Abstract: A method for classifying features in a digital medical image includes providing a plurality of feature points in an N-dimensional space, wherein each feature point is a member of one of two sets, determining a classifying plane that separates feature points in a first of the two sets from feature points in a second of the two sets, transforming the classifying plane wherein a normal vector to said transformed classifying plane has positive coefficients and a feature domain for one or more feature points of one set is a unit hypercube in a transformed space having n axes, obtaining an upper bound along each of the n-axes of the unit hypercube, inversely transforming said upper bound to obtain a new rule containing one or more feature points of said one set, and removing the feature points contained by said new rule from said one set.

Abstract: A method for training a classifier for classifying candidate regions in computer aided diagnosis of digital medical images includes providing a training set of images, each image including one or more candidate regions that have been identified as suspicious by a computer aided diagnosis system. Each image has been manually annotated to identify malignant regions. Multiple instance learning is applied to train a classifier to classify suspicious regions in a new image as malignant or benign by identifying those candidate regions that overlap a same identified malignant region, grouping each candidate region that overlaps the same identified malignant region into a same bag, and maximizing a probability P = ? i = 1 N ? p i y i ? ( 1 - p i ) 1 - y i , wherein N is a number of bags, pi is a probability of bag i containing a candidate region that overlaps with an identified malignant region, and yi is a label where a value of 1 indicates malignancy and 0 otherwise.

Abstract: A method is provided for automatically identifying a disease outbreak indicative of a potential bio-terror attack. Patient records are mined from structured and unstructured clinical sources. The patient records are then analyzed by correlating selected patient data contained in the patient records with disease indicia for each of a plurality of diseases. A probability of a disease outbreak is estimated at least in part based on these correlations. Suspicion may also be indicated if anomalous disease clusters are found. If any of the estimated probabilities exceeds a threshold value, a disease outbreak alert is outputted. The disease indicia may be defined by disease progression models, which may be stored in a disease knowledge base.

Abstract: A method for creating and searching medical ontologies includes providing a semi-structured information source comprising a plurality of articles linked to each other, each article having one or more sections and each article is associated with a concept, creating a directed unlabeled graph representative of the information source, providing a plurality of labels, labeling a subset of edges, and assigning each unlabeled edge an equal probability of being assigned one of the labels. For each node, the probability of each outgoing edge is updated by smoothing each probability by an overall probability distribution of labels over all outgoing edges of each node, and the probability of each incoming edge is updated the same way. A label with a maximum probability is assigned to an edge if said maximum probability is greater than a predetermined threshold to create a labeled graph.

Abstract: A list of biomarkers indicative of patient outcome is reduced. A computer program is applied to a set of biomarkers indicative of a patient outcome (e.g., prognosis, diagnosis, or treatment result). The computer program models the set of biomarkers with a subset of the biomarkers. The subset is identified without labeling based on the patient outcome. Instead, biomarker scores (e.g., sequence score) are used to identify the subset of biomarkers.

Abstract: A method for predicting survival rates of medical patients includes providing a set D of survival data for a plurality of medical patients, providing a regression model having an associated parameter vector ?, providing an example x0 of a medical patient whose survival probability is to be classified, calculating a parameter vector {circumflex over (?)} that maximizes a log-likelihood function of ? over the set of survival data, l(?|D), wherein the log likelihood l(?|D) is a strictly concave function of ? and is a function of the scalar x?, calculating a weight w0 for example x0, calculating an updated parameter vector ?* that maximizes a function l(?|D?{(y0,x0,w0)}), wherein data points (y0,x0,w0) augment set D, calculating a fair log likelihood ratio ?ƒ from {circumflex over (?)} and ?* using ?ƒ=?(?*|x0)+sign(?({circumflex over (?)}|x0)){l({circumflex over (?)}|D)?l(?*|D)}, and mapping the fair log likelihood ratio ?ƒ to a fair price y0ƒ, wherein said fair price is a probability that class label y0 for exam

Abstract: A method is provided for automatically identifying a disease outbreak indicative of a potential bio-terror attack. Patient records are mined from structured and unstructured clinical sources. The patient records are then analyzed by correlating selected patient data contained in the patient records with disease indicia for each of a plurality of diseases. A probability of a disease outbreak is estimated at least in part based on these correlations. Suspicion may also be indicated if anomalous disease clusters are found. If any of the estimated probabilities exceeds a threshold value, a disease outbreak alert is outputted. The disease indicia may be defined by disease progression models, which may be stored in a disease knowledge base.

