Decoding children dental health risks: a machine learning approach to identifying key influencing factors.

Introduction and objectives: This study investigates key factors influencing dental caries risk in children aged 7 and under using machine learning techniques. By addressing dental caries' prevalence, it aims to enhance early identification and preventative strategies for high-risk individuals. Methods: Data from clinical examinations of 356 children were analyzed using Logistic Regression, Decision Trees, and Random Forests models. These models assessed the influence of dietary habits, fluoride exposure, and socio-economic status on caries risk, emphasizing accuracy, precision, recall, F1 score, and AUC metrics. Results: Poor oral hygiene, high sugary diet, and low fluoride exposure were identified as significant caries risk factors. The Random Forest model demonstrated superior performance, illustrating the potential of machine learning in complex health data analysis. Our SHAP analysis identified poor oral hygiene, high sugary diet, and low fluoride exposure as significant caries risk factors. Conclusion: Machine learning effectively identifies and quantifies dental caries risk factors in children. This approach supports targeted interventions and preventive measures, improving pediatric dental health outcomes. Clinical significance: By leveraging machine learning to pinpoint crucial caries risk factors, this research lays the groundwork for data-driven preventive strategies, potentially reducing caries prevalence and promoting better dental health in children.

A machine learning approach for differentiating bipolar disorder type II and borderline personality disorder using electroencephalography and cognitive abnormalities.

This study addresses the challenge of differentiating between bipolar disorder II (BD II) and borderline personality disorder (BPD), which is complicated by overlapping symptoms. To overcome this, a multimodal machine learning approach was employed, incorporating both electroencephalography (EEG) patterns and cognitive abnormalities for enhanced classification. Data were collected from 45 participants, including 20 with BD II and 25 with BPD. Analysis involved utilizing EEG signals and cognitive tests, specifically the Wisconsin Card Sorting Test and Integrated Cognitive Assessment. The k-nearest neighbors (KNN) algorithm achieved a balanced accuracy of 93%, with EEG features proving to be crucial, while cognitive features had a lesser impact. Despite the strengths, such as diverse model usage, it's important to note limitations, including a small sample size and reliance on DSM diagnoses. The study suggests that future research should explore multimodal data integration and employ advanced techniques to improve classification accuracy and gain a better understanding of the neurobiological distinctions between BD II and BPD.

Artificial intelligence approaches for tinnitus diagnosis: leveraging high-frequency audiometry data for enhanced clinical predictions.

This research investigates the application of machine learning to improve the diagnosis of tinnitus using high-frequency audiometry data. A Logistic Regression (LR) model was developed alongside an Artificial Neural Network (ANN) and various baseline classifiers to identify the most effective approach for classifying tinnitus presence. The methodology encompassed data preprocessing, feature extraction focused on point detection, and rigorous model evaluation through performance metrics including accuracy, Area Under the ROC Curve (AUC), precision, recall, and F1 scores. The main findings reveal that the LR model, supported by the ANN, significantly outperformed other machine learning models, achieving an accuracy of 94.06%, an AUC of 97.06%, and high precision and recall scores. These results demonstrate the efficacy of the LR model and ANN in accurately diagnosing tinnitus, surpassing traditional diagnostic methods that rely on subjective assessments. The implications of this research are substantial for clinical audiology, suggesting that machine learning, particularly advanced models like ANNs, can provide a more objective and quantifiable tool for tinnitus diagnosis, especially when utilizing high-frequency audiometry data not typically assessed in standard hearing tests. The study underscores the potential for machine learning to facilitate earlier and more accurate tinnitus detection, which could lead to improved patient outcomes. Future work should aim to expand the dataset diversity, explore a broader range of algorithms, and conduct clinical trials to validate the models' practical utility. The research highlights the transformative potential of machine learning, including the LR model and ANN, in audiology, paving the way for advancements in the diagnosis and treatment of tinnitus.

Versatile Microfluidics for Biofabrication Platforms Enabled by an Agile and Inexpensive Fabrication Pipeline.

