i preferències com per a la classificació dels aspectes que intervenen en l'adherència. Es van emprar models lineals i no lineals, com el model de Kano. Es va trobar que aquest model permet una identificació més precisa sobre quins atributs tenen més importància i el grau d'influència d'aquests en l'adherència. Així mateix, es va comprovar que la satisfacció és una mesura indirecta de la importància i constitueix un predictor adequat de l'adherència a ortesis. Per contra, la importància explícita no compta amb la mateixa fiabilitat. La segona fase, Disseny Participatiu, va incloure 9 persones voluntàries que van avaluar les propostes d'ortesis i van donar recomanacions de disseny. En la tercera fase, Modelatge i Prototipatge, es van produir una sèrie d'iteracions de disseny, donant lloc a un nou desenvolupament d'òrtesis. En la quarta fase, Validació, es va comprovar la funcionalitat i usabilitat de l'òrtesi amb 11 subjectes sans mitjançant un estudi amb electromiografia de superfície. Amb això es va demostrar que la inclusió d'un mecanisme deformable en el disseny del moll articular permet una òptima assistència motora en condicions normals. Finalment, en la fase de Desenvolupament Final, es va fabricar un prototip funcional d'òrtesi radial tenint en compte les oportunitats de millora identificades. / [EN] Peripheral neuropathies are pathologies that deteriorate the nerves located outside the central nervous system and significantly affect sensorimotor functions. There are several therapeutic alternatives, including orthoses. These devices are responsible for protecting the musculature, correcting alterations, and assisting the function of the affected limb. Their effectiveness has been demonstrated. However, it depends directly on proper compliance with the usage protocol. The main objective of this thesis was to identify ergonomic criteria applicable to the development of orthoses that increase treatment adherence in patients with radial, ulnar, and median neuropathies. To this end, the possibility of optimizing therapeutic properties by including electrophysical agents in the device was evaluated. To achieve this, a systematic review and meta-analysis of the available evidence in the last 40 years regarding the effectiveness of the primary applied modalities. It was determined that some modalities are favored when used in conjunction with an orthosis. Nevertheless, none of the review results were clinically significant. Subsequently, a co-creation protocol was proposed, involving the main phases of a design process with the participation of orthosis users. The first phase, User Perspective, involved 100 subjects with peripheral neuropathies. Information was obtained for the identification of needs and preferences, as well as for the classification of aspects involved in adherence. Linear and non-linear models, such as the Kano model, were employed. It was found that this model allows a more precise identification of which attributes are more important and their influence on adherence. Additionally, it was verified that satisfaction is an indirect measure of importance and constitutes an adequate predictor of orthosis adherence. In contrast, explicit importance is not a reliable indicator. The second phase, Participatory Design, included nine voluntary individuals who evaluated orthosis proposals and provided design recommendations. In the third phase, Modeling and Prototyping, a series of design iterations were carried out, resulting in a new orthosis development. The fourth phase, Validation, tested the functionality and usability of the orthosis with 11 healthy subjects through a study with surface electromyography. It was demonstrated that including a deformable mechanism in the joint spring design allows optimal motor assistance under normal conditions. Finally, in the Final Development phase, a functional prototype of the radial orthosis was manufactured, considering the identified opportunities for improvement. / Bula Oyola, EL. (2023). Factores ergonómicos en el diseño de órtesis de mano para rehabilitación sensoriomotora de neuropatías radial, cubital y mediana [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/199996

Patient reported outcome (PRO) measurement of disability is integral to a patient-centered approach to health care and gauging the biopsychosocial impact of health conditions from the patient's perspective. This thesis investigates disability after proximal humerus, elbow and distal radius fractures; conditions that constitute a major burden in musculoskeletal health care and a substantial impact on health-related quality of life (HrQoL). Disability is defined by the World Health Organisation (WHO) International Classification of Disability, Functioning and Health (ICF) as ‘a multi-dimensional construct involving a dynamic interaction between impairment, activity limitations and participation restrictions, that are influenced by contextual factors'. This international, consensus-based framework acts as a guide for the application of outcome measures in performing scientific research. The WHO ICF also considers other patient perspectives on health and health care systems, including patient experience and patient activation within the contextual factors component. Patient experience encompasses aspects such as satisfaction, expectation management and confidence with care, and is measured using a variety of scales and questionnaires. Patient activation relates to 'the knowledge, skills and confidence a person has in managing their own health and health care'. This concept is quantified using patient activation measures (PAMs). The overarching goal of this thesis is to identify the most influential factors predicting disability after proximal humerus, elbow and distal radius fractures. This work also aimed to define the relationship between disability, experience and activation to inform the development of a patient-centred approach to managing these challenging injuries. The first systematic review highlights the dominance of psychosocial factors in influencing disability associated with a range of upper extremity conditions. Few studies have assessed this relationship in specific trauma populations. The second review underlines the paucity of upper extremity PRO measures incorporating fracture populations in their original development. It also reports the highly variable quality of initial studies introducing these measures. The final review demonstrates the superior measurement properties of computer adaptive tests (CATs), a contemporary form of PRO measurement, over fixed-scale instruments. Few studies apply CATs in trauma and few have been performed outside the U.S. These reviews collectively informed the selection of PRO measures for the experimental studies in this thesis. Firstly, a pilot study establishes a methodology for addressing the key objectives and the feasibility of using a web-based platform for measuring patient outcomes. Strong correlation between PROMIS Physical function CAT, a computer adaptive measure of physical function, and the Quick Disabilities of the Arm, Shoulder and Hand (QuickDASH), a region-specific, fixed scale is observed. The core experiment (n=734) expands upon this work and demonstrates correlations between a range of generic and region-specific measures in an upper extremity trauma population. Disability is shown to correlate with satisfaction, and the strength of this correlation increases over time. Applying PRO measures of disability in populations with shoulder, elbow and wrist fractures show that self-efficacy (i.e. coping ability) within 6 weeks of injury was the strongest predictor of medium-term disability at 6-9 months. In proximal humerus and elbow fractures, kinesiophobia (i.e. fear of movement) within a week of injury was also a strong predictor of disability. The final study concludes that greater patient activation is associated with greater health-related and experiential outcomes. However, psychosocial factors including self-efficacy, superseded activation in predicting disability and satisfaction. This thesis contributes evidence for musculoskeletal health care professionals (HCPs) to consider specific psychosocial factors, such as coping abilities, and patient activation early in the recovery process to improve disability following these injuries.

