Search

Alzheimer's disease (AD) is a neurodegenerative condition characterized by a gradual decline in cognitive functions. Currently, there are no effective treatments for AD, underscoring the importance of identifying individuals in the preclinical stages of mild cognitive impairment (MCI) to enable early interventions. Among the neuropathological events associated with the onset of the disease is the accumulation of amyloid protein in the brain, which correlates with decreased levels of Aβ42 peptide in the cerebrospinal fluid (CSF). Consequently, the development of non-invasive, low-cost, and easy-to-administer proxies for detecting Aβ42 positivity in CSF becomes particularly valuable. A promising approach to achieve this is spontaneous speech analysis, which combined with machine learning (ML) techniques, has proven highly useful in AD. In this study, we examined the relationship between amyloid status in CSF and acoustic features derived from the description of the Cookie Theft picture in MCI patients from a memory clinic. The cohort consisted of fifty-two patients with MCI (mean age 73 years, 65% female, and 57% positive amyloid status). Eighty-eight acoustic parameters were extracted from voice recordings using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), and several ML models were used to classify the amyloid status. Furthermore, interpretability techniques were employed to examine the influence of input variables on the determination of amyloid-positive status. The best model, based on acoustic variables, achieved an accuracy of 75% with an area under the curve (AUC) of 0.79 in the prediction of amyloid status evaluated by bootstrapping and Leave-One-Out Cross Validation (LOOCV), outperforming conventional neuropsychological tests (AUC = 0.66). Our results showed that the automated analysis of voice recordings derived from spontaneous speech tests offers valuable insights into AD biomarkers during the preclinical stages. These findings introduce novel possibilities for the use of digital biomarkers to identify subjects at high risk of developing AD. [ABSTRACT FROM AUTHOR]

Copyright of HNO is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Background Rehabilitation medicine is facing a new development phase thanks to a recent wave of rigorous clinical trials aimed at improving the scientific evidence of protocols. This phenomenon, combined with new trends in personalised medical therapies, is expected to change clinical practice dramatically. The emerging field of Rehabilomics is only possible if methodologies are based on biomedical data collection and analysis. In this framework, the objective of this work is to develop a systematic review of machine learning algorithms as solutions to predict motor functional recovery of post-stroke patients after treatment. Methods We conducted a comprehensive search of five electronic databases using the Patient, Intervention, Comparison and Outcome (PICO) format. We extracted health conditions, population characteristics, outcome assessed, the method for feature extraction and selection, the algorithm used, and the validation approach. The methodological quality of included studies was assessed using the prediction model risk of bias assessment tool (PROBAST). A qualitative description of the characteristics of the included studies as well as a narrative data synthesis was performed. Results A total of 19 primary studies were included. The predictors most frequently used belonged to the areas of demographic characteristics and stroke assessment through clinical examination. Regarding the methods, linear and logistic regressions were the most frequently used and cross-validation was the preferred validation approach. Conclusions We identified several methodological limitations: small sample sizes, a limited number of external validation approaches, and high heterogeneity among input and output variables. Although these elements prevented a quantitative comparison across models, we defined the most frequently used models given a specific outcome, providing useful indications for the application of more complex machine learning algorithms in rehabilitation medicine.

Copyright of Der Gynäkologe is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Der Gynäkologe is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: Rehabilitation medicine is facing a new development phase thanks to a recent wave of rigorous clinical trials aimed at improving the scientific evidence of protocols. This phenomenon, combined with new trends in personalised medical therapies, is expected to change clinical practice dramatically. The emerging field of Rehabilomics is only possible if methodologies are based on biomedical data collection and analysis. In this framework, the objective of this work is to develop a systematic review of machine learning algorithms as solutions to predict motor functional recovery of post-stroke patients after treatment.Methods: We conducted a comprehensive search of five electronic databases using the Patient, Intervention, Comparison and Outcome (PICO) format. We extracted health conditions, population characteristics, outcome assessed, the method for feature extraction and selection, the algorithm used, and the validation approach. The methodological quality of included studies was assessed using the prediction model risk of bias assessment tool (PROBAST). A qualitative description of the characteristics of the included studies as well as a narrative data synthesis was performed.Results: A total of 19 primary studies were included. The predictors most frequently used belonged to the areas of demographic characteristics and stroke assessment through clinical examination. Regarding the methods, linear and logistic regressions were the most frequently used and cross-validation was the preferred validation approach.Conclusions: We identified several methodological limitations: small sample sizes, a limited number of external validation approaches, and high heterogeneity among input and output variables. Although these elements prevented a quantitative comparison across models, we defined the most frequently used models given a specific outcome, providing useful indications for the application of more complex machine learning algorithms in rehabilitation medicine. [ABSTRACT FROM AUTHOR]