Microfluidics have transformed diagnosis and screening in regenerative medicine. Recently, they are showing much promise in biofabrication. However, their adoption is inhibited by costly and drawn-out lithographic processes thus limiting progress. Here, multi-material fibers with complex core-shell geometries with sizes matching those of human arteries and arterioles are fabricated employing versatile microfluidic devices produced using an agile and inexpensive manufacturing pipeline. The pipeline consists of material extrusion additive manufacturing with an innovative continuously varied extrusion (CONVEX) approach to produce microfluidics with complex seamless geometries including, novel variable-width zigzag (V-zigzag) mixers with channel widths ranging from 100-400 µm and hydrodynamic flow-focusing components. The microfluidic systems facilitated rapid mixing of fluids by decelerating the fluids at specific zones to allow for increased diffusion across the interfaces. Better mixing even at high flow rates (100-1000 µL min-1 ) whilst avoiding turbulence led to high cell cytocompatibility (>86%) even when 100 µm nozzles are used. The presented 3D-printed microfluidic system is versatile, simple and efficient, offering a great potential to significantly advance the microfluidic platform in regenerative medicine.

Efficient Observer Design for Ambulatory Estimation of Body Centre of Mass Position.

Complementary Linear Filter (CLF) is a common techinque employed for estimating the ground projection of body Centre of Mass starting from ground reaction forces. This method fuses centre of pressure position and double integration of horizontal forces, selecting best cut-off frequencies for low-pass and high-pass filters. Classical Kalman filter is a substantially equivalent approach, as both methods rely on an overall quantification of error/noise and don't analyze its origin and time-dependence. In order to overcome such limitations, a Time-Varying Kalman Filter (TVKF) is proposed in this paper: the effect of unknown variables is directly taken into account by employing a statistical description which is obtained from experimental data. To this end, in this paper we have employed a dataset of 8 walking healthy subjects: beside supplying gait cycles at different speeds, it deals with subjects in age of development and provides a wide range of body sizes, allowing therefore to assess the observers' behaviour under different conditions. The comparison carried out between CLF and TVKF appears to highlight several advantages of the latter method in terms of better average performance and smaller variability. Results presented in this paper suggest that a strategy which incorporates a statistical description of unknown variables and a time-varying structure can yield a more reliable observer. The demonstrated methodology sets a tool that can undergo a broader investigation to be carried out including more subjects and different walking styles.

Simulated muscle activity in locomotion: implications of co-occurrence between effort minimisation and gait modularity for robot-assisted rehabilitation therapy.

Evolution of gait rehabilitation robotic devices for stroke survivors has aimed at providing transparency to user's efforts and implementing 'assist-as-needed' paradigm. Alteration of muscle activity and synergies recruitment has been noticed in trials involving healthy subjects but no analytic tool has been proposed to understand root causes. In this paper, a simplified neuro-mechanical model is introduced for simulating lower limbs' muscle activity during unrestrained and device-constrained gait, taking into consideration exoskeleton-plus-treadmill and end-effector categories. Muscle control is based on the key hypothesis that optimality criterion pursues co-occurrence between effort minimisation and modularity during regular gait. Results highlight that modelised motion constraints on lower body raise additional redundancies which alter muscle activity and increase intervention external to unrestrained gait synergies. Accordingly, the developed simulations help to identify the inherent limitations of current technology: further degree of freedom addition to exoskeleton-plus-treadmill device could be useful but impractical, while end-effector devices would benefit significantly from an improved interaction management.

Real-time deep learning-based image recognition for applications in automated positioning and injection of biological cells.

Biological cell injection is an effective method in which a foreign material is directly introduced into a biological cell. Since human involvement reduces the success rate of the biological microinjection procedure, an extensive research effort has been made towards its automation. The accurate positioning of a randomly placed biological cell in the microscope's field of view is a prerequisite for any automated injection procedure. Vision is the primary source for visual servoing in microinjection applications. For this reason, a visual sensing system is required to recognise, calculate, and manipulate the cell to the desired position. In this study, eight different pretrained neural networks were analysed and used as a backbone for the YOLOv2 object detection method, and the optimal network was evaluated based on mean Intersection over Union (IoU) accuracy, average precision (AP) at different thresholds, and frame rate (fps) in our dataset. YOLOv2 with Resnet-50 model demonstrated superior performance with 89% mean IoU accuracy and 100% detection accuracy at an average of 33 fps. Ten different sets of experiments were conducted to examine the algorithm by verifying the zebrafish embryo gradual presence within the field of view to bring the zebrafish embryo to the predefined position. Experimental results demonstrated that the developed solution performed real-time with high accuracy and illustrates auto-positioning with a 100% success rate regardless of the initial position of the biological cell within the Petri dish. Later, the generalization of the proposed solution was verified in a different dataset from the real microinjection setup.

