Invented by Namita Kohli, Priya Padate, General Electric Co
The imaging related clinical context apparatus includes a wide range of devices such as magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, and X-ray machines. These devices are used to capture images of the internal structures of the body, allowing doctors to detect abnormalities and diagnose medical conditions.
The associated methods used in imaging related clinical context apparatus include image processing, image analysis, and image interpretation. These methods are used to enhance the quality of the images captured by the devices and to extract useful information from the images.
The market for imaging related clinical context apparatus and associated methods is driven by several factors, including the increasing prevalence of chronic diseases, the growing aging population, and the rising demand for minimally invasive diagnostic and treatment procedures. Additionally, technological advancements in imaging devices and software are also contributing to the growth of this market.
The MRI segment of the imaging related clinical context apparatus market is expected to grow at the highest rate due to its ability to provide detailed images of soft tissues and organs. The CT segment is also expected to grow significantly due to its ability to provide fast and accurate images of the body.
North America is the largest market for imaging related clinical context apparatus and associated methods, followed by Europe and Asia-Pacific. The growth of this market in these regions is attributed to the presence of well-established healthcare infrastructure, increasing healthcare expenditure, and the growing demand for advanced medical imaging technologies.
The key players in the imaging related clinical context apparatus and associated methods market include Siemens Healthineers, GE Healthcare, Philips Healthcare, Canon Medical Systems, and Fujifilm Holdings Corporation. These companies are investing heavily in research and development activities to develop new and innovative imaging technologies.
In conclusion, the market for imaging related clinical context apparatus and associated methods is expected to grow significantly in the coming years due to the increasing demand for advanced medical imaging technologies. The growth of this market is driven by several factors, including the increasing prevalence of chronic diseases, the growing aging population, and the rising demand for minimally invasive diagnostic and treatment procedures. Technological advancements in imaging devices and software are also contributing to the growth of this market.
The General Electric Co invention works as follows
Herein are described and disclosed “systems, methods and apparatus that facilitate detection, processing and relevancy analyses of clinical data, including imaging-related clinical context.” A processor for example of an imaging related clinical context apparatus analyzes a plurality documents to identify relevant documents within the plurality by applying natural language processing, with a subset forming tagged concept. The identified terms are then processed using a machine-learning model in relation to a relevancy criteria to select the subset relevant documents. The processor will output the subset relevant documents, including emphasized tags concepts.
Background for Imaging related Clinical Context Apparatus and Associated Methods
The statements in this section are merely background information about the disclosure, and may not be prior art.
Information systems are used in healthcare environments such as hospitals and clinics. These include hospital information system (HIS), radiology and clinical information systems and cardiovascular information systems. They also use storage systems such as library information systems and electronic medical records. The information stored may include, for instance, patient medication orders, medical history, imaging data and test results. It could also be management information or scheduling information. There is a wealth of information available but it can be siloed into separate systems that require separate search and retrieval. The associated systems’ technological limitations make it difficult to find correlations between healthcare data.
BRIEF DESCRIPTION
The apparatus includes a memory for storing instructions and data, and at least one processor. The at least processor analyzes a plurality documents to identify relevant documents within the plurality by applying natural language processing, with a subset forming tagged concept. It then processes the identified term using a machine-learning model in relation to a relevancy criteria for an examination in order to select the relevant subset. The subset of documents containing emphasized tagged concept is output by the at least one processor.
The following examples are provided: “Selecting the subset relevant documents by using a machine-learning model based on a relevancy criteria for an examination, and processing the identified words according to that model.
The computer-implemented methods include: analyzing a plurality documents by executing a processor instruction; a subset from the identified documents forming tagged concept; processing the identified term using a machine learning algorithm with respect to relevancy criteria for an examination; and adding emphasis to the tagged concept found in the selected subset. The example method includes outputting the subset relevant documents, including the emphasized tagged concept, by executing a processor instruction.
The following detailed description refers to the accompanying drawings, which form a part of this disclosure. In which are shown specific examples that can be practiced. These examples provide enough detail for one skilled in art to practice the subject matter. It is also to be understood that additional examples can be used and that logical and mechanical changes as well as electrical modifications may be made to the disclosure without departing from its scope. This detailed description does not limit the scope of this disclosure. It is intended to illustrate an example implementation. You can combine features from different parts of this description to create new aspects of subject matter.