Purpose The Epic Lift Capacity (ELC) test is used to determine a worker's maximum lifting capacity. In the ELC test, maximum lifting capacity is often determined as the maximum weight lifted without exhibiting a visually appraised "high-risk workstyle." However, the criteria for evaluating lifting mechanics have limited justification. This study applies feature detection and biomechanical analysis to motion capture data obtained while participants performed the ELC test to objectively identify aspects of movement that may help define "high-risk workstyle". Method In this cross-sectional study, 24 participants completed the ELC test. We applied Principal Component Analysis, as a feature detection approach, and biomechanical analysis to motion capture data to objectively identify movement features related to biomechanical exposure on the low back and shoulders. Principal component scores were compared between high and low exposure trials (relative to median exposure) to determine if features of movement differed. Features were interpreted using single component reconstructions of principal components. Results Statistical testing showed that low exposure lifts and lowers maintained the body closer to the load, exhibited squat-like movement (greater knee flexion, wider base of support), and remained closer to neutral posture at the low back (less forward flexion and axial twist) and shoulder (less flexion and abduction). Conclusions Use of feature detection and biomechanical analyses revealed movement features related to biomechanical exposure at the low back and shoulders. The objectively identified criteria could augment the existing scoring criteria for ELC test technique assessment. In the future, such features can inform the design of classifiers to objectively identify "high-risk workstyle" in real-time. [ABSTRACT FROM AUTHOR]

ObjectivesClinical discharge summaries provide valuable information about patients' clinical history, which is helpful for the realization of intelligent healthcare applications. The documents tend to take the form of separate segments based on temporal or topical information. If a patient's clinical history can be seen as a consecutive sequence of clinical events, then each temporal segment can be seen as a snapshot, providing a certain clinical context at a specific moment. This study aimed to demonstrate a temporal segmentation method of Korean clinical narratives for identifying textual snapshots of patient history as a proof-of-a-concept.MethodsOur method uses pattern-based segmentation to approximate human recognition of the temporal or topical shifts in clinical documents. We utilized rheumatic patients' discharge summaries and transformed them into sequences of constituent chunks. We built 97 single pattern functions to denote whether a certain chunk has attributes that indicate that it can be a segment boundary. We manually defined the relationships between the pattern functions to resolve multiple pattern matchings and to make a final decision.ResultsThe algorithm segmented 30 discharge summaries and processed 1,849 decision points. Three human judges were asked whether they agreed with the algorithm's prediction, and the agreement percentage on the judges' majority opinion was 89.61%.ConclusionsAlthough this method is based on manually constructed rules, our findings demonstrate that the proposed algorithm can achieve fairly good segmentation results, and it may be the basis for methodological improvement in the future.

Objective: To investigate the feasibility of a deep learning-based detection (DLD) system for multiclass lesions on chest radiograph, in comparison with observers.Methods: A total of 15,809 chest radiographs were collected from two tertiary hospitals (7204 normal and 8605 abnormal with nodule/mass, interstitial opacity, pleural effusion, or pneumothorax). Except for the test set (100 normal and 100 abnormal (nodule/mass, 70; interstitial opacity, 10; pleural effusion, 10; pneumothorax, 10)), radiographs were used to develop a DLD system for detecting multiclass lesions. The diagnostic performance of the developed model and that of nine observers with varying experiences were evaluated and compared using area under the receiver operating characteristic curve (AUROC), on a per-image basis, and jackknife alternative free-response receiver operating characteristic figure of merit (FOM) on a per-lesion basis. The false-positive fraction was also calculated.Results: Compared with the group-averaged observations, the DLD system demonstrated significantly higher performances on image-wise normal/abnormal classification and lesion-wise detection with pattern classification (AUROC, 0.985 vs. 0.958; p = 0.001; FOM, 0.962 vs. 0.886; p < 0.001). In lesion-wise detection, the DLD system outperformed all nine observers. In the subgroup analysis, the DLD system exhibited consistently better performance for both nodule/mass (FOM, 0.913 vs. 0.847; p < 0.001) and the other three abnormal classes (FOM, 0.995 vs. 0.843; p < 0.001). The false-positive fraction of all abnormalities was 0.11 for the DLD system and 0.19 for the observers.Conclusions: The DLD system showed the potential for detection of lesions and pattern classification on chest radiographs, performing normal/abnormal classifications and achieving high diagnostic performance.Key Points: • The DLD system was feasible for detection with pattern classification of multiclass lesions on chest radiograph. • The DLD system had high performance of image-wise classification as normal or abnormal chest radiographs (AUROC, 0.985) and showed especially high specificity (99.0%). • In lesion-wise detection of multiclass lesions, the DLD system outperformed all 9 observers (FOM, 0.962 vs. 0.886; p < 0.001). [ABSTRACT FROM AUTHOR]