Vision-Based Sensor for Three-Dimensional Vibrational Motion Detection in Biological Cell Injection.

Intracytoplasmic sperm injection (ICSI) is an infertility treatment where a single sperm is immobilised and injected into the egg using a glass injection pipette. Minimising vibration in three orthogonal axes is essential to have precise injector motion and full control during the egg injection procedure. Vibration displacement sensing using physical sensors in ICSI operation is challenging since the sensor interfacing is not practically feasible. This study proposes a non-invasive technique to measure the three-dimensional vibrational motion of the injection pipette by a single microscope camera during egg injection. The contrast-limited adaptive histogram equalization (CHALE) method and blob analyses technique were employed to measure the vibration displacement in axial and lateral axes, while the actual dimension of the focal axis was directly measured using the Brenner gradient algorithm as a focus measurement algorithm. The proposed algorithm operates between the magnifications range of 4× to 40× with a resolution of half a pixel. Experiments using the proposed vision-based algorithm were conducted to measure and verify the vibration displacement in axial and lateral axes at various magnifications. The results were compared against manual procedures and the differences in measurements were up to 2% among all magnifications. Additionally, the effect of injection speed on lateral vibration displacement was measured experimentally and was used to determine the values for egg deformation, force fluctuation, and penetration force. It was shown that increases in injection speed significantly increases the lateral vibration displacement of the injection pipette by as much as 54%. It has been demonstrated successfully that visual sensing has played a key role in identifying the limitation of the egg injection speed created by lateral vibration displacement of the injection pipette tip.

Effect of Injection Speed on Oocyte Deformation in ICSI.

Oocyte deformation during injection is a major cause of potential cell damage which can lead to failure in the Intracytoplasmic Sperm Injection (ICSI) operation used as an infertility treatment. Injection speed plays an important role in the deformation creation. In this paper the effect of different speeds on deformation of zebrafish embryos is studied using a specially designed experimental set-up. An analytical model is developed in order to link injection force, deformation, and injection speed. A finite element (FE) model is also developed to analyse the effect of injection speed, allowing the production of additional information that is difficult to obtain experimentally, e.g., deformation and stress fields on the oocyte. The numerical model is validated against experimental results. Experimental results indicate that by increasing the injection speed, the deformation decreases. However, higher speeds cause higher levels of injection force and force fluctuation, leading to a higher vibration during injection. For this reason, an optimum injection speed range is determined. Finally, the FE model was validated against experimental results. The FE model is able to predict the force-deformation variation during injection for different speeds. This proves to be useful for future studies investigating different injection conditions.

Oocyte Positional Recognition for Automatic Manipulation in ICSI.

Polar body position detection is a necessary process in the automation of micromanipulation systems specifically used in intracytoplasmic sperm injection (ICSI) applications. The polar body is an intracellular structure, which accommodates the chromosomes, and the injection must not only avoid this structure but be at the furthest point away from it. This paper aims to develop a vision recognition system for the recognition of the oocyte and its polar body in order to be used to inform the automated injection mechanism to avoid the polar body. The novelty of the paper is its capability to determine the position and orientation of the oocyte and its polar body. The gradient-weighted Hough transform method was employed for the detection of the location of the oocyte and its polar body. Moreover, a new elliptical fitting method was employed for size measurement of the polar bodies and oocytes for the allowance of morphological variance of the oocytes and their polar bodies. The proposed algorithm has been designed to be adaptable with typical commercial inverted microscopes with different criteria. The successful experimental results for this algorithm produce maximum errors of 5% for detection and 10% for reporting respectively.

Targeting effect on gait parameters in healthy individuals and post-stroke hemiparetic individuals.

BACKGROUND: A targeting effect may occur in any gait analysis trial where the participant is instructed to step in a particular area or a clearly marked target is in their path. The targeting effect may affect the gait parameters and any variability being studied in regard to the participants. There are few studies examining this effect for healthy subjects and none for special populations. METHODS: This study aimed to investigate if any targeting effects occurred in healthy and stroke-survivor populations. Eight male participants were recruited, four of whom exhibited right-hand side hemiparesis resulting from stroke. Each participant performed a series of gait trials at a comfortable walking pace after being made aware of the force plate in the centre of the walkway. The participants gait was then analysed and compared before and after the target force plate. RESULTS: The results of the trials showed significant variations (p < 0.005) in the spatiotemporal gait parameters in both the healthy and stroke-survivor groups indicating a targeting effect. CONCLUSIONS: The effects were similar in both groups with the step speed and length being slower and shorter for the targeting step compared to the step after the force plate.

