Application of neural networks for the detection of oral cancer: A systematic review

One potential application of neural networks (NNs) is the early-stage detection of oral cancer. This systematic review aimed to determine the level of evidence on the sensitivity and specificity of NNs for the detection of oral cancer, following the Preferred Reporting Items for Systematic Reviews and MetaAnalyses (PRISMA) and Cochrane guidelines. Literature sources included PubMed, ClinicalTrials, Scopus, Google Scholar, and Web of Science. In addition, the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool was used to assess the risk of bias and the quality of the studies. Only 9 studies fully met the eligibility criteria. In most studies, NNs showed accuracy greater than 85%, though 100% of the studies presented a high risk of bias, and 33% showed high applicability concerns. Nonetheless, the included studies demonstrated that NNs were useful in the detection of oral cancer. However, studies of higher quality, with an adequate methodology, a low risk of bias and no applicability concerns are required so that more robust conclusions could be reached.

Improving Adherence to Physical Therapy in the Development of Serious Games: Conceptual Framework Design Study

BACKGROUND

Insufficient levels of treatment adherence can have adverse effects on the outcomes of physical rehabilitation. To address this issue, alternative approaches to traditional therapies, such as serious games, have been designed to enhance adherence. Nevertheless, there remain gaps in the development of serious games concerning the effective implementation of motivation, engagement, and the enhancement of treatment adherence.

OBJECTIVE

This study aims to design a conceptual framework for the development of serious games that incorporate essential adherence factors to enhance patient compliance with physical rehabilitation programs.

METHODS

We formulated a conceptual framework using iterative techniques inspired by a conceptual framework analysis. Initially, we conducted a comprehensive literature review, concentrating on the critical adherence factors in physical rehabilitation. Subsequently, we identified, categorized, integrated, and synthesized the concepts derived from the literature review to construct the conceptual framework.

RESULTS

The framework resembles a road map, comprising 3 distinct phases. In the initial phase, the patient's characteristics are identified through an initial exploration. The second phase involves the development of a serious game, with a focus on enhancing treatment adherence by integrating the key adherence factors identified. The third phase revolves around the evaluation of the serious game. These phases are underpinned by 2 overarching themes, namely, a user-centered design and the GameFlow model.

CONCLUSIONS

The conceptual framework offers a detailed, step-by-step guide for creating serious games that incorporate essential adherence factors, thereby contributing to improved adherence in the physical rehabilitation process. To establish its validity, further evaluations of this framework across various physical rehabilitation programs and user groups are necessary.

Accuracy of machine learning algorithms for the assessment of upper-limb motor impairments in patients with post-stroke hemiparesis: A systematic review and meta-analysis

BACKGROUND

The assessment of motor function is vital in post-stroke rehabilitation protocols, and it is imperative to obtain an objective and quantitative measurement of motor function. There are some innovative machine learning algorithms that can be applied in order to automate the assessment of upper extremity motor function.

OBJECTIVES

To perform a systematic review and meta-analysis of the efficacy of machine learning algorithms for assessing upper limb motor function in post-stroke patients and compare these algorithms to clinical assessment.

MATERIAL AND METHODS

The protocol was registered in the International Prospective Register of Systematic Reviews (PROSPERO) database. The review was carried out according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and the Cochrane Handbook for Systematic Reviews of Interventions. The search was performed using 6 electronic databases. The meta-analysis was performed with the data from the correlation coefficients using a random model.

RESULTS

The initial search yielded 1626 records, but only 8 studies fully met the eligibility criteria. The studies reported strong and very strong correlations between the algorithms tested and clinical assessment. The meta-analysis revealed a lack of homogeneity (I2 = 85.29%, Q = 48.15), which is attributable to the heterogeneity of the included studies.

CONCLUSION

Automated systems using machine learning algorithms could support therapists in assessing upper extremity motor function in post-stroke patients. However, to draw more robust conclusions, methodological designs that minimize the risk of bias and increase the quality of the methodology of future studies are required.

Software Engineering Frameworks Used for Serious Games Development in Physical Rehabilitation: Systematic Review

Background

Serious games are a support in the rehabilitation process for treating people with physical disabilities. However, many of these serious games are not adapted to the patient’s needs because they are not developed with a software engineering framework with a set of activities, actions, and tasks that must be executed when creating a software product. Better serious games for rehabilitation will be developed if the patient and therapist requirements are identified, the development is planned, and system improvements and feedback are involved. The goal is that the serious game must offer a more attractive environment, while maintaining patient interest in the rehabilitation process.

Objective

This paper submits the results of a systematic review of serious games in physical rehabilitation identifying the benefits of using a software engineering framework.

