Abstract: A neural network and its information processing method, information processing system. The neural network includes N layers of neuron layers connected to each other one by one, except for a first layer of neuron layer, each of the neurons of the other neuron layers includes m dendritic units and one hippocampal unit; the dendritic unit includes a resistance value graded device, the hippocampal unit includes a resistance value mutation device, and the m dendritic units can be provided with different threshold voltage or current, respectively; and the neurons on the nth layer neuron layer are connected to the m dendritic units of the neurons on the n+1th layer neuron layer; wherein N is an integer larger than 3, m is an integer larger than 1, n is an integer larger than 1 and less than N.

Abstract: An electronic device is provided. The electronic device includes a memory storing recording data including a content of a conversation and at least one instruction, and a processor configured, by executing the at least one instruction, to input first data corresponding to a first voice in the content of the conversation into a first neural network model and acquire category information of the first data, and acquire category information of second data corresponding to a second voice in the content of the conversation. The processor is configured to, based on the category information of the first data and the category information of the second data being different, train the first neural network model based on the category information of the second data and the first data.

Abstract: In some instances, a person may need monitoring. The monitoring may be based on age, or on other factors such as abilities and functionality. The monitoring may enable a supervising person to remotely receive updates regarding the subject person. The supervising person may enter in various biometric parameters to monitor. The supervising person may alternatively and/or additionally set other factors to monitor such as time of day, location, activity level, and the like. The monitoring may provide peace of mind to a supervising person to ensure the subject person is safe. In some embodiments, the supervising person may set various alarm thresholds. The alarm thresholds may trigger an alert to the supervising person. In alternative embodiments, if the subject person is a grown person without a supervising person in the same vicinity, a security and/or automation system may act as the supervising adult.

Abstract: A neural waveform distinguishment apparatus includes: a neural waveform obtainment unit that obtains multiple neural waveforms in a pre-designated manner from neural signals sensed by way of at least one electrode; a preprocessing unit that obtains multiple gradient waveforms by calculating pointwise slopes in each of the neural waveforms; a feature extraction unit comprising an encoder ensemble composed of multiple encoders, which have a pattern estimation method learned beforehand and include different numbers of hidden layers, where the feature extraction unit obtains multiple codes as multiple features extracted by the encoders respectively from the gradient waveforms and concatenates the codes extracted by the encoders respectively to extract a feature ensemble for each of the gradient waveforms; and a clustering unit that distinguishes the neural waveforms corresponding respectively to the gradient waveforms by clustering the feature ensembles extracted respectively in correspondence to the gradient wav

Abstract: Training a neural network for signal analysis in NMR spectra may use a plurality of computed NMR raw spectra, each raw spectrum being associated with a different NMR active molecule having a known number of protons (#P). Peaks of the raw spectra may be broadened to generate a broadened spectrum for each raw spectrum. For each broadened spectrum, its integral function may be computed to count the number of protons associated with peaks of the respective broadened spectrum. Signal intervals may be identified as intervals in the broadened spectrum where the integral function increases approximately by multiples of the value associated with a single proton so that the total number of counted protons matches the known number of protons (#P) of the associated molecule. The obtained spectra with associated labels for the identified signal intervals are provided as the training data set to the neural network.

Abstract: Devices, systems, and techniques are disclosed for managing electrical stimulation therapy and/or sensing of physiological signals such as brain signals. For example, a system may assist a clinician in identifying one or more electrode combinations for sensing a brain signal. In another example, a user interface may display brain signal information and values of a stimulation parameter at least partially defining electrical stimulation delivered to a patient when the brain signal information was sensed.

Abstract: The present subject matter provides systems and methods for distributed training of artificial intelligence (AI) systems for medical image analysis. The systems allow for offline prediction of abnormalities of medical images on a local AI system associated with an imaging device (102). In one example, the local AI system (100) extracts image parameters from the analyzed medical images and sends it to a global AI system (120) for training a global AI model. In another example, the local AI system (100) retrains a previously trained local AI model based on the image parameters to obtain a local AI model. Model parameters are extracted from the local AI model and are sent to the global AI system to retrain a global AI model. The retrained global AI model is deployed back to the local AI system (100) for updating the local AI model.