This article outlines recent developments in the clinical and automated assessment of neurological gait disorders. With a primary focus on vestibular, cerebellar, and functional gait disorders, we discuss how instrumented gait examination may assist clinical decision making in these disorders with respect to the initial differential diagnosis and prognosis as well as the objective monitoring of disease progression and therapeutic interventions. We delineate strategies for data handling and analysis of quantitative gait examinations that can facilitate the clinical characterization and interpretation of walking impairments. These strategies include data normalization and dimensionality reduction procedures. We further emphasize the value of a comprehensive, standardized gait assessment protocol. Accordingly, the examination of walking conditions that challenge patients with respect to their biomechanical, sensory, or cognitive resources are particularly helpful to disclose and characterize the causes underlying their gait impairment. Finally, we provide a perspective on the emerging implementation of pattern recognition approaches within the framework of clinical management of gait disorders and discuss their potential to assist clinical decision making with respect to the differential diagnosis and the prognosis of fall risk in individual patients. [ABSTRACT FROM AUTHOR]

Classification of the sources of partial discharges has been a standard procedure to assess the status of insulation in high voltage systems. One of the challenges while classifying these sources is the decision on the distinct properties of each one, often requiring the skills of trained human experts. Machine learning offers a solution to this problem by allowing to train models based on extracted features. The performance of such algorithms heavily depends on the choice of features. This can be overcome by using deep learning where feature extraction is done automatically by the algorithm, and the input to such an algorithm is the raw input data. In this work, an enhanced convolutional neural network is proposed that is capable of classifying single sources as well as multiple sources of partial discharges without introducing multiple sources in the training phase. The training is done by using only single-source phase-resolved partial discharge (PRPD) patterns, while testing is performed on both single and multi-source PRPD patterns. The proposed model is compared with single-branch CNN architecture. The average percentage improvements of the proposed architecture for single-source PDs and multi-source PDs are 99.6% and 96.7% respectively, compared to 96.2% and 77.3% for that of the traditional single-branch CNN architecture.

• About one third of positive routine HEp-2 IFA tests show mixed antinuclear patterns. • On these sera correct identification of ANA patterns is challenging. • We established a novel way to analyze the interference between two patterns. • Nuclear homogeneous disturb the recognition of speckled pattern more than vice versa. • Conventional/on-screen evaluation is superior to EUROPattern in pattern analysis. A major challenge of the HEp-2 cell-based indirect immunofluorescence (IIF) assays is the correct identification of the individual anti-nuclear antibodies (ANAs) if more than one is present in a sample. We created artificial mixes by pooling two different samples with a single autoantibody in different titers. Comparison of the expected and observed patterns and titers clarifies the interference between the two tested ANAs. Serum samples with a single homogeneous or speckled ANA pattern were serially diluted and mixed in 16 combinations, providing end-point titers of 1:5,120 to 1:80 for both patterns. These mixes were tested by a HEp-2 IIF assay and were evaluated by conventional evaluation, the EUROPattern (EPa) system and on-screen analysis. Homogeneous pattern can alter the identification of the speckled pattern much more than vice versa, but both has an interfering effect on the other. The effect of the interfering on the tested pattern was higher if the titer of the former one was higher. The pattern recognition efficacy of conventional and the on-screen evaluation was similar and superior compared to the EPa analysis. The application of artificial mixed samples can help the evaluation of the efficacy of manual and computer-aided ANA HEp-2 pattern recognition. [ABSTRACT FROM AUTHOR]