An optimized design of a parallel robot for gait training.

The guidelines for enhancing robot-assisted training for post-stroke survivors head towards increasing exercise realism and variability; in particular lower limb rehabilitation needs the patient to feel challenged to adapt his locomotion and dynamic balance capabilities to different virtual ground scenarios. This paper proposes a design for a robot whose end-effector acts as a footplate to be in permanent contact with the user's foot during practice: the structure is such that it enables the user's foot to rotate around three axis, differently from what is currently available in the research for gait training; the parallel kinematic structure and the dimensional synthesis allow a suitable range of motion and aim at limiting device mass, footprint and reaction forces on the actuators when rendering virtual ground. The employed methodology has been validated using ground reaction forces data relative to stroke survivors.

Parallel Robot for Lower Limb Rehabilitation Exercises.

The aim of this study is to investigate the capability of a 6-DoF parallel robot to perform various rehabilitation exercises. The foot trajectories of twenty healthy participants have been measured by a Vicon system during the performing of four different exercises. Based on the kinematics and dynamics of a parallel robot, a MATLAB program was developed in order to calculate the length of the actuators, the actuators' forces, workspace, and singularity locus of the robot during the performing of the exercises. The calculated length of the actuators and the actuators' forces were used by motion analysis in SolidWorks in order to simulate different foot trajectories by the CAD model of the robot. A physical parallel robot prototype was built in order to simulate and execute the foot trajectories of the participants. Kinect camera was used to track the motion of the leg's model placed on the robot. The results demonstrate the robot's capability to perform a full range of various rehabilitation exercises.

Lower Limb Rehabilitation Using Patient Data.

The aim of this study is to investigate the performance of a 6-DoF parallel robot in tracking the movement of the foot trajectory of a paretic leg during a single stride. The foot trajectories of nine patients with a paretic leg including both males and females have been measured and analysed by a Vicon system in a gait laboratory. Based on kinematic and dynamic analysis of a 6-DoF UPS parallel robot, an algorithm was developed in MATLAB to calculate the length of the actuators and their required forces during all trajectories. The workspace and singularity points of the robot were then investigated in nine different cases. A 6-DoF UPS parallel robot prototype with high repeatability was designed and built in order to simulate a single stride. Results showed that the robot was capable of tracking all of the trajectories with the maximum position error of 1.2 mm.

Differential influence of ampullary and isthmic derived epithelial cells on zona pellucida hardening and in vitro fertilization in ovine.

The central role of the oviduct, as the site of zona pellucida (ZP) maturation, fertilization and early embryogenesis, has been recognized. The objective of this study was to investigate whether ampullary and isthmic derived epithelial cells have different effects on in vitro ZP hardening, in vitro fertilization (IVF) and in vitro culture (IVC) of the resulting embryos. Cumulus oocyte complexes (COCs) were matured in a coculture system with ampullary/isthmic epithelial cells, TCM199 supplemented with insulin-like growth factor I (IGF-I) and epithelial derived growth factor (EGF) (GF treated group), conditioned media produced using ampullary (ACM), isthmic (ICM), COCs+ampullary, and COCs+isthmic epithelial cells, contactless culture system, oviductal fluid, GF+ACM/ICM, and drops of TCM199 (control), for 24h. The matured oocytes were randomly divided into two groups: Group I was subjected to ZP digestion; Group II underwent IVF. The duration of the ZP digestion, in a coculture system with ampullary epithelial cells (AE) was significantly increased (p<0.05), compared with other groups. Penetrated oocytes and monospermic fertilization were significantly increased (p<0.05) in the AE group. The mean number of spermatozoa per penetrated oocyte was reduced dramatically for the AE group (p<0.05). A significant increase (p<0.05) in the embryo development was observed in all treated groups, compared to the control. Results revealed that epithelial cells harvested from the ampullary segment of the oviduct had in vitro specialized role in ZP hardening and have subsequent IVF and IVC outcomes.