Abstract: Hitherto, preprocessing for separating impurities and calculation processing, for example, a peak splitting method, are required in order to acquire information on test substances from spectral information. An information processing apparatus according to the present invention includes information acquisition means for acquiring quantitative information on a test substance estimated by inputting spectral information on a sample containing the test substance and impurities into a learning model.

Abstract: Systems and methods for virtual implant placement to implement joint gap planning are discussed. For example, a method can include operations for receiving a first implant parameter set based on a surgical plan that was generated while moving the joint through a range of motion. The method can include generating a first set of candidate implant parameter sets that are the result of an incremental change, relative to the first implant parameter set, to at least one parameter of the first parameter set. The method can include calculating a result for at least one candidate implant parameter set and providing a graphical representation of the result according to at least one candidate implant parameter set. The result can be color-coded to correlate to a candidate implant parameter set. The display can include color-coded user interface controls to allow a user to execute incremental changes corresponding to candidate implant parameter sets.

Abstract: By analyzing an image of a cell sample, whether a cell shown in the image is cancerous or not, the type of cancer, etc. are objectively and appropriately determined.

Abstract: A medical information processing apparatus according to an embodiment includes a processing circuitry. The processing circuitry sets, as a finding, an item related to diagnosis of a subject; disposes, in an identical screen in accordance with the finding, each display region for displaying a piece of medical data related to diagnosis of the subject; and displays the medical data extracted from a first facility in the display region for displaying the medical data and displays the lacked medical data extracted from a second facility, together with information that identifies the second facility from which the extraction is made, in the display region for displaying the lacked medical data.

Abstract: A method of evaluating lung cancer risk by generating a set of features comprising a plurality of current blood test results from a blood collected from a target individual, providing at least one classifier generated according to an analysis of a plurality of respective historical blood test results of each of another of a plurality of sampled individuals, and evaluating, using a processor, a lung cancer risk of said target individual by classifying said set of features using said at least one classifier. Each of said plurality of historical and current blood test results comprises results of one or more selected blood tests such as white blood cells blood test results, biochemistry test results, platelets blood test results including at least one of platelets count and mean platelet volume (MPV) and/or a combination of smoking history and red cell test results.

Abstract: A disease diagnosis system includes a processor and a storage device storing a neural network. The processor trains the neural network in the storage device to output a determination value corresponding to a probability having at least one of a plurality of states using a given loss function and learning data labeled so that a given unitary unit included in a biometric image is to have at least one of the plurality of states. The neural network includes a specific layer to output a plurality of feature values corresponding to a probability that the unitary unit is to be determined as each of the plurality of states. The loss function incorporates both first and second feature values corresponding to first and second states into a dual labeling unitary unit with the first state having a higher probability and a second state having lower probability.

Abstract: A system, having a memory that stores computer executable components, and a processor that executes the computer executable components, reduces data size in connection with training a neural network by exploiting spatial locality to weight matrices and effecting frequency transformation and compression. A receiving component receives neural network data in the form of a compressed frequency-domain weight matrix. A segmentation component segments the initial weight matrix into original sub-components, wherein respective original sub-components have spatial weights. A sampling component applies a generalized weight distribution to the respective original sub-components to generate respective normalized sub-components. A transform component applies a transform to the respective normalized sub-components.

Abstract: Improved systems and methods for laboratory instrument calibration. A laboratory instrument retrieves a number of sets of past quality control parameters from a data structure. Each set includes a recovered value and a timestamp. The recovered value is equal to an output value adjusted by an initial calibration factor. The laboratory instrument determines that the number of sets is greater than a threshold and that each of the past quality control parameters has a timestamp that is within a time threshold. The laboratory instrument computes an updated calibration factor such that when the updated calibration factor is applied to a representative value of the recovered values, the representative value equals the expected recovered value. The instrument updates the data structure with the calibration factor such that the calibration factor is used in subsequent testing of patient specimens.

Abstract: The invention relates to a method of, and apparatus for, examining a sample using a charged particle beam apparatus. The method as defined herein comprises the step of detecting, using a first detector, emissions of a first type from the sample in response to the charged particle beam illuminating the sample. The method further comprises the step of acquiring spectral information on emissions of a second type from the sample in response to the charged particle beam illuminating the sample. As defined herein, said step of acquiring spectral information comprises the steps of providing a spectral information prediction algorithm and using said algorithm for predicting said spectral information based on detected emissions of the first type as an input parameter of said algorithm. With this it is possible to gather EDS data using only a BSE detector.