Background: No previous study has comprehensively reviewed the application of machine learning algorithms in mood disorders populations. Herein, we qualitatively and quantitatively evaluate previous studies of machine learning-devised models that predict therapeutic outcomes in mood disorders populations.Methods: We searched Ovid MEDLINE/PubMed from inception to February 8, 2018 for relevant studies that included adults with bipolar or unipolar depression; assessed therapeutic outcomes with a pharmacological, neuromodulatory, or manual-based psychotherapeutic intervention for depression; applied a machine learning algorithm; and reported predictors of therapeutic response. A random-effects meta-analysis of proportions and meta-regression analyses were conducted.Results: We identified 639 records: 75 full-text publications were assessed for eligibility; 26 studies (n=17,499) and 20 studies (n=6325) were included in qualitative and quantitative review, respectively. Classification algorithms were able to predict therapeutic outcomes with an overall accuracy of 0.82 (95% confidence interval [CI] of [0.77, 0.87]). Pooled estimates of classification accuracy were significantly greater (p < 0.01) in models informed by multiple data types (e.g., composite of phenomenological patient features and neuroimaging or peripheral gene expression data; pooled proportion [95% CI] = 0.93[0.86, 0.97]) when compared to models with lower-dimension data types (pooledproportion=0.68[0.62,0.74]to0.85[0.81,0.88]).Limitations: Most studies were retrospective; differences in machine learning algorithms and their implementation (e.g., cross-validation, hyperparameter tuning); cannot infer importance of individual variables fed into learning algorithm.Conclusions: Machine learning algorithms provide a powerful conceptual and analytic framework capable of integrating multiple data types and sources. An integrative approach may more effectively model neurobiological components as functional modules of pathophysiology embedded within the complex, social dynamics that influence the phenomenology of mental disorders. [ABSTRACT FROM AUTHOR]

ObjectivesAlthough acronyms and abbreviations in clinical text are used widely on a daily basis, relatively little research has focused upon word sense disambiguation (WSD) of acronyms and abbreviations in the healthcare domain. Since clinical notes have distinctive characteristics, it is unclear whether techniques effective for acronym and abbreviation WSD from biomedical literature are sufficient.MethodsThe authors discuss feature selection for automated techniques and challenges with WSD of acronyms and abbreviations in the clinical domain.ResultsThere are significant challenges associated with the informal nature of clinical text, such as typographical errors and incomplete sentences; difficulty with insufficient clinical resources, such as clinical sense inventories; and obstacles with privacy and security for conducting research with clinical text. Although we anticipated that using sophisticated techniques, such as biomedical terminologies, semantic types, part-of-speech, and language modeling, would be needed for feature selection with automated machine learning approaches, we found instead that simple techniques, such as bag-of-words, were quite effective in many cases. Factors, such as majority sense prevalence and the degree of separateness between sense meanings, were also important considerations.ConclusionsThe first lesson is that a comprehensive understanding of the unique characteristics of clinical text is important for automatic acronym and abbreviation WSD. The second lesson learned is that investigators may find that using simple approaches is an effective starting point for these tasks. Finally, similar to other WSD tasks, an understanding of baseline majority sense rates and separateness between senses is important. Further studies and practical solutions are needed to better address these issues.

ObjectivesTo provide accurate personalized medical care, it is necessary to gather individual-related data or contextual information regarding the target person. Nowadays a large number of people possess smartphones, which enables sensors in the smartphones to be used for lifelogging. The objective of the study is to analyze human activity pattern by using lifelog agent cooperating with the Health Avatar platform.MethodsUsing the lifelog measured by accelerometer and gyroscope in a smartphone at a 50 Hz rate, the agent reveals how long the user walks, runs, sits, stands, and lies down, and this information is summarized by hours. The summaries are sent to the Health Avatar platform and finally are written in the Continuity of Care Record (CCR) format.ResultsThe lifelog agent is successfully operated with the Health Avatar platform. In addition, we implement an application that displays the user's activity patterns in a graph and calculates the metabolic equivalent of task based calorie burned by hour or by day using the lifelog of the CCR form to show that the lifelog can be used as medical records.ConclusionsThe agent shows how lifelogs are analyzed and summarized to help activity recognition. We believe that our agent demonstrates a way of incorporating lifelogs into medical care and a way of exploiting lifelogs in a medical format.

