Machine Learning on Prediction of Relative Physical Activity Intensity Using Medical Radar Sensor and 3D Accelerometer.

BACKGROUND: One of the most critical topics in sports safety today is the reduction in injury risks through controlled fatigue using non-invasive athlete monitoring. Due to the risk of injuries, it is prohibited to use accelerometer-based smart trackers, activity measurement bracelets, and smart watches for recording health parameters during performance sports activities. This study analyzes the synergy feasibility of medical radar sensors and tri-axial acceleration sensor data to predict physical activity key performance indexes in performance sports by using machine learning (ML). The novelty of this method is that it uses a 24 GHz Doppler radar sensor to detect vital signs such as the heartbeat and breathing without touching the person and to predict the intensity of physical activity, combined with the acceleration data from 3D accelerometers. METHODS: This study is based on the data collected from professional athletes and freely available datasets created for research purposes. A combination of sensor data management was used: a medical radar sensor with no-contact remote sensing to measure the heart rate (HR) and 3D acceleration to measure the velocity of the activity. Various advanced ML methods and models were employed on the top of sensors to analyze the vital parameters and predict the health activity key performance indexes. three-axial acceleration, heart rate data, age, as well as activity level variances. RESULTS: The ML models recognized the physical activity intensity and estimated the energy expenditure on a realistic level. Leave-one-out (LOO) cross-validation (CV), as well as out-of-sample testing (OST) methods, have been used to evaluate the level of accuracy in activity intensity prediction. The energy expenditure prediction with three-axial accelerometer sensors by using linear regression provided 97-99% accuracy on selected sports (cycling, running, and soccer). The ML-based RPE results using medical radar sensors on a time-series heart rate (HR) dataset varied between 90 and 96% accuracy. The expected level of accuracy was examined with different models. The average accuracy for all the models (RPE and METs) and setups was higher than 90%. CONCLUSIONS: The ML models that classify the rating of the perceived exertion and the metabolic equivalent of tasks perform consistently.

Inference of Evolutionary Jumps in Large Phylogenies using Lévy Processes.

Although it is now widely accepted that the rate of phenotypic evolution may not necessarily be constant across large phylogenies, the frequency and phylogenetic position of periods of rapid evolution remain unclear. In his highly influential view of evolution, G. G. Simpson supposed that such evolutionary jumps occur when organisms transition into so-called new adaptive zones, for instance after dispersal into a new geographic area, after rapid climatic changes, or following the appearance of an evolutionary novelty. Only recently, large, accurate and well calibrated phylogenies have become available that allow testing this hypothesis directly, yet inferring evolutionary jumps remains computationally very challenging. Here, we develop a computationally highly efficient algorithm to accurately infer the rate and strength of evolutionary jumps as well as their phylogenetic location. Following previous work we model evolutionary jumps as a compound process, but introduce a novel approach to sample jump configurations that does not require matrix inversions and thus naturally scales to large trees. We then make use of this development to infer evolutionary jumps in Anolis lizards and Loriinii parrots where we find strong signal for such jumps at the basis of clades that transitioned into new adaptive zones, just as postulated by Simpson's hypothesis. [evolutionary jump; Lévy process; phenotypic evolution; punctuated equilibrium; quantitative traits.

Creeping through the cranium: A rare and interesting presentation of a meningioma.