Abstract: In one embodiment, a temperature sensor system includes a sensor assembly with a temperature sensing portion configured to generate a first signal based upon a temperature of body proximate a surface portion of the temperature sensing portion, and a thermoelectric generator portion configured to receive heat flow from the body through the temperature sensing portion and to generate a second signal based upon the heat flow. A control unit is operably connected to the sensor assembly and a memory and configured to execute program instructions stored in the memory to calculate and output a corrected temperature based upon the first signal, the second signal, and at least one correction factor stored in the memory. The at least one correcting factor is determined based upon at least one of a thermal conductivity of the sensor assembly, a size of the sensor assembly, and an aspect ratio of the sensor assembly.

Abstract: A method and apparatus include receiving, by a device, medical information associated with a user. Inquiry information is determined based on the medical information associated with the user and a reinforcement learning model. The inquiry information is provided to permit response information to be received. The response information is received based on providing the inquiry information. Diagnosis information is determined based on the medical information and the response information using a machine learning model. The diagnosis information is provided to a set of devices via a network.

Abstract: The present embodiments relate generally to a system and method for generating images from ultrasound imaging data. The system can include a data acquisition processor, and administrator processor, a user device, and a server. The method can include transmitting images to a server, applying an implicit misfit function to generate a first set of images, then, based on this first set, apply an explicit misfit function to generate a second set of images of higher accuracy.

Abstract: There is provided a recognition system adaptable to a portable device or a wearable device. The recognition system senses a body heat using a thermal sensor, and performs functions such as the living body recognition, image denoising and body temperature prompting according to detected results.

Abstract: A method and system are disclosed for performing supervised outcome-driven persona-typing, including receiving a first data set having patient specific data, treatment data, and outcome data for each of a plurality of first patients. Once received, the plurality of first patients are grouped based on the first data set, and a persona for each of patient groups is generated. A second data set may then be received for a second patient including second patient specific data. A comparison is then carried out on the second data set to identify an existing persona, and then associate the second patient with the identified persona. Based on each of the above steps, a patient care plan is then created.

Abstract: Systems and methods for determining an arrhythmia type are provided. A method may include: obtaining an electrocardiogram signal, obtaining a feature vector of the electrocardiogram signal, obtaining a trained prediction model, and determining an arrhythmia type of the electrocardiogram signal based on the trained prediction model and the feature vector. The feature vector includes a threshold crossing sample (TCSC) percent feature, an L-Z complexity feature, an empirical mode decomposition (EMD) complex number feature, a sample entropy feature, and a set of wavelet transform energy features.

Abstract: Medical device systems and methods for operating medical device systems conserve energy by efficiently managing computational demands of the systems. A first analysis, having relatively lower computational processing demand than at least a second analysis, processes signals from a subject to determine a first estimate of a propensity for the subject to have a neurological event. If the first estimate meets a set of specified criteria, a second analysis is performed to determine a second estimate of the propensity for the subject to have a neurological event.

Abstract: A system for establishing a model for cardiac ventricular hypertrophy (VH) screening includes a storage and a processor. The storage stores multiple pieces of subject data respectively associated with multiple subjects. Each of the pieces of subject data contains a basic physiological parameter group, an electrocardiographic parameter group, and an actual VH condition that corresponds to a left or right ventricle of the subject associated with the piece of subject data. The processor is electrically connected to the storage, splits the pieces of subject data into a training set and a test set, and establishes the model for VH screening based on the pieces of subject data in the training set by using machine learning techniques.

Abstract: A method for training a baseline risk model, including: pre-processing input data by normalizing continuous variable inputs and producing one-hot input features for categorical variables; providing definitions for clean input data and dirty input data based upon various input data related to a patient condition; segmenting the input data into clean input data and dirty input data, wherein the clean input data includes a first subset and a second subset, where the first subset and the second subset include all of the clean input data and are disjoint; training a machine learning model using the first subset of the clean data; and evaluating the performance of the trained machine learning model using the second subset of the clean input data and the dirty input data.

