Abstract: An apparatus (10) for predicting patient respiratory stability includes a patient data memory (24) which stores patient data for a patient (12) and an analyzer (34) in communication with the memory computes a measure of patient respiratory stability. The analyzer applies one or more rules to the patient data that are based on a plurality of parameters which in combination, have been identified as being predictive of patient respiratory instability, such as mean airway pressure (MAWP), plateau pressure (PP), arterial oxygen saturation (SaO2 or SpO2), and heart rate (HR). Based on the application of the rules, the analyzer determines the measure of patient respiratory stability.

Abstract: A system (202) generates patient alarms using a stepped alarm scheme. The system (202) includes one or more processors (220) programmed to receive physiological scores and/or physiological parameter values; compare the physiological scores and/or the physiological parameter values to a plurality of alarm levels; in response to a physiological score and/or physiological parameter value falling within an uninhibited zone of the alarm levels, issue an alarm; and set a first inhibition period for the uninhibited alarm level after issuing the alarm.

Abstract: A clinical decision support system (16) monitors one or more patients. The system (16) includes one or more processors (84) programmed to receive patient data for the patients. For each patient, one or more monitoring rules are selected from a plurality of monitoring rules based on patient data availability and/or patient context. A determination is made as to whether a patient is deteriorating using the selected monitoring rules for the patient. In response to determining the patient is deteriorating, an alert is generated.

Abstract: A system (202) generates patient alarms using a stepped alarm scheme. The system (202) includes one or more processors (220) programmed to receive physiological scores and/or physiological parameter values; compare the physiological scores and/or the physiological parameter values to a plurality of alarm levels; in response to a physiological score and/or physiological parameter value falling within an uninhibited zone of the alarm levels, issue an alarm; and set a first inhibition period for the uninhibited alarm level after issuing the alarm.

Abstract: Methods and apparatus for training a system for developing a process of data mining, false positive reduction, computer-aided detection, computer-aided diagnosis and artificial intelligence are provided. A method includes choosing a training set from a set of training cases using systematic data scaling and creating a classifier based on the training set using a classification method. The classifier yields fewer false positives. The method is suitable for use with a variety of data mining techniques including support vector machines, neural networks and decision trees.

Abstract: A method for segmenting regions within a medical image includes evaluating a set of candidate segmentations generated from an initial segmentation. Based on distance calculations for each candidate using derivative segmentations, the best candidate is recommended to clinician if it is better than the initial segmentation. This recommender realizes a most stable segmentation that will benefit follow-up computer aided diagnosis (i.e. classifying lesion to benign/malignant).

Abstract: An electronic programming guide (EPG) system employing a preference engine and processing system that combines explicit rule profile, history profile, and feedback profile data to generate new predictions. Television shows are presumed to be indexed by many features. These features are extracted and counted for TV shows watched (implicit profile), and for TV shows rated by the viewer (feedback profile). These profiles are straightforward to combine with suitably greater weight being given to the feedback information. In addition, explicit profiles can make recommendations that stand alone or may be used to modify recommendations arising from either of the two sources. The modifications may take the form of additive or multiplicative changes to the existing recommendations or some other suitable mathematical form.

Abstract: An apparatus (10) for predicting patient respiratory stability includes a patient data memory (24) which stores patient data for a patient (12) and an analyzer (34) in communication with the memory computes a measure of patient respiratory stability. The analyzer applies one or more rules to the patient data that are based on a plurality of parameters which in combination, have been identified as being predictive of patient respiratory instability, such as mean airway pressure (MAWP), plateau pressure (PP), arterial oxygen saturation (SaO2 or SpO2), and heart rate (HR). Based on the application of the rules, the analyzer determines the measure of patient respiratory stability.

Abstract: A method for computer aided detection (CAD) and classification of regions of interest detected within HRCT medical image data includes post-CAD machine learning techniques applied to maximize specificity and sensitivity of identification of a region/volume as being a nodule or non-nodule. The regions are identified by a CAD process, and automatically segmented. A feature pool is identified and extracted from each segmented region, and processed by genetic algorithm to identify an optimal feature subset, which subset is used to train the support vector machine to classify candidate region/volumes found within non-training data.

Abstract: Methods and apparatus for training a system for developing a process of data mining, false positive reduction, computer-aided detection, computer-aided diagnosis and artificial intelligence are provided. A method includes choosing a training set from a set of training cases using systematic data scaling and creating a classifier based on the training set using a classification method. The classifier yields fewer false positives. The method is suitable for use with a variety of data mining techniques including support vector machines, neural networks and decision trees.