A meningioma is a rare primary CNS tumor that tends to present more so in females in a slowly progressive fashion. The cavernous sinus and cerebellopontine angle are uncommon locations for meningiomas. We present a case of a meningioma in a 60-year-old female presenting to the emergency department for a sudden onset headache, vertigo, facial paresthesias, and chest pain. Inpatient workup revealed orthostatic hypotension, a meningioma spanning from the left cavernous sinus to the left cerebellopontine angle encasing the left cavernous internal carotid artery on MRI and CTA, and an incidental 12 mm calcified fibroadenoma on CT. Hospital course consisted of supportive treatment, physical rehabilitation, and review of previous imaging to determine need for intervention per consultants' recommendations. The patient was discharged with an antiplatelet, an antihistamine, appropriate additional medications, a vestibular therapy script, and outpatient referrals for a decision regarding surveillance and intervention. Overall, this case describes some key points. It demonstrates that cavernous sinus and cerebellopontine angle meningiomas can occur simultaneously, especially as a continuous mass, which very few cases have done so far. It also highlights an acute clinical presentation of a meningioma, contrary to the gradually progressive one observed in most instances. Last, but not least, it shows how nonspecific symptoms can lead to unique findings at times.

Focal Diastematomyelia in an Adult: A Case Report.

Diastematomyelia (DSM) is a rare congenital malformation that splits the spinal cord longitudinally into two by either cartilage, bone, or fibrous septum. There are multiple case reports of DSM in the pediatric population, but only a few cases of DSM in adult patients have been reported in the literature. This case report describes a middle-aged female patient who presented to the hospital with progressive worsening bilateral proximal lower extremity weakness. A neurological exam was significant for effort-dependent bilateral proximal lower extremity weakness. In addition, magnetic resonance imaging was consistent with an incidental finding of a focal structural-developmental anomaly of diastematomyelia at the distal conus medullaris of the spinal cord vertebral level L2-L3. Following no acute imaging or laboratory abnormalities, the patient was treated with pain management, physical therapy, and outpatient follow-up care. Even though there are multiple differential diagnoses of bilateral lower extremity weakness in adult patients, diastematomyelia malformation is rarely diagnosed in this age group. Therefore, knowledge of this rare congenital anomaly in adult patients should be familiar to interpreting radiologists and treating clinicians.

Detecting Selection from Linked Sites Using an F-Model.

Allele frequencies vary across populations and loci, even in the presence of migration. While most differences may be due to genetic drift, divergent selection will further increase differentiation at some loci. Identifying those is key in studying local adaptation, but remains statistically challenging. A particularly elegant way to describe allele frequency differences among populations connected by migration is the F-model, which measures differences in allele frequencies by population specific FST coefficients. This model readily accounts for multiple evolutionary forces by partitioning FST coefficients into locus- and population-specific components reflecting selection and drift, respectively. Here we present an extension of this model to linked loci by means of a hidden Markov model (HMM), which characterizes the effect of selection on linked markers through correlations in the locus specific component along the genome. Using extensive simulations, we show that the statistical power of our method is up to twofold higher than that of previous implementations that assume sites to be independent. We finally evidence selection in the human genome by applying our method to data from the Human Genome Diversity Project (HGDP).

Breast involvement in mixed connective tissue disease.

To date, mammographic involvement in mixed connective tissue disease has not been described in the literature to the authors' knowledge. In addition, only 2 case reports have described panniculitis in mixed connective tissue disease. We present a patient with mixed connective tissue disease with coarse sheet-like calcifications on mammography bilaterally, which increased over time corresponding to rise in levels of anti-dsDNA. Biopsy showed fat necrosis with calcifications, chronic inflammation and fibrosis, vasculitis, as well as CD3, CD4, and CD8+ T cells and CD20+ B cells. These findings are similar histologically and mammographically to "lupus mastitis."

Impact of inflammation-mediated response on pan-coronary plaque vulnerability, myocardial viability and ventricular remodeling in the postinfarction period - the VIABILITY study: Protocol for a non-randomized prospective clinical study.