Abstract: Monitoring the quality of sleep of an individual is essential for ensuring one's overall well-being. The existing methods for non-apnea sleep arousal detection are manual. A system and method for the non-apnea sleep arousal detection has been provided. The method uses a feature engineering based binary classification approach for distinguishing non-apnea arousal and non-arousal. A training data set is prepared using a plurality of physiological signals. A plurality of features are derived from the training data set. Out of those only a set of features are selected for training a plurality of random forest classifier models. A test sample is then provided to the plurality of random forest classifier models in the instances of fixed duration. This results in generation of prediction probabilities for each instances. The prediction probabilities are then used to predict the probabilities of non-apnea sleep arousal in the test sample.

Abstract: Methods, systems, and computer program products are included to provide a universal database driver, into which one or more driver implementations may be loaded. The universal database driver communicates with one or more databases using the appropriate driver implementation for each database. A driver manager is provided that requests driver implementations corresponding to the databases, and loads the driver implementations into the universal database driver.

Abstract: A method for assessing whether a patient is at risk of developing a clinical condition includes receiving training data representing a set of patient-related variables for each of a plurality of patients; generating model data based on the received training data; receiving target data representing the set of patient-related variables for a target patient; determining a risk level for the target patient of developing the clinical condition; and indicating the risk level of the target patient, where the set of patient-related variables consists of a first set of variables when the clinical condition is a mortality condition and a second set of variables when the clinical condition is a morbidity condition.

Abstract: A method and system to evaluate image-guided dental implant treatment plans with error simulation. Error sources contributing to the inaccuracy of implant cases come from impressions, stone models, radiographic guides, CT scan and its image processing, surgical guides, as well as the surgical procedures. They are translated into the deviations between the planned and actual implant positions and orientations. The error simulation is to continuously modify and update treatment plans with the possible deviations so that the treatment plans can be visually evaluated along with other evaluation tools.

Abstract: The present invention is a system and method of remote patient monitoring to allow a patient to initiate and activate sensing systems. In the system and method, standard parameters can be sensed, and the information can then be processed and sent to the physician or clinician. The clinician then has the ability to remotely configure or reconfigure the parameters of the sensing system so as to probe for more targeted information based on the initial sensed data.

Abstract: Various embodiments may provide methods and systems capable of evaluating physiological parameter data. The methods and systems may include a receiver capable of collecting a signal representative of a physiological status of a patient, a plurality of data analysis components, wherein each of the plurality of data analysis components is capable of generating a metric based on the signal, and an arbitrator communicatively coupled to each of the plurality of data analysis components and capable of generating a single metric from the metrics generated by the plurality of data analysis components.

Abstract: A system and related method for identifying a trigger event to a patient health-related exacerbation. The system includes at least one sensor configured to collect data related to the patient health-related exacerbation, an analyzer configured to validate the collected data, a patient interface device configured to receive patient inputs to at least one question, and an identifier device configured to receive the patient inputs and collected data and identify the trigger event. The system may also include an expert system configured to receive the patient inputs and the validated collected data and identify a primary patient disease, and a reporting device configured to generate reports related to the identified primary patient disease, patient inputs, and sensed patient conditions.

Abstract: This document discusses, among other things, a system capable of resolving interactions between programmable parameters for operation of a medical device. Programming these devices is a difficult task when many parameters are involved. The disclosed systems and methods attempt to reduce and minimize constraint violations between interdependent parameters using an initial set of parameter values supplied by user (typically a physician) input or calculated automatically, and constraint violations describing invalid parameter values. If possible, a set of parameter values with less egregious constraint violations is generated and may be displayed to the user. A user is prompted to accept the set of parameter values and program the medical device.

Abstract: In an embodiment, an automated peritoneal dialysis (“APD”) machine includes at least one pump, a logic implementer storing a plurality of therapy prescriptions by which to operate the at least one pump, each therapy prescription pre-approved for a particular patient, and an input device operating with the logic implementer to allow the patient to select one of the therapy prescriptions for a particular therapy. In another embodiment, the input device operating with the logic implementer allows a doctor/clinician to select or approve one of the therapy prescriptions to be run on the APD machine. In a further embodiment, the logic implementer is programmed to select or suggest one of the therapy prescriptions to be run on the APD machine.

