Abstract: Disclosed herein are methods for identifying a subject as having NSCLC that is predicted or is likely to respond to treatment with an ALK inhibitor, for example crizotinib. The methods include identifying a sample including NSCLC tumor cells as ALK-positive or ALK-negative using immunohistochemistry (IHC) and scoring methods disclosed herein. A subject is identified as having NSCLC likely to respond to treatment with an ALK inhibitor if the sample is identified as ALK-positive and is identified as having NSCLC not likely to respond to treatment with an ALK inhibitor if the sample is identified as ALK-negative. According to certain embodiments of the methods, subjects predicted to respond to an ALK inhibitor may then be treated with an ALK inhibitor such as crizotinib.

Abstract: A system can obtain a first prompt as output from inputting an alert about a computer system to a first retrieval-augmented generation system (RAG). The system can obtain a first answer as output from inputting the first prompt to a first large language model (LLM). The system can obtain a value maintained by an entity associated with the computing system as output from inputting the alert to a second RAG. The system can obtain a second answer as output from inputting the first answer, the value, and a second prompt to a second LLM, wherein the second LLM comprises the first LLM or another LLM different from the first LLM. The system can obtain a third answer as output from inputting the second answer, user information associated with the entity, and a third prompt to a third LLM. The system can make the third answer available to the entity.

Abstract: Service request generation using generative artificial intelligence is disclosed. For instance, a user query comprising character strings is received; the character strings are converted to initial vector values associated with a first continuous vector space. Groups of data representing knowledge base articles that are identified. The knowledge base articles are retrieved from first database equipment. The text content of the knowledge base articles is converted to further vector values associated with a second continuous vector space. A listing of support agent identities is determined based on the further vector values being proximate to additional vector values associated with the listing of support agent identities. The additional vector values are used to retrieve the listing of support agent identities from second database equipment and generate and transmit a service ticket to resolve the user query.

Abstract: Methods, systems, and apparatuses for detecting and describing heterogeneity in a cell sample are disclosed herein. A plurality of fields of view (FOV) are generated for one or more areas of interest (AOI) within an image of the cell sample are generated. Hyperspectral or multispectral data from each FOV is organized into an image stack containing one or more z-layers, with each z-layer containing intensity data for a single marker at each pixel in the FOV. A cluster analysis is applied to the image stacks, wherein the clustering algorithm groups pixels having a similar ratio of detectable marker intensity across layers of the z-axis, thereby generating a plurality of clusters having similar expression patterns.

Abstract: Service request generation using generative artificial intelligence is disclosed. For instance, a user query comprising character strings is received; the character strings are converted to initial vector values associated with a first continuous vector space. Groups of data representing knowledge base articles that are identified. The knowledge base articles are retrieved from first database equipment. The text content of the knowledge base articles is converted to further vector values associated with a second continuous vector space. A listing of support agent identities is determined based on the further vector values being proximate to additional vector values associated with the listing of support agent identities. The additional vector values are used to retrieve the listing of support agent identities from second database equipment and generate and transmit a service ticket to resolve the user query.

Abstract: Architectures and techniques are described that can encode temporal context into a prompt and/or a soft prompt associated with a natural language artificial intelligence (AI) model such as a large language model (LLM). For example, a group of alert messages generated by a rules-based engine can be received. Based on timestamp data associated with the alert messages temporal context can be retrieved from telemetry store or another store with time series data and/or temporal context data. The temporal context can be encoded into an embedding layer of the AI model that is configured to receive input according to a text modality rather than a temporal modality.

Abstract: The subject disclosure provides systems, computer-implemented methods, and clinical workflows for meso-dissection of biological specimens and tissue slides by incorporating annotation and inter-marker registration modules within digital pathology imaging and meso-dissection (or milling) systems. Images of a reference slide a milling slide may be acquired using the same imaging system, with the annotations on the image associated with the milling slide being based on the inter-marker registration. Each image along with its respective annotations and meta-data may be associated with a project or a case and stored in an image management system. A same-marker registration may be used to map annotations from the annotated image of the milling slide to a live image of the milling slide. The milling slide may be milled based on the annotations, with milled tissue output into a contained that is labeled in association with the labeled input slides.

Abstract: A method for time series anomaly detection with rare event failure prediction includes determining, by a device including a processor and using a first machine learning model, a location of a data anomaly within sequential data. The method also includes determining, by the device and using a second machine learning model that is not the first machine learning model, whether a probability of a future failure event is at least a threshold probability based on the data anomaly and the sequential data.

Abstract: A system can receive user input data that comprises an identification of a computer infrastructure component of a group of computer infrastructure components that are associated with a user account. The system can identify information about the group of computer infrastructure components based on the identification of the computer infrastructure component. The system can convert text of the user input data into a first numerical vector. The system can create a context of the user input data based on identifying a match between the first numerical vector and a second numerical vector of a group of numerical vectors, wherein the context corresponds to a natural-language version of the second numerical vector. The system can combine the context and the information about the group of computer infrastructure components into a combined context, and input the combined context and the user input data to a large language model to produce a result.