INTRODUCTION: While the role of inflammation in acute coronary events is well established, the impact of inflammatory-mediated vulnerability of coronary plaques from the entire coronary tree, on the extension of ventricular remodeling and scaring, has not been clarified yet. MATERIALS AND METHODS: The present manuscript describes the procedures of the VIABILITY trial, a descriptive prospective single-center cohort study. The main purpose of this trial is to assess the link between systemic inflammation, pan-coronary plaque vulnerability (referring to the plaque vulnerability within the entire coronary tree), myocardial viability and ventricular remodeling in patients who had suffered a recent ST-segment elevation acute myocardial infarction (STEMI). One hundred patients with STEMI who underwent successful revascularization of the culprit lesion in the first 12 hours after the onset of symptoms will be enrolled in the study. The level of systemic inflammation will be evaluated based on the serum biomarker levels (hs-CRP, matrix metalloproteinases, interleukin-6) in the acute phase of the myocardial infarction (MI) and at 1 month. Pan-coronary plaque vulnerability will be assessed based on serum biomarkers known to be associated with increased plaque vulnerability (V-CAM or I-CAM) and at 1 month after infarction, based on computed tomographic angiography analysis of vulnerability features of all coronary plaques. Myocardial viability and remodeling will be assessed based on 3D speckle tracking echocardiography associated with dobutamine infusion and LGE-CMR associated with post-processing imaging methods. The study population will be categorized in 2 subgroups: subgroup 1 - subjects with STEMI and increased inflammatory response at 7 days after the acute event (hs-CRP ≥ 3 mg/dl), and subgroup 2 - subjects with STEMI and no increased inflammatory response at 7 days (hs-CRP < 3 mg/dl). Study outcomes will consist in the rate of post-infarction heart failure development and the major adverse events (MACE) rate. CONCLUSION: VIABILITY is the first prospective study designed to evaluate the influence of infarct-related inflammatory response on several major determinants of post-infarction outcomes, such as coronary plaque vulnerability, myocardial viability, and ventricular remodeling.

Medication status affects the relationship of symptoms to prepulse inhibition of acoustic startle in schizophrenia.

Inhibition of the acoustic startle response by a smaller preliminary nonstartling stimulus is termed prepulse inhibition (PPI). Schizophrenia patients have impairments in PPI that may not fully normalize even when they are clinically stable on medication, particularly typical antipsychotics. There is evidence that more severe symptoms are associated with more severe PPI abnormalities, but the effect of antipsychotics on this relationship is not clear. Seventy-three male schizophrenia patients underwent acoustic startle and PPI testing. Symptom ratings were performed using the Brief Psychiatric Rating Scale (BPRS) and its subscales. Fifty-two subjects were treated with antipsychotic medication at time of testing; 21 were unmedicated. For all subjects, PPI was negatively correlated with the BPRS psychological discomfort subscale but not with BPRS total symptoms, BPRS positive symptoms or BPRS negative symptoms. For medicated subjects analyzed separately, there were no correlations with BPRS total scores or any subscales. For the unmedicated subjects analyzed separately, there were significant correlations of lower PPI with greater severity of BPRS total symptoms, positive symptoms and the psychological discomfort subscale. These data indicate that more severe symptoms are associated with lower PPI, but that medication status is an important factor in the relationship between symptom severity and sensorimotor gating.

A modified two-stage Markov clustering algorithm for large and sparse networks.

BACKGROUND: Graph-based hierarchical clustering algorithms become prohibitively costly in both execution time and storage space, as the number of nodes approaches the order of millions. OBJECTIVE: A fast and highly memory efficient Markov clustering algorithm is proposed to perform the classification of huge sparse networks using an ordinary personal computer. METHODS: Improvements compared to previous versions are achieved through adequately chosen data structures that facilitate the efficient handling of symmetric sparse matrices. Clustering is performed in two stages: the initial connected network is processed in a sparse matrix until it breaks into isolated, small, and relatively dense subgraphs, which are then processed separately until convergence is obtained. An intelligent stopping criterion is also proposed to quit further processing of a subgraph that tends toward completeness with equal edge weights. The main advantage of this algorithm is that the necessary number of iterations is separately decided for each graph node. RESULTS: The proposed algorithm was tested using the SCOP95 and large synthetic protein sequence data sets. The validation process revealed that the proposed method can reduce 3-6 times the processing time of huge sequence networks compared to previous Markov clustering solutions, without losing anything from the partition quality. CONCLUSIONS: A one-million-node and one-billion-edge protein sequence network defined by a BLAST similarity matrix can be processed with an upper-class personal computer in 100 minutes. Further improvement in speed is possible via parallel data processing, while the extension toward several million nodes needs intermediary data storage, for example on solid state drives.