Rationale: The vast majority of children around the world undergoing adenotonsillectomy for obstructive sleep apnea-hypopnea syndrome (OSA) are not objectively diagnosed by nocturnal polysomnography because of access availability and cost issues. Automated analysis of nocturnal oximetry (nSpO2), which is readily and globally available, could potentially provide a reliable and convenient diagnostic approach for pediatric OSA.Methods: Deidentified nSpO2 recordings from a total of 4,191 children originating from 13 pediatric sleep laboratories around the world were prospectively evaluated after developing and validating an automated neural network algorithm using an initial set of single-channel nSpO2 recordings from 589 patients referred for suspected OSA.Measurements and Main Results: The automatically estimated apnea-hypopnea index (AHI) showed high agreement with AHI from conventional polysomnography (intraclass correlation coefficient, 0.785) when tested in 3,602 additional subjects. Further assessment on the widely used AHI cutoff points of 1, 5, and 10 events/h revealed an incremental diagnostic ability (75.2, 81.7, and 90.2% accuracy; 0.788, 0.854, and 0.913 area under the receiver operating characteristic curve, respectively).Conclusions: Neural network-based automated analyses of nSpO2 recordings provide accurate identification of OSA severity among habitually snoring children with a high pretest probability of OSA. Thus, nocturnal oximetry may enable a simple and effective diagnostic alternative to nocturnal polysomnography, leading to more timely interventions and potentially improved outcomes. [ABSTRACT FROM AUTHOR]

Untreated paediatric obstructive sleep apnoea syndrome (OSAS) can severely affect the development and quality of life of children. In-hospital polysomnography (PSG) is the gold standard for a definitive diagnosis though it is relatively unavailable and particularly intrusive. Nocturnal portable oximetry has emerged as a reliable technique for OSAS screening. Nevertheless, additional evidences are demanded. Our study is aimed at assessing the usefulness of multiscale entropy (MSE) to characterise oximetric recordings. We hypothesise that MSE could provide relevant information of blood oxygen saturation (SpO2) dynamics in the detection of childhood OSAS. In order to achieve this goal, a dataset composed of unattended SpO2 recordings from 50 children showing clinical suspicion of OSAS was analysed. SpO2 was parameterised by means of MSE and conventional oximetric indices. An optimum feature subset composed of five MSE-derived features and four conventional clinical indices were obtained using automated bidirectional stepwise feature selection. Logistic regression (LR) was used for classification. Our optimum LR model reached 83.5% accuracy (84.5% sensitivity and 83.0% specificity). Our results suggest that MSE provides relevant information from oximetry that is complementary to conventional approaches. Therefore, MSE may be useful to improve the diagnostic ability of unattended oximetry as a simplified screening test for childhood OSAS. [ABSTRACT FROM AUTHOR]

ObjectivesAcquiring temporal information is important because knowledge in clinical narratives is time-sensitive. In this paper, we describe an approach that can be used to extract the temporal information found in Korean clinical narrative texts.MethodsWe developed a two-stage system, which employs an exhaustive text analysis phase and a temporal expression recognition phase. Since our target document may include tokens that are made up of both Korean and English text joined together, the minimal semantic units are analyzed and then separated from the concatenated phrases and linguistic derivations within a token using a corpus-based approach to decompose complex tokens. A finite state machine is then used on the minimal semantic units in order to find phrases that possess time-related information.ResultsIn the experiment, the temporal expressions within Korean clinical narratives were extracted using our system. The system performance was evaluated through the use of 100 discharge summaries from Seoul National University Hospital containing a total of 805 temporal expressions. Our system scored a phrase-level precision and recall of 0.895 and 0.919, respectively.ConclusionsFinding information in Korean clinical narrative is challenging task, since the text is written in both Korean and English and frequently omits syntactic elements and word spacing, which makes it extremely noisy. This study presents an effective method that can be used to aquire the temporal information found in Korean clinical documents.