No description available.

In the context of health improving, the measurement of vital parameters such as heart rate (HR) can provide solutions for health monitoring, prevention and screening for certain chronic diseases. Among the different technologies for HR measuring, photoplethysmography (PPG) technique embedded in smart watches is the most commonly used in the field of consumer electronics since it is comfortable and does not require any user intervention. To be able to provide an all day and night long HR monitoring method, difficulties associated with PPG signals vulnerability to Motion Artifact (MA) must be overcome. Conventional signal processing solutions (power spectral density analysis) have limited generalization capability as they are specific to certain types of movements, highlighting the interest of machine learning tools, particularly deep learning (DL). Since DL models in the literature are trained on data from a different sensor than the internal sensor, transfer learning may prove unsuccessful. This work proposes a DL approach for estimating HR from wrist PPG signals. The model is trained on internal data with a greater demographic diversity of participants. This project also illustrates the contribution of multi-path and multi-wavelength PPG instead of the conventional single green PPG solution. This work presents several models, called DeepTime, with selected input channels and wavelengths: Mono_Green, Multi_Green, Multi_Wavelength, and Multi_Channel_Multi_Wavelength. They take temporal PPG signals as inputs along with 3D acceleration and provide HR estimation every 2 seconds with an 8-second initialization. This convolutional neural network comprised of several input branches improves the existing Withings internal method’s overall Mean Absolute Error (MAE) from 9.9 BPM to 6.9 BPM on the holdout test set. This work could be completed and improved by adding signal temporal history using recurrent layers, such as Long-Short-Term-Memory (LSTM), training the model with a bigger dataset, improving preprocessing steps or using a more elaborate loss function that includes a trust score. / I sammanhanget av förbättring av hälsouppföljning kan mätning av vitala parametrar som hjärtfrekvens (HR) erbjuda lösningar för förebyggande och screening av vissa kroniska sjukdomar. Bland olika tekniker för mätning av HR är fotoplethysmografi (PPG) integrerad i smartklockor den vanligast använda inom elektronikområdet eftersom den är bekväm och inte kräver något användaringripande. För att erbjuda en kontinuerlig HRövervakningsmetod utgör sårbarheten hos PPG-signaler för rörelseartefakter (MA) en stor utmaning. Konventionella signalbehandlingslösningar (analys av effektspektraltäthet) har begränsad generaliseringsförmåga eftersom de är specifika för vissa typer av rörelser, vilket betonar intresset för maskininlärningsverktyg, särskilt djupinlärning (DL). Eftersom DL-modeller i litteraturen tränas på data från en annan sensor än den interna sensorn kan överföringsinlärning vara misslyckad. Detta arbete föreslår en DL-ansats för att uppskatta HR från PPG-signaler på handleden. Modellen tränas på interna data med en större demografisk mångfald bland deltagarna. Detta projekt illustrerar även bidraget från flervägs- och flervågs-PPG istället för den konventionella enkla gröna PPG-lösningen. Detta arbete presenterar flera modeller, kallade DeepTime, med utvalda ingångskanaler och våglängder: Mono_Green, Multi_Green, Multi_Wavelength och Multi_Channel_Multi_Wavelength. De tar in temporära PPG-signaler tillsammans med 3D-acceleration och ger HR-uppskattning var 2:a sekund med en initialisering på 8 sekunder. Detta konvolutionella neurala nätverk, som består av flera ingångsgrenar, förbättrar den totala medelabsoluta felet (MAE) från 9,9 BPM (befintlig intern metod) till 6,9 BPM på testuppsättningen. Detta arbete kan kompletteras och förbättras genom att integrera den temporala historiken hos signalen med hjälp av återkommande lager (som LSTM), träna modellen på mer data, förbättra förbehandlingsstegen eller välja en mer sofistikerad förlustfunktion som inkluderar ett konfidensvärde.