Inferior frontal white matter anisotropy and negative symptoms of schizophrenia: a diffusion tensor imaging study.

OBJECTIVE: The purpose of this study was test the hypothesis that abnormalities of inferior frontal white matter are related to the negative symptoms of schizophrenia. METHOD: Fractional anisotropy of white matter tracts in the prefrontal area of 10 schizophrenic patients was determined by diffusion tensor imaging. Patients were also assessed for severity of negative symptoms by using the Schedule for the Assessment of Negative Symptoms (SANS). RESULTS: Inferior frontal white matter fractional anisotropy was significantly inversely correlated with the SANS global ratings of negative symptoms. CONCLUSIONS: These data, while preliminary, suggest that impaired white matter integrity in the inferior frontal region may be associated with the severity of negative symptoms in schizophrenia.

Effect of treatment status on prepulse inhibition of acoustic startle in schizophrenia.

RATIONALE: The acoustic startle response is inhibited when the startling stimulus is preceded by a weaker non-startling acoustic stimulus. This phenomenon, termed prepulse inhibition of acoustic startle (PPI), is impaired in schizophrenics compared to normal controls. To date, there is conflicting evidence regarding whether PPI impairments improve with antipsychotic treatment. OBJECTIVES: To examine the effect of medication status on PPI in schizophrenic subjects. METHODS: First, we performed acoustic startle testing on 16 schizophrenic subjects when they were acutely decompensated off medication and later after they were stabilized on antipsychotic treatment. Second, in a between-group design, we tested 21 schizophrenic subjects off medication, 16 subjects on atypical neuroleptics, and 27 subjects on typical neuroleptics. RESULTS: In both the test-retest study and the between-group study, ANOVAs revealed no significant changes in startle to pulse alone stimuli, habituation of startle to pulse alone stimuli, PPI, latency to response onset, or latency to response peak between the treatment conditions. CONCLUSIONS: Our results do not support the hypothesis that impaired sensorimotor gating in schizophrenia improves with antipsychotic treatment. Rather, impaired gating persists despite symptomatic improvement on medication.

Effects of D-cycloserine on negative symptoms in schizophrenia.

INTRODUCTION: The negative and cognitive symptoms of schizophrenia are poorly responsive to neuroleptic treatment. Glutamatergic dysfunction may mediate some of these symptoms. Low dose D-cycloserine (DCS) is a partial agonist at the glycine site of the NMDA-associated receptor complex, noncompetitively enhancing NMDA neurotransmission. Prior studies suggest a beneficial effect of DCS on negative symptoms and cognition. This treatment trial was initiated to confirm and extend these findings. METHODS: Twenty-two male schizophrenic subjects displaying prominent negative symptoms who were stabilized on typical neuroleptics completed the study. A randomized double-blind parallel group design was used to compare the effects of 50 mg p.o. QD of DCS to placebo over 4 weeks. The two subject groups did not differ significantly in age, age of onset of illness or time on current neuroleptic treatment. Symptoms were rated by means of the SANS, BPRS and Abrams and Taylor rating scale. Cognition was assessed with the Sternberg Memory Test and the Continuous Performance Test. RESULTS: Both medication groups improved over the 4 weeks of treatment. However, there were no significant differences between the DCS and placebo group on any symptom rating. DCS effects on cognition did not differ from placebo. DISCUSSION: This study did not detect improvement in negative symptoms or cognitive performance with DCS treatment that has been found in some prior studies. This negative finding may be attributed to small sample size, relatively short duration of treatment and the overall modest effect of DCS. Future studies of DCS should be adequately powered to detect a small to medium effect size and should provide for a longer treatment phase than was used in this study in order to avoid a type II error.