Abstract: An evaluation method of a progressive-addition lens is provided. First, powers of the progressive-addition lens at a plurality of measurement points are measured to obtain an actually measured power distribution. Next, a comparison power distribution created based on the actually measured power distribution and a defective power distribution prepared in advance are compared with each other to perform similarity search between the both. Thereafter, whether or not the comparison power distribution and the defective power distribution are similar to each other is determined based on the result of the similarity search step, and if it is determined that the comparison power distribution and the defective power distribution are similar to each other, then the progressive-addition lens is evaluated as defective.

Abstract: Image processing method that includes the steps of considering each image point as a node of an artificial neural network, and of processing the image as function of values of the nodes and of connections of each image point undergoing processing with neighboring image points, the image points of the processed image being obtained by iterative evolution steps of parameters defining the appearance as evolution steps of the value of nodes or by iterative evolution steps of values of the set of connections or by a combination of the evolutions, wherein the processing occurs by evolution iterative steps that are functions of connections of neighboring image points with the image point under examination, each of the neighboring image points being further considered as neighboring one or more or all adjacent image points, the functions providing immediate feedback contributions for determining appearance values of all other image points.

Abstract: This document discusses, among other things, a system capable of resolving interactions between programmable parameters for operation of a medical device. Programming these devices is a difficult task when many parameters are involved. The disclosed systems and methods attempt to reduce and minimize constraint violations between interdependent parameters using an initial set of parameter values supplied by user (typically a physician) input or calculated automatically, and constraint violations describing invalid parameter values. If possible, a set of parameter values with less egregious constraint violations is generated and may be displayed to the user. A user is prompted to accept the set of parameter values and program the medical device.

Abstract: This method uses two sets of sensors to estimate certain characteristics of the movement of a device or a person or states, especially postures, they adopt. A first, abundant, set of sensors (1) is removed after a learning phase where it records with certainty the states obtained by interpreting first decisional rules. The measurements of a second set of sensors (2), much more restricted than the first, are correlated to the states reached during the learning period by second decisional rules automatically obtained by supplying a classifier. They are then interpreted to determine the new states reached by the wearer just by means of the second sensors. The results are good in spite of the low number of second sensors, thanks to the accuracy of the second decisional rules.

Abstract: A method of reviewing medical images and clinical data to generate a diagnosis or treatment decision is provided. The method includes receiving, at a computer-aided detection (CAD) system, the medical images and clinical data, processing the medical images and clinical data; to generate initial finding candidates and clustering the initial finding candidates into a plurality of groups. The method further includes classifying the initial finding candidates using machine learning algorithms integrated into the CAD system into one or more categories one or more categories of the initial finding candidates using type 2 fuzz logic, and determining detection and assessment statistics based on at least the assessed categories and classified findings using Bayesian probability analysis.

Abstract: In an embodiment, an automated peritoneal dialysis (“APD”) machine includes at least one pump, a logic implementer storing a plurality of therapy prescriptions by which to operate the at least one pump, each therapy prescription pre-approved for a particular patient, and an input device operating with the logic implementer to allow the patient to select one of the therapy prescriptions for a particular therapy. In another embodiment, the input device operating with the logic implementer allows a doctor/clinician to select or approve one of the therapy prescriptions to be run on the APD machine. In a further embodiment, the logic implementer is programmed to select or suggest one of the therapy prescriptions to be run on the APD machine.

Abstract: A method of automatically determining which type of treatment is most appropriate for (or the physiological state of) a patient. The method comprises transforming one or more time domain measurements from the patient into frequency domain data representative of the frequency content of the time domain measurements; processing the frequency domain data to form a plurality of spectral bands, the content of a spectral band representing the frequency content of the measurements within a frequency band; forming a weighted sum of the content of the spectral bands, with different weighting coefficients applied to at least some of the spectral bands; determining the type of treatment (or physiological state) based on the weighted sum.

Abstract: A device and method of providing information to a healthcare provider regarding the dosing of insulin is provided where the data is analyzed to produce a qualified set of points. The applied analysis is performed via parameters that are independent of patient input.

