International Business Machines Corporation

Edward Vitkin

Alex Melament

Yardena Lia Peres

Igor Kostirev-Kronos

Ariel Farkash

Dorit Baras

Bazarbek Uatay

Igor Kostirev

Time-series data uncertainty reduction can include generating an initial accumulated signal based on an event classifier prediction score. The event classifier prediction score can be generated by an event predicator based on time-series data and can correspond to a probability that a target event occurs. Signal leakage can be imposed on the initial accumulated signal. Additionally, an alert can be generated in response to determining that the initial accumulated signal is greater than an alert threshold.

Time-series data uncertainty reduction

A method comprising using at least one hardware processor for: receiving multiple data clusters, each comprising one or more path variations of a process performed with respect to multiple subjects, wherein each of the path variations comprises multiple stages of the process, and wherein at least some of the stages, each comprises one or more parameters; constructing a visualization template representative of the path variations, wherein the visualization template comprises multiple nodes, each node having one or more graphical attributes, wherein each node representative of a corresponding stage; assigning each of the graphical attributes of each of the nodes to a corresponding parameter of the corresponding stage; and visualizing one or more differences between the data clusters by generating at least one instance of the visualization template, the instance being representative of and corresponding to at least two of the data clusters, wherein each of the at least one instance is representative of and corresponding to at least one of the data clusters, and wherein in the at least one instance, each of the assigned one or more graphical attributes of each node represent a value of the corresponding parameter, the value relating to the corresponding stage of the at least one corresponding data cluster.

Visual comparison of data clusters

Method, system, and computer program product are provided for predicting diagnosis of a patient performed by a computerized device. The method may include: modeling data from a group of successfully diagnosed patients, wherein the data is modeled as treatment paths of patients including referrals to medical practitioners; and predicting diagnosis for a current patient by comparing a treatment path of the current patient with the modeled treatment paths of successfully diagnosed patients, including calculating a probability of a given diagnosis from the modeled treatment paths. The method may include: defining a set of medical entities including medical practitioners to which a patient has been referred; and gathering treatment paths of successfully diagnosed patients, wherein the treatment path links medical entities in a directional route. Predicting diagnosis for a current patient may use the modeled data to calculate the probability of each model instance for each diagnosis and choosing the model instance of the diagnosis that maximizes the treatment path probability.

Predicting diagnosis of a patient

Growing community of inventors

Nesher, Israel

Edward Vitkin