Prepulse inhibition of acoustic startle in subjects with schizophrenia treated with olanzapine or haloperidol.

Studies of the acoustic startle response and of its inhibition by the presentation of a non-startling preliminary stimulus (prepulse inhibition, PPI) have revealed deficits in PPI in schizophrenic subjects compared to healthy controls. Animal studies indicate that atypical antipsychotics improve PPI deficits induced by NMDA antagonists more consistently than typical antipsychotics. The effect of medication status on PPI in schizophrenia is unresolved in the literature. In the current study the effects on PPI of the atypical antipsychotic olanzapine and the typical antipsychotic haloperidol were compared to the unmedicated state in subjects with schizophrenia. In a between-group design, 11 schizophrenic subjects on olanzapine, 16 subjects on haloperidol, and 14 subjects who were on no medication received acoustic startle testing with PPI determination. ANOVAs revealed no significant differences in startle to pulse alone stimuli, habituation of startle, or PPI between the olanzapine, haloperidol and unmedicated groups. These 41 subjects with schizophrenia were compared to a group of 21 historical healthy controls and found to have reduced PPI. These data do not indicate a preferential effect of olanzapine compared to haloperidol on sensorimotor gating in schizophrenia. The results are consistent with the hypothesis that PPI impairments are relatively stable across treatment conditions.

A fast hierarchical clustering algorithm for large-scale protein sequence data sets.

TRIBE-MCL is a Markov clustering algorithm that operates on a graph built from pairwise similarity information of the input data. Edge weights stored in the stochastic similarity matrix are alternately fed to the two main operations, inflation and expansion, and are normalized in each main loop to maintain the probabilistic constraint. In this paper we propose an efficient implementation of the TRIBE-MCL clustering algorithm, suitable for fast and accurate grouping of protein sequences. A modified sparse matrix structure is introduced that can efficiently handle most operations of the main loop. Taking advantage of the symmetry of the similarity matrix, a fast matrix squaring formula is also introduced to facilitate the time consuming expansion. The proposed algorithm was tested on protein sequence databases like SCOP95. In terms of efficiency, the proposed solution improves execution speed by two orders of magnitude, compared to recently published efficient solutions, reducing the total runtime well below 1min in the case of the 11,944proteins of SCOP95. This improvement in computation time is reached without losing anything from the partition quality. Convergence is generally reached in approximately 50 iterations. The efficient execution enabled us to perform a thorough evaluation of classification results and to formulate recommendations regarding the choice of the algorithm׳s parameter values.

Efficient Markov clustering algorithm for protein sequence grouping.

In this paper we propose an efficient reformulation of a Markov clustering algorithm, suitable for fast and accurate grouping of protein sequences, based on pairwise similarity information. The proposed modification consists of optimal reordering of rows and columns in the similarity matrix after every iteration, transforming it into a matrix with several compact blocks along the diagonal, and zero similarities outside the blocks. These blocks are treated separately in later iterations, thus reducing the computational burden of the algorithm. The proposed algorithm was tested on protein sequence databases like SCOP95. In terms of efficiency, the proposed solution achieves a speed-up factor in the range 15-50 compared to the conventional Markov clustering, depending on input data size and parameter settings. This improvement in computation time is reached without losing anything from the partition accuracy. The convergence is usually reached in 40-50 iterations. Combining the proposed method with sparse matrix representation and parallel execution will certainly lead to a significantly more efficient solution in future.

Efficient inhomogeneity compensation using fuzzy c-means clustering models.