Abstract: A method for training classifiers for ICD-9 patient codes includes providing a set of documents regarding patient hospital visits, combining the documents for each patient visit to create a hospital visit profile, defining a feature as an ngram with a frequency of occurrence greater or equal to a predetermined value that does not appear in a standard list of ngrams, processing the profiles to remove redundancy at a paragraph level and perform tokenization and sentence splitting, performing feature selection, randomly dividing the documents into training, validation, and test sets, and training a set of binary classifiers using a weighted ridge regression, each binary classifier targeting a single ICD-9 code using the training set, wherein each classifier is adapted to determining a specific ICD-9 code by analyzing a patient's hospital records.

Abstract: The present invention provides methods and compositions for predicting patient responses to cancer treatment using a proliferation gene signature. These methods can comprise measuring in a biological sample from a patient the levels of gene expression of a group of the genes designated herein. The present invention also provides for microarrays that can detect expression from a group of genes.

Abstract: Improvements in mining information from patient records and/or use of such mined information are provided. The identity of the patient is used to link to patient records at different institutions for mining. The user controls one or more thresholds for mining and/or inferring. By providing a user interface that allows selection of a portion of the statistical summary, data supporting the statistics may be output. To assist in understanding the knowledge base used for mining or inferring, a visual representation is output. The mining may be used for diagnosis related groupings.

Abstract: Medical or other data is de-identified by obfuscation. Located instances are replaced. By replacing with values in a same format and level of generality, multiple possible identifications—the replacement values and the instances not located—are provided in the data, obfuscating the original identification. By replacing as a function of a probability, the resulting data set has different instances distributed in a way making identification of the actual or original instances not located by searching more difficult.

Abstract: Members of a medical entity class are extracted from patient data. A semi-supervised approach uses one or more initial medical terms such as terms from an ontology, for a given category or medical canonical entity. A larger set of medical terms is extracted from the medical information. In one example, the extraction is performed using lexical surface form features, rather than syntactical parsing.

Abstract: A system and method for diagnosis and treatment decisions based on information maximization is disclosed. Utilizing patient information as well as clinical records from other patients can reduce the uncertainty in both diagnosis and treatment options. The information maximization may consider additional data such as risk, cost, and comfort in making a proper medical decision.

Abstract: A system and method for optimizing database access for record linkage by tiling the space of record pairs are provided, the system including a processor, a segmentation and pairing unit in signal communication with the processor for segmenting database data into data segments and pairing the data segments into data quadrants, and a duplicate detection unit in signal communication with the processor for detecting duplicates for each quadrant; and the method including receiving database data, segmenting the database data into data segments, pairing the data segments into data quadrants, and detecting duplicates for each quadrant.

Abstract: A method for interpreting date information from unstructured text includes performing phrase tokenization on the unstructured text to identify one or more temporal phrases. Word categorization is performed on the one or more temporal phrases to categorize one or more words of each temporal phrase. Grammar analysis is performed to match each temporal phrase to an understood syntax using the categorizations of the words of each temporal phrase. Each temporal phrase is interpreted based on the matched syntax.

Abstract: A system and method for diagnosis and treatment decisions based on information maximization is disclosed. Utilizing patient information as well as clinical records from other patients can reduce the uncertainty in both diagnosis and treatment options. The information maximization may consider additional data such as risk, cost, and comfort in making a proper medical decision.

Abstract: A method and device having instructions for analyzing input data-space by learning classifiers include choosing a candidate subset from a predetermined training data-set that is used to analyze the input data-space. Candidates are temporarily added from the candidate subset to an expansion set to generate a new kernel space for the input data-space by predetermined repeated evaluations of leave-one-out errors for the candidates added to the expansion set. This is followed by removing the candidates temporarily added to the expansion set after the leave-one-out error evaluations are performed, and selecting the candidates to be permanently added to the expansion set based on the leave-one-out errors of the candidates temporarily added to the expansion set to determine the one or more classifiers.

Abstract: A method for multiple-label data analysis includes: obtaining labeled data points from more than one labeler; building a classifier that maximizes a measure relating the data points, labels on the data points and a predicted output label; and assigning an output label to an input data point by using the classifier.

Abstract: A method and an apparatus display marks in an image data set, wherein an image data set comprising marks is provided and wherein during a review phase not all marks within the image data set are displayed at the same time. A list of the marks can be generated by sorting the marks depending on a predetermined sorting criterion and wherein the marks are displayed temporally one after another within the image data set in accordance with the generated list. The image data set is for example a medical image data set, wherein the marks are CAD marks and wherein the sorting criterion is the probability of marking illness, in particular the suspiciousness.

Abstract: A method and system for determining patient states is provided. The method includes the steps of data mining a patient record using a domain knowledge base relating to a disease of interest; inputting the mined data into a model of the disease of interest; and determining a state of the patient based on the model. The system includes a data miner for mining information from a patient record using a domain knowledge base relating to a disease of interest; and a processor for creating a patient model of the disease of interest, processing the mined data in the model to determine a current state of the patient and future states for different courses of treatment, and recommending a therapy based on the determined future state.