Abstract: A television programming recommender is disclosed that selectively obtains feedback information from a user to update one or more profiles associated with the user. Previously obtained implicit and explicit preferences are utilized to selectively focus the collection of feedback information to further update and refine the implicit and explicit preferences. The present invention obtains feedback from a user in a manner that maximizes the value of the obtained information and improves the performance of the television programming recommender. The present invention automatically requests feedback from the user upon the occurrence of predefined criteria. The nature of the requested feedback, and the manner in which the obtained feedback is used to adjust a profile, can vary.

Abstract: A method for computer aided detection (CAD) and classification of regions of interest detected within HRCT medical image data. The method includes post-CAD machine learning techniques applied to maximize specificity and sensitivity of identification of a region/volume as being a nodule or non-nodule. The regions are identified by a CAD process, and automatically segmented. A feature pool is identified and extracted from each segmented region, and processed by genetic algorithm to identify an optimal feature subset, wherein a data stratification method is used to balance the number of cases in different classes. The subset determined by GA is used to train the support vector machine to classify candidate region/volumes found within non-training data.

Abstract: A method for computer aided detection (CAD) and classification of regions of interest detected within HRCT medical image data includes post-processing machine learning to maximize specificity and sensitivity of the classification to realize a reduction in number of false positive detections reported. The method includes training a classifier on a set of medical image training data selected to include a number of true and false regions, wherein the true and false regions are identified by a CAD process, and automatically segmented, wherein the segmented training regions are reviewed by at least one specialist to classify each training region for its ground truth, i.e.

Abstract: A method for computer aided detection (CAD) and classification of regions of interest detected within HRCT medical image data includes post-CAD machine learning techniques applied to maximize specificity and sensitivity of identification of a region/volume as being a nodule or non-nodule. The regions are identified by a CAD process, and automatically segmented. A feature pool is identified and extracted from each segmented region, and processed by genetic algorithm to identify an optimal feature subset, which subset is used to train the support vector machine to classify candidate region/volumes found within non-training data.

Abstract: A method for segmenting regions within a medical image includes evaluating a set of candidate segmentations generated from an initial segmentation. Based on distance calculations for each candidate using derivative segmentations, the best candidate is recommended to clinician if it is better than the initial segmentation. This recommender realizes a most stable segmentation that will benefit follow-up computer aided diagnosis (i.e. classifying lesion to benign/malignant).

Abstract: A conversion system converts DICOM SR information from a DICOM-formatted file into an XML representation. By providing a mapping between DICOM SR and XML, the DICOM SR content material can be more easily processed by application programs that are DICOM-specific, such as medical analysis programs, as well as by application programs that are not DICOM-specific, such as routine clerical or data-management programs. In a preferred embodiment, a two-phase conversion is employed. The DICOM information is parsed and Fig converted directly into a “raw” XML data set. Thereafter, the “raw” XML is transformed into a proper XML output form, via an XSLT processor. Changes to the desired XML output form can thus be effected via changes in the corresponding XSLT stylesheets.

Abstract: A method for mapping a DICOM document into a UML document is disclosed and claimed by this invention. The method includes mapping each DICOM Information Entity in the DICOM document into a corresponding UML class in the UML document, mapping each DICOM IOD Module in the DICOM document into a corresponding UML class in the UML document, mapping each DICOM Macro in the DICOM document into a corresponding UML class in the UML document, and mapping each DICOM Attribute in the DICOM document into a corresponding UML attribute in the UML document. It also includes a UML profile for DICOM information model which guides the UML modeling for all the DICOM IODs. It can also guide the genertion of XML schemas and DTDs from UML models based on this profile.

Abstract: Artificial intelligence applications require use of training sets containing positive and negative examples. Negative examples are chosen using distributions of positive examples with respect to a dominant feature in feature space. Negative examples should share or approximately share, with the positive examples, values of a dominant feature in feature space. This type of training set is illustrated with respect to content recommenders, especially recommenders for television shows.

Abstract: The invention relates to a method of providing DICOM SR constraints within an XML document. An XML document is created containing DICOM SR constraints using declarative language. The document can then be accessed and displayed if desired.

Abstract: An electronic programming guide (EPG) system employs a preference engine and processing system that learns viewers' television watching preferences by monitoring their viewing patterns. The system operates transparently to build a profile of a viewer's tastes. The profile is used to provide services, for example, recommending or automatically recording television programs the viewer might be interested in watching. To permit the personalization of the preferences database, a user interface is provided to allow the user to simulate various kinds of interaction with the system. This allows the system to build a profile rapidly without requiring a long interaction history to personalize the system.