Intensity inhomogeneity or intensity non-uniformity (INU) is an undesired phenomenon that represents the main obstacle for magnetic resonance (MR) image segmentation and registration methods. Various techniques have been proposed to eliminate or compensate the INU, most of which are embedded into classification or clustering algorithms, they generally have difficulties when INU reaches high amplitudes and usually suffer from high computational load. This study reformulates the design of c-means clustering based INU compensation techniques by identifying and separating those globally working computationally costly operations that can be applied to gray intensity levels instead of individual pixels. The theoretical assumptions are demonstrated using the fuzzy c-means algorithm, but the proposed modification is compatible with a various range of c-means clustering based INU compensation and MR image segmentation algorithms. Experiments carried out using synthetic phantoms and real MR images indicate that the proposed approach produces practically the same segmentation accuracy as the conventional formulation, but 20-30 times faster.

A patient specific electro-mechanical model of the heart.

This paper presents a patient specific deformable heart model that involves the known electrical and mechanical properties of the cardiac cells and tissue. The whole heart model comprises ten Tusscher's ventricular and Nygren's atrial cell models, the anatomical and electrophysiological model descriptions of the atria (introduced by Harrild et al.) and ventricle (given by Winslow et al.), and the mechanical model of the periodical cardiac contraction and resting phenomena proposed by Moireau et al. During the propagation of the depolarization wave, the kinetic, compositional and rotational anisotropy is handled by the tissue, organ and torso model. The applied patient specific parameters were determined by an evolutionary computation method. An intensive parameter reduction was performed using the abstract formulation of the searching space. This patient specific parameter representation enables the adjustment of deformable model parameters in real-time. The validation process was performed using simultaneously measured ECG and ultrasound image records that were compared with simulated signals and shapes using an abstract, parameterized evaluation criterion.

An enhanced method for accessory pathway localization in case of Wolff-Parkinson-White syndrome.

This paper presents an analysis of the Arruda accessory pathway localization method for patients suffering from Wolff-Parkinson-White syndrome, with modifications to increase the overall accuracy. The Arruda method was tested on a total of 79 cases, and 91.1% localization performance was reached. After a deeper analysis of each decision point of the Arruda localization method, we considered that the lead aVF was not as relevant as other leads (I, II, III, V1) used. The branch of the decision tree, which evaluates the left ventricle positions, was entirely replaced using different decision criteria based on the same biological parameters. The modified algorithm significantly improves the localization accuracy in the left ventricle, reaching 94.9%. An accurate localization performance of non-invasive methods is relevant because it can enlighten the necessary invasive interventions, and it also reduces the discomfort caused to the patient.

Inhomogeneity compensation for MR brain image segmentation using a multi-stage FCM-based approach.

Intensity inhomogeneity or intensity non-uniformity (INU) is an undesired phenomenon that represents the main obstacle for MR image segmentation and registration methods. Various techniques have been proposed to eliminate or compensate the INU, most of which are embedded into clustering algorithms. This paper proposes a multiple stage fuzzy c-means (FCM) based algorithm for the estimation and compensation of the slowly varying additive or multiplicative noise, supported by a pre-filtering technique for Gaussian and impulse noise elimination. The slowly varying behavior of the bias or gain field is assured by a smoothening filter that performs a context dependent averaging, based on a morphological criterion. The experiments using 2-D synthetic phantoms and real MR images show, that the proposed method provides accurate segmentation. The produced segmentation and fuzzy membership values can serve as excellent support for 3-D registration and segmentation techniques.

A novel ECG telemetry and monitoring system based on Z-Wave communication.

This paper presents a novel ECG telemetry system based on Z-Wave communication protocol. The proposed system consists of small portable devices that acquire, compress and transmit the ECG to a RF-USB interface connected to a central monitoring computer. The received signals are filtered, QRS complexes and P and T waves are localized, and different waveforms are classified in order to be able to provide diagnosis tools like heart rate variability and turbulence analysis. Due to the limitation of communication bandwidth, the maximum number of measuring devices connected to a central monitor is four. The proposed system composed of inexpensive components can serve as flexible alternative to current ECG monitoring systems.