Abstract: A data center monitoring and management operation. Ther data center monitoring and management operation includes receiving telemetry input data from a plurality of data center assets contained within a data center, the telemetry input data; accessing data center remediation information from a repository of data center remediation information; training a hierarchical classifier using the input data from the plurality of data center assets and data center remediation information; and, predicting an occurrence of a data center issue associated with a particular data center asset using the trained hierarchical classifier.

Abstract: Provided herein are certain inhibitors of ROCK (rho-kinases or rho-associated kinases), which are useful as medicament, for the treatment Huntington's disease in particular.

Abstract: A cutting tool and a method of operating a cutting jaw is provided. The cutting tool includes a first jaw member having a first cutting edge and a first relief area adjacent the first cutting edge, the first jaw member further having a first projection extending from the first cutting edge into the first relief area. A second jaw member has a second cutting edge and a second relief area adjacent the second cutting edge, the second jaw member further having a second projection extending from the second cutting edge into the second relief area. Wherein the first projection and the second projection are sized to engage a leg of an ear clamp and prevent fully closing the ear clamp when the cutting tool is used in a crimping operation.

Abstract: Automated systems and methods are presented for retrospectively analyzing clinical trial data. A plurality of image derived from biological samples of patients in a cohort population are accessed. Image features are computed based on the plurality of images. A diagnostic feature metric is derived based on the computed image features. A cut point value is determined by applying a statistical minimization method using the derived diagnostic feature metric and patient outcome data from the cohort population, in which the cut point value identifies a patient in the cohort population as positive or negative for a diagnostic test.

Abstract: A method for time series anomaly detection with rare event failure prediction includes determining, by a device including a processor and using a first machine learning model, a location of a data anomaly within sequential data. The method also includes determining, by the device and using a second machine learning model that is not the first machine learning model, whether a probability of a future failure event is at least a threshold probability based on the data anomaly and the sequential data.

Abstract: A method for assisted context generation for enhanced accuracy in document inferencing includes designating, by a device including a processor and in response to an input prompt, a selected context information source from a group of context information sources using a first machine learning model. The selected context information source is designated based on relevance of the selected context information source to the input prompt. The method further includes constructing, by the device and using a second machine learning model that is not the first machine learning model, a human-readable response to the input prompt by applying parameters of the second machine learning model to the input prompt and the selected context information source.

Abstract: Immune context scores are calculated for tumor tissue samples using continuous scoring functions. Feature metrics for at least one immune cell marker are calculated for a region or regions of interest, the feature metrics including at least a quantitative measure of human CD3 or total lymphocyte counts. A continuous scoring function is then applied to a feature vector including the feature metric and at least one additional metric related to an immunological biomarker, the output of which is an immune context score. The immune context score may then be plotted as a function of a diagnostic or treatment metric, such as a prognostic metric (e.g. overall survival, disease-specific survival, progression-free survival) or a predictive metric (e.g. likelihood of response to a particular treatment course). The immune context score may then be incorporated into diagnostic and/or treatment decisions.

Abstract: A system, method, and computer-readable medium for processing in-order messages. A message broker is provided with unique message keys to performing in-order ensuring that a batch of messages are sent on the same message broker partition or data flow. A reactive generic data streaming processor provides a parallel data stream uniquely grouped to each message broker partition or data flow. In-order processing is maintained on each parallel data stream by using downstream publishers that preserve strict order in each data stream. A terminal sync message with a unique message key to identifies end of in-order streaming a message group.

Abstract: The technology described herein describes training an automatic semi-supervised labeler model, such as including a time series transformer with self-attention encoder, in conjunction with classifier training to produce more precise labels describing when anomalous, rare events occurred. The automatic labeler assigns a probability distribution parameterized by distribution parameters over a sample window. A classifier outputs an approximation of distribution parameters for an imprecise label (secondary event) correlated with the anomalous event. The approximation distribution along with the secondary event distribution are input into a loss function, which couples the automatic labeler to the classifier in a feedback loop. The loss function is optimized over iterations of the loop, with the loss minimized when the automatic labeler outputs the correct label. Once trained, additional labels can be automatically generated for further training.

Abstract: Immune context scores are calculated for tumor tissue samples using continuous scoring functions. Feature metrics for at least one immune cell marker are calculated for a region or regions of interest, the feature metrics including at least a quantitative measure of human CD3 or total lymphocyte counts. A continuous scoring function is then applied to a feature vector including the feature metric and at least one additional metric related to an immunological biomarker, the output of which is an immune context score. The immune context score may then be plotted as a function of a diagnostic or treatment metric, such as a prognostic metric (e.g. overall survival, disease-specific survival, progression-free survival) or a predictive metric (e.g. likelihood of response to a particular treatment course). The immune context score may then be incorporated into diagnostic and/or treatment decisions.

Abstract: A system, method, and computer-readable medium for encoded byte message serialization and deserialization by microservices. A comprising receiving a multi-level message is received that includes generic data types for serialization and deserialization the encoded byte message. The multi-level message includes a top level message as to type that provides general information about content and applicability, and sub-messages as to types that include content related to purpose which includes an undefined type that contains properties related to schema for serialization and deserialization of the encoded byte message. The top level message and sub-messages content are processed to determine the undefined type that contains properties related to schema for serialization and deserialization of the encoded byte message. Dynamic loading is performed as to schema properties of the undefined type for serialization and deserialization of the encoded byte message for consumption by the microservices.