When introducing the elements of different embodiments of this disclosure, the articles are?a? ?an,? The words?an?,? The terms?first,? The words?first? ?second,? The terms?second,’?third,’, and akin to them do not indicate any sort of order, quantity or importance but are instead used to differentiate one element from another. The words?including,? ?including,? The words ‘including,? The terms?connected to’ and?having’ are inclusive, meaning that additional elements may exist in addition to the list of elements. The terms “connected to” and “coupled to” are used interchangeably. ?coupled to,? etc. When one object is used (e.g. a material or element, structure, component, etc.), it can be referred to as a “material, element, structural, member” “An object can be directly coupled or connected to another object, or there may be one or more intermediary objects between one object and the second object.
The terms “system” and “unit” are used in this document. ?unit,? ?module,? ?engine,? Engines, etc. can include hardware and/or a software system that performs one or more functions. A module, unit or system, for example, may include a controller, computer processor and/or another logic-based device which performs operations on the basis of instructions stored in a tangible non-transitory storage medium such as a memory. A module, unit or system can also include a device with hard-wired logic that performs the operations. The various modules, units and/or engines shown in the figures can represent hardware that is controlled by software or hardwired commands, software that directs the hardware to perform operations, or any combination of the two.
It should also be understood that the term “one embodiment” is used in this context. or ?an embodiment? The present disclosure is not intended to exclude the existence of other embodiments which also incorporate the recited feature.
I. OVERVIEW
Research has shown that radiologists seek answers to two primary questions when interpreting imaging studies on a patient. What clinical question does the ordering physician hope to answer with this test? 2. What is the underlying condition of the patient, including severity and affected body region? Some examples are apparatus, systems and methods that generate and capture the imaging-related clinical context (IRCC). This helps answer these questions, as well as provide new resources and options, such as analysis, routing and computer-aided treatment options, for diagnosis and treatment.
The IRCC uses certain examples to provide relevant patient context when radiologists are reviewing images. Patient context is delivered to radiologists directly and integrated into their workflow. This includes pathology reports, clinical notes and surgical notes. The IRCC algorithm is taught by radiologists using keywords and sentence structures how to select relevant data.
Certain Examples enable exam, patient and image-specific data retrieval from disparate sources systems, and generate a visualisation of the retrieved info, individually and/or combined, to reveal new insight to improve image analysis and processing, as well as other health-related information processing and analysis. This will improve a radiologists’ ability to complete vital tasks across the continuum of imaging.
A sudden increase in EMR adoption has created a surplus of healthcare data. This data is increasing as healthcare providers are required to keep historical patient records. The data that is being accumulated rapidly includes imaging data, exam reports, procedure reports, pathology reports and other diagnostic information. The information available is increasing as bidirectional patient portals are used more. Patients’ uploaded data such as white visible-light images, blood pressure and blood sugar data, along with other home monitoring data, adds to this. It is impossible to review all the patient data in detail and determine what clinically relevant information can be used in any patient care context, such as the reading of an examination.
In a radiological exam, the clinical history and indication of a patient (CHI) is critical to a quality interpretation. This data gives a context for acute symptoms and findings that can be more accurately interpreted. Radiologists can interpret imaging findings within the correct clinical context when they have accurate and relevant information about current symptoms and medical history. This leads to a more accurate differential diagnosis and a useful report for clinicians, as well as a better outcome for patients.
However, studies have shown that the radiologist’s exam orders often lack relevant medical information. This lack of data could have a negative impact on the quality of interpretation of information. The radiologist can improve their interpretation by automatically presenting aggregated information about the patient in a reading workflow.
Radiologists are able to access patient records through other systems, such as electronic medical records. However, this can be time-consuming because the radiologist has to navigate multiple menus and access separate systems in order find clinically relevant information. Some examples meet the technological needs of the industry, by providing systems, devices, and methods that automatically collect and aggregate information, and then present it to the radiologists in the context reading workflow.
In certain examples, the IRCC links data in real-time (or virtually real-time, depending on whether it is storing, retrieving, transmitting, or processing latency). One or more external systems are used to embed data such as pathology reports and lab results in the workflow. The clinical content of a patient is then presented in context, so that clinicians are able to gain a better understanding of the patient and arrive at a diagnosis more quickly.
The IRCC allows users to visualize exam, patient and image-specific data from multiple sources and gain new insights. This will improve their ability to perform tasks throughout the imaging continuum. Instead of assuming a radiologist?s content will remain unchanged until the report is completed, certain examples retrieve and display the information as the radiologist?s needs change.
The IRCC eliminates any need for a radiologist log in to another application, search for documents and look for relevant information. The IRCC allows the user to save time and diagnose the patient faster. The sheer amount of information that is often available on a patient – especially if they have a chronic illness – can make it difficult to convey the correct information to a radiologist.
Click here to view the patent on Google Patents.