Abstract: A peritoneal dialysis system includes a logic implementer configured to: (i) accept at least one therapy target input; (ii) accept at least one patient transport characteristic input; (iii) accept at least one solution input; (iv) accept at least one fluid volume input; (v) accept at least one therapy time input, at least one of the inputs (ii) to (v) including an input range; and (vi) generate each therapy regimen using the inputs of (ii), (iii), (iv) and (v), including each of the possibilities within the at least one input range, that satisfy the at least one therapy target input.

Abstract: This document discusses, among other things, a user interface capable of resolving interactions between programmable parameters for operation of a personal medical device. Programming these devices is a difficult task when many parameters are involved. The medical device interface attempts to reduce and minimize constraint violations between interdependent parameters using an initial set of parameter values supplied by user (typically a physician) input, and constraint violations describing invalid parameter values. A user is given the option to select one or more parameters to remain constant. If possible, a set of parameter values with less egregious constraint violations is displayed to the user. A user is prompted to accept the set of parameter values and program the medical device.

Abstract: A system for analyzing the risks of adverse effect resulting from the use of a drug comprises a selector for identifying at least one drug, a profiler for selecting from multiple profiles related to the safety of the drug, using at least one filter; at least one data mining engine; and an output device for displaying the analytic results from the data mining engine. Preferably, the at least one data mining engine is selected from (1) a proportional analysis engine to assess deviations in a set of reactions to the drug; (2) a comparator to measure the reactions to the drug against a user-defined backdrop, and (3) a correlator to look for correlated signal characteristics in drug/reaction/demographic information; and an output device whereby a user can receive analytic.

Abstract: A computer implemented system and method for encouraging frequent and purposeful electronic communications from caregivers to individuals with impaired memory to, inter alia, alleviate feelings of isolation and improve memory. The system includes a Web-based application through which caregivers send text, image, voice and other forms of data for receipt by the sufferer on a PDA having a simple user interface. The Web application records the dates and nature (i.e., text, audio, photograph, video) of communications sent by each caregiver, processes the data in order to display it in a variety of meaningful ways to all caregivers, thus creating a peer-pressure environment to encourage more frequent communication.

Abstract: A communication system for monitoring the health status of a patient includes a communication device and a sensor device, the communication device comprising a first communication interface for communication with the sensor device and comprising a second communication interface for communication with a health care center, the communication device being able to generate a warning message upon failure of either the first communication interface or the second communication interface, wherein the generation of a warning message is prevented if the failure of the first communication interface begins and ends during a first time interval and/or the generation of a warning message is prevented if the failure of the second communication interface begins and ends during a third time interval and/or the communication device comprises a detection device for detecting a critical or non-critical health status, and the generation of a warning message is prevented if both the duration of failure of the second communication

Abstract: An enhanced method for displaying assessment and analysis of risks of adverse effects resulting from use of at least one substance of interest, comprising: identifying the at least one substance of interest; selecting a profile related to the safety of the at least one substance of interest, using at least one filter; analyzing the risks of adverse effects resulting from the use of the at least one substance of interest using at least one data mining engine; and displaying the results of the analysis of risks of adverse effects in a format that permits perception of correlations. Such a format is preferably at least one format selected from the group consisting of a radar display for display of correlations, a sortable table, and a sortable line listing and where the format contains elements linked to data regarding the adverse effects.

Abstract: A method of treating a wound using a customized dressing. In the method, at least one wound characteristic is evaluated. A treatment need as a function of the at least one wound characteristic is determined. A dressing having a dressing characteristic responsive to the treatment need is fabricated and applied to the wound. A dressing for use therewith and an apparatus and system for fabricating the dressing are provided.

Abstract: A neural network for processing arrays of data with pertinent topology includes a n-dimensional array of cells (Ki) corresponding to the knots of the neural network, each cell having connections to the directly adjacent cells (Kj) forming the neighborhood of a cell (Ki), Each cell (Ki) has inputs for each connection to directly adjacent cells; an output for the connection to one or more of the directly adjacent cells (Kj), the connection between the cells being determined by weights (wij), and each cell being characterized by an internal value and being able to carry out signal processing for generating a cell output signal (ui), The output signal (ui) of a cell (Ki) is a function of its internal value and of the input signals from the neighboring cells, each cell being associated univocally to a record of a n-dimensional database (Pi) with pertinent topology and the value of each data record being the starting value of the corresponding cell.