Background: Medication adherence is a global public health challenge, as only approximately 50% of people adhere to their medication regimens. Medication reminders have shown promising results in terms of promoting medication adherence. However, practical mechanisms to determine whether a medication has been taken or not, once people are reminded, remain elusive. Emerging smartwatch technology may more objectively, unobtrusively, and automatically detect medication taking than currently available methods., Objective: This study aimed to examine the feasibility of detecting natural medication-taking gestures using smartwatches., Methods: A convenience sample (N=28) was recruited using the snowball sampling method. During data collection, each participant recorded at least 5 protocol-guided (scripted) medication-taking events and at least 10 natural instances of medication-taking events per day for 5 days. Using a smartwatch, the accelerometer data were recorded for each session at a sampling rate of 25 Hz. The raw recordings were scrutinized by a team member to validate the accuracy of the self-reports. The validated data were used to train an artificial neural network (ANN) to detect a medication-taking event. The training and testing data included previously recorded accelerometer data from smoking, eating, and jogging activities in addition to the medication-taking data recorded in this study. The accuracy of the model to identify medication taking was evaluated by comparing the ANN's output with the actual output., Results: Most (n=20, 71%) of the 28 study participants were college students and aged 20 to 56 years. Most individuals were Asian (n=12, 43%) or White (n=12, 43%), single (n=24, 86%), and right-hand dominant (n=23, 82%). In total, 2800 medication-taking gestures (n=1400, 50% natural plus n=1400, 50% scripted gestures) were used to train the network. During the testing session, 560 natural medication-taking events that were not previously presented to the ANN were used to assess the network. The accuracy, precision, and recall were calculated to confirm the performance of the network. The trained ANN exhibited an average true-positive and true-negative performance of 96.5% and 94.5%, respectively. The network exhibited <5% error in the incorrect classification of medication-taking gestures., Conclusions: Smartwatch technology may provide an accurate, nonintrusive means of monitoring complex human behaviors such as natural medication-taking gestures. Future research is warranted to evaluate the efficacy of using modern sensing devices and machine learning algorithms to monitor medication-taking behavior and improve medication adherence., (©Chrisogonas Odero Odhiambo, Lukacs Ablonczy, Pamela J Wright, Cynthia F Corbett, Sydney Reichardt, Homayoun Valafar. Originally published in JMIR Human Factors (https://humanfactors.jmir.org), 04.05.2023.)

Purpose To compare the performance of computer-automated diagnosis using functional magnetic resonance imaging (fMRI) interictal graph theory (CADFIG) to that achieved in standard clinical practice with MRI, for lateralizing the affected hemisphere in temporal lobe epilepsy (TLE). Materials and Methods Interictal resting state fMRI and high-resolution MRI were performed on 14 left and 10 right TLE patients. Functional topology measures were calculated from fMRI using graph theory, and used to lateralize the epileptogenic hemisphere using quadratic discriminant analysis. Leave-one-out cross-validation prediction accuracy of CADFIG was compared to performance based on expert manual analysis (MA) of MRI, using video EEG as the "gold standard" for focus lateralization. Results CADFIG correctly lateralized 95.8% (23/24) of cases, compared to 66.7% (16/24) with expert MA of MRI. Combining MA with CADFIG allowed all cases (24/24) to be correctly lateralized. CADFIG correctly identified the affected hemisphere for all patients (8/8) where MRI failed to lateralize. Conclusion CADFIG based on fMRI lateralized the affected hemisphere in TLE with superior performance compared to expert MA of MRI. These results demonstrate that functional patterns in fMRI can be used with automated machine learning for diagnostic lateralization in TLE. Addition of fMRI-based tests to existing protocols for identifying the affected hemisphere in presurgical assessment can improve diagnostic accuracy and surgical outcome in TLE. J. Magn. Reson. Imaging 2015;41:1689-1694. © 2014 Wiley Periodicals, Inc. [ABSTRACT FROM AUTHOR]

Shoeprints are an important source of information for criminal investigation. Therefore, an increasing number of automatic shoeprint recognition methods have been proposed for detecting the corresponding shoe models. However, comprehensive comparisons among the methods have not previously been made. In this study, an extensive set of methods proposed in the literature was implemented, and their performance was studied in varying conditions. Three datasets of different quality shoeprints were used, and the methods were evaluated also with partial and rotated prints. The results show clear differences between the algorithms: while the best performing method, based on local image descriptors and RANSAC, provides rather good results with most of the experiments, some methods are almost completely unrobust against any unidealities in the images. Finally, the results demonstrate that there is still a need for extensive research to improve the accuracy of automatic recognition of crime scene prints. [ABSTRACT FROM AUTHOR]

Neurodegenerative diseases comprise a wide variety of mental symptoms whose evolution is not directly related to the visual analysis made by radiologists, who can hardly quantify systematic differences. Moreover, automatic brain morphometric analyses, that do perform this quantification, contribute very little to the comprehension of the disease, i.e., many of these methods classify but they do not produce useful anatomo-functional correlations. This paper presents a new fully automatic image analysis method that reveals discriminative brain patterns associated to the presence of neurodegenerative diseases, mining systematic differences and therefore grading objectively any neurological disorder. This is accomplished by a fusion strategy that mixes together bottom-up and top-down information flows. Bottom-up information comes from a multiscale analysis of different image features, while the top-down stage includes learning and fusion strategies formulated as a max-margin multiple-kernel optimization problem. The capacity of finding discriminative anatomic patterns was evaluated using the Alzheimer's disease (AD) as the use case. The classification performance was assessed under different configurations of the proposed approach in two public brain magnetic resonance datasets (OASIS-MIRIAD) with patients diagnosed with AD, showing an improvement varying from 6.2% to 13% in the equal error rate measure, with respect to what has been reported by the feature-based morphometry strategy. In terms of the anatomical analysis, discriminant regions found by the proposed approach highly correlates to what has been reported in clinical studies of AD. [ABSTRACT FROM PUBLISHER]