Methods

A systematic research was conducted using PubMed, PEDro (Physiotherapy Evidence Database), IEEE Xplore, ScienceDirect, ACM Digital Library, Mary Ann Liebert, Taylor & Francis Online, Wiley Online Library, and Springer databases. The initial search resulted in 701 papers. After assessing the results according to the inclusion criteria, 83 papers were selected for this study.

Results

From the 83 papers reviewed, 8 used a software engineering framework for its development. Most of them focused their efforts on 1 or more aspects, such as data acquisition and processing, game levels, motivation, therapist supervision.

Conclusions

This systematic review proves that most of the serious games do not use a software engineering framework for their development. As a result, development systems overlook several aspects and do not have a standardized process, eventually omitting important implementation aspects, which impact the patient’s recovery time.

Standardizing the Development of Serious Games for Physical Rehabilitation: Conceptual Framework Proposal

Background

Serious games have been used as supportive therapy for traditional rehabilitation. However, most are designed without a systematic process to guide their development from the phases of requirement identification, planning, design, construction, and evaluation, which reflect the lack of adaptation of rehabilitation requirements and thus the patient’s needs.

Objective

The aim of this study was to propose a conceptual framework with standardized elements for the development of information systems by using a flexible and an adaptable process centered on the patient’s needs and focused on the creation of serious games for physical rehabilitation.

Methods

The conceptual framework is based on 3 fundamental concepts: (1) user-centered design, which is an iterative design process focused on users and their needs at each phase of the process, (2) generic structural activities of software engineering, which guides the independent development process regardless of the complexity or size of the problem, and (3) gamification elements, which allow the transformation of obstacles into positive and fun reinforcements, thereby encouraging patients in their rehabilitation process.

Results

We propose a conceptual framework to guide the development of serious games through a systematic process by using an iterative and incremental process applying the phases of context identification, user requirements, planning, design, construction of the interaction devices and video game, and evaluation.

Conclusions

This proposed framework will provide developers of serious games a systematic process with standardized elements for the development of flexible and adaptable software with a high level of patient commitment, which will effectively contribute to their rehabilitation process.

Optimizing an LED array for an infrared illumination source using the near field for venous pattern detection

Accuracy in vein detection is important for intravenous applications such as venipuncture and other medical procedures. The near-infrared (NIR) imaging technique is used to visualize veins based on the difference of absorption of the infrared light by the oxyhemoglobin present in the blood and surrounding tissue. A problem commonly found during the visualization of veins is attributed to the source of light, saturation, low contrast, and dispersion, which are causes of inhomogeneous illumination. In this work, the design and implementation of a light source with LEDs in the range of 750-860 nm are presented. To obtain the design, a numerical simulation was made using the near-field diffraction theory to obtain homogeneous illumination at 40 cm of the sample, with a radial arrangement of three concentric LED rings. With the developed light source, an experimental scheme for the acquisition of vein patterns was implemented. Using a basic algorithm for the identification of intravenous patterns, a prototype was obtained that we believe can be used in intravenous applications and other medical procedures.

A portable system with sample rate of 250 Hz for characterization of knee and hip angles in the sagittal plane during gait

Background

Gait analysis and research have been developed to obtain characteristics of movement patterns of people while walking. However, traditional measuring systems present different drawbacks that reduce their use and application. Among those drawbacks one can find: high price, low sampling frequency and limiting number of steps to be analyzed. Traditional measuring gait systems carry out their measurement at frequencies oscillating between 60 to 100 Hz. It can be argued about the need of higher sampling rates for gait measurements. However small displacements of the knee or hip for example, cannot be seen with low frequencies required a more detailed sampling and higher frequency sampling. Bearing this in mind, in this paper is presented a 250 Hz system based on accelerometers for gait measurement, and the particularities of knee and hip angles during gait are highlighted.

Methods

The system was designed with a PCI data acquisition card instrumented with an FPGA to achieve a rate sample of 250 Hz. The accelerometers were placed in thighs and legs to calculate the joint angles of hip and knee in the sagittal plane. The angles were estimated using the acceleration polygon method without integrating the acceleration and without filters.

Results

The gait of thirty healthy people of Mexican phenotype was analyzed over a flat floor free of obstacles. The results showed the gait phases and particularities associated with the walking style and people's laterality; the movement patterns were similar in the thirty persons. Based on the results, the particularities as the maximum amplitude in the angles and the shape in the movement patterns were related to the anthropometry and people phenotype.

Conclusions

The sampling frequency was essential to record 340 samples in single gait cycle and so registering the gait cycle with its particularities. In this work were recorded an average of 8 to 10 gait cycles, and the results showed variation regarding works carried out in biomechanics laboratories; this variation was related to the method and reference frame used to obtain the joint angles and the accuracy of measurement system.