The aim of this study was to compare the energy expenditure (EE) estimations of activity-specific prediction equations (ASPE) and of an artificial neural network (ANNEE) based on accelerometry with measured EE. Forty-three children (age: 9.8 ± 2.4 yr) performed eight different activities. They were equipped with one tri-axial accelerometer that collected data in 1-s epochs and a portable gas analyzer. The ASPE and the ANNEE were trained to estimate the EE by including accelerometry, age, gender, and weight of the participants. To provide the activity-specific information, a decision tree was trained to recognize the type of activity through accelerometer data. The ASPE were applied to the activity-type-specific data recognized by the tree (Tree-ASPE). The Tree-ASPE precisely estimated the EE of all activities except cycling [bias: -1.13 ± 1.33 metabolic equivalent (MET)] and walking (bias: 0.29 ± 0.64 MET; P < 0.05). The ANNEE overestimated the EE of stationary activities (bias: 0.31 ± 0.47 MET) and walking (bias: 0.61 ± 0.72 MET) and underestimated the EE of cycling (bias: -0.90 ± 1.18 MET; P < 0.05). Biases of EE in stationary activities (ANNEE: 0.31 ± 0.47 MET, Tree-ASPE: 0.08 ± 0.21 MET) and walking (ANNEE 0.61 ± 0.72 MET, Tree-ASPE: 0.29 ± 0.64 MET) were significantly smaller in the Tree-ASPE than in the ANNEE (P < 0.05). The Tree-ASPE was more precise in estimating the EE than the ANNEE. The use of activity-type-specific information for subsequent EE prediction equations might be a promising approach for future studies. [ABSTRACT FROM AUTHOR]

The article presents a study that predicts early signs of illness in older adults by using the data generated by continuous, unobtrusive nursing home monitoring system. It describes he possibility of employing a multiple instance learning (MIL) framework for early illness detection. It is given that the use of simulated sensor data is very useful for algorithm development and testing.

The emergence of nanoscale devices has provided robust interfaces to biomolecules that faithfully transduce and define fundamental interactions of living systems. Measuring single-event behavior of important targets like DNA, and diseased cells has been achieved with a number of devices and systems. An important dimension to these systems, often discounted, is real-time computational decision-making from measured data. This paper describes an adaptive approach that can record single-molecule or single-cell events in real-time and automatically analyze patterns from the measured data. The automated analysis of measured data is done using a static threshold technique and two variations of a dynamic threshold technique: baseline-tracker and moving average filtering. Dynamic techniques for threshold detection enable noise suppression in the measured data and precise detection of patterns, but at the cost of more complex software as compared to static technique. To mitigate the computational overhead, a real-time system is implemented that uses advanced I/O techniques to minimize the execution stalls, thus enabling the system to process data significantly faster than the electrical measurement setup. Furthermore, the algorithms are implemented on programmable graphics processing units for parallel pattern detection. Our implementation provides five times faster data acquisition and pattern detection than the maximum sampling rate of the electrical measurement setup. [ABSTRACT FROM AUTHOR]

The article presents as study aimed at developing an automatic detection system in detecting the activities of anesthetist in the operating room . The study uses a radio frequency identification device (RFID) technology to capture the location, orientation and stance (LOC) of the anesthetist, The study suggests that active RFID tags can provide useful information on LOS at a low cost and minimal impact on the work environment.

Task analysis is a valuable research method for better understanding the activity of anaesthetists in the operating room (OR), providing evidence for designing and evaluating improvements to systems and processes. It may also assist in identifying potential error paths to adverse events, ultimately improving patient safety. Human observers are the current ‘gold standard’ for capturing task data, but they are expensive and have cognitive limitations. Our current research – Towards Automated Detection of Anaesthetic Activity (TADAA) - aims to produce an automated task analysis system, employing Radio Frequency Identification (RFID) technology to capture anaesthetists' location, orientation and stance (LOS), and machine learning techniques to translate that data into low-level and high-level activity labels. In this paper we present details of the system design and promising results from LOS sensing testing in laboratory and highfidelity OR simulator settings. [ABSTRACT FROM AUTHOR]

Abstract: Evidence supports the robustness and stability of individual differences in non-rapid eye movement (NREM) sleep electroencephalogram (EEG) spectra with a special emphasis on the 9–16Hz range corresponding to sleep spindle activity. These differences cast doubt on the universal validity of sleep spindle analysis methods based on strict amplitude and frequency criteria or a set of templates of natural spindles. We aim to improve sleep spindle analysis by the individual adjustments of frequency and amplitude criteria, the use of a minimum set of a priori knowledge, and by clear dissections of slow- and fast sleep spindles as well as to transcend the concept of visual inspection as being the ultimate test of the method''s validity. We defined spindles as those segments of the NREM sleep EEG which contribute to the two peak regions within the 9–16Hz EEG spectra. These segments behaved as slow- and fast sleep spindles in terms of topography and sleep cycle effects, while age correlated negatively with the occurrence of fast type events only. Automatic detections covered 92.9% of visual spindle detections (A&VD). More than half of the automatic detections (58.41%) were exclusively automatic detections (EADs). The spectra of EAD correlated significantly and positively with the spectra of A&VD as well as with the average (AVG) spectra. However, both EAD and A&VD had higher individual-specific spindle spectra than AVG had. Results suggest that the individual adjustment method (IAM) detects EEG segments possessing the individual-specific spindle spectra with higher sensitivity than visual scoring does. [Copyright &y& Elsevier]

We investigate the use of relevance feedback (RFb) and the inclusion of expert knowledge to reduce the semantic gap in content-based image retrieval (CBIR) of mammograms. Tests were conducted with radiologists, in which their judgment of the relevance of the retrieved images was used with techniques of query-point movement to incorporate RFb. The measures of similarity of images used for CBIR were based upon textural characteristics and the distribution of density of fibroglandular tissue in the breast. The features used include statistics of the gray-level histogram, texture features based upon the gray-level co-occurrence matrix, moment-based features, measures computed in the Radon domain, and granulometric measures. Queries for CBIR with RFb were executed by three radiologists. The performance of CBIR was measured in terms of precision of retrieval and a measure of relevance-weighted precision (RWP) of retrieval. The results indicate improvement due to RFb of up to 62% in precision and 39% in RWP. The gain in performance of CBIR with RFb depended upon the BI-RADS breast density index of the query mammographic image, with greater improvement in cases of mammograms with higher density. [ABSTRACT FROM AUTHOR]

Abstract: Digital image analysis of faces has been demonstrated to be effective in a small number of syndromes. In this paper we investigate several aspects that help bringing these methods closer to clinical application. First, we investigate the impact of increasing the number of syndromes from 10 to 14 as compared to an earlier study. Second, we include a side-view pose into the analysis and third, we scrutinize the effect of geometry information. Picture analysis uses a Gabor wavelet transform, standardization of landmark coordinates and subsequent statistical analysis. We can demonstrate that classification accuracy drops from 76% for 10 syndromes to 70% for 14 syndromes for frontal images. Including side-views achieves an accuracy of 76% again. Geometry performs excellently with 85% for combined poses. Combination of wavelets and geometry for both poses increases accuracy to 93%. In conclusion, a larger number of syndromes can be handled effectively by means of image analysis. [Copyright &y& Elsevier]

Classification of the sources of partial discharges has been a standard procedure to assess the status of insulation in high voltage systems. One of the challenges while classifying these sources is the decision on the distinct properties of each one, often requiring the skills of trained human experts. Machine learning offers a solution to this problem by allowing to train models based on extracted features. The performance of such algorithms heavily depends on the choice of features. This can be overcome by using deep learning where feature extraction is done automatically by the algorithm, and the input to such an algorithm is the raw input data. In this work, an enhanced convolutional neural network is proposed that is capable of classifying single sources as well as multiple sources of partial discharges without introducing multiple sources in the training phase. The training is done by using only single-source phase-resolved partial discharge (PRPD) patterns, while testing is performed on both single and multi-source PRPD patterns. The proposed model is compared with single-branch CNN architecture. The average percentage improvements of the proposed architecture for single-source PDs and multi-source PDs are 99.6% and 96.7% respectively, compared to 96.2% and 77.3% for that of the traditional single-branch CNN architecture. [ABSTRACT FROM AUTHOR]