Siemens Healthineers has debuted its second pathway for its AI-Pathway Companion. This new pathway is focused on non-small cell lung cancer, supporting personalized and standardized decision-making along the whole treatment process.
The AI-Pathway Companion Lung Cancer assists multidisciplinary teams (MDT) by facilitating patient management and case reviews in a single dashboard, providing quality checks on data completeness and enabling the documentation of clinically relevant patient-specific notations.
“During lung MDT discussion, it frequently becomes apparent that a key diagnostic report or other crucial information is not yet available,” said Mathias Prokop, head of the department of radiology, nuclear medicine and anatomy at Radboud University Nijmegen.
“These patients have to be discussed again in the next meeting. This wastes time and effort for all physicians involved in the MDT. A digital assistant, which ensures that the right set of information is available, would substantially increase efficiency.”
Siemens Healthineers adds the pathway for lung cancer for its AI-Pathway Companion to the existing CE-marked pathway for prostate cancer. The software is designed to help in advanced oncology care by integrating contextualized data along the patient pathway.
Using the full pathway with all available data, healthcare professionals can optimize the treatment for the individual patient, and adherence to evidence-based standards of care is easier to accomplish, the company said. This transparency also helps collaboration across departments and cancer boards.
Siemens Healthineers is in HIMSS21 booth 3121.
Chooch AI automates with computer vision
Chooch AI, a computer vision AI platform company, has introduced computer vision models that will efficiently support healthcare, the company said.
Chooch AI models have been developed and deployed for a growing number of applications:
- Smart operating rooms. Collects log information at beginning and end of medical procedures; counts and tracks all surgical protocols, devices and materials. The data generated triggers alerts, actions and messages to the appropriate parties throughout the system.
- Workplace and patient safety. Patient monitoring in hospital settings to detect issues such as falls or other activity. PPE detection is an industry-agnostic application of computer vision that protects workers and reduces risk in many industries, the company said. In healthcare, these AI models can detect that safety equipment is used and procedures such as handwashing are followed.
- Microscopy. Chooch AI can count cells on slides with 98% accuracy and more than 100 times the speed of human cell-counting, the company asserted. Chooch AI Models currently are being licensed for use in research facilities and microscopes. The main focus has been to accelerate drug discovery, but AI models have been created to detect types of cells.
- Imaging analysis. The platform is being used for several different imaging analysis use-cases. The AI models are extremely accurate and fast to train, the company said. Any type of imaging process can be used to train AI and detect features for radiology analysis.
Chooch offers a computer vision platform to ingest data, generate data sets, train models and deploy computer vision to the edge. Chooch relieves data scientists from time-consuming tasks such as bundling different deep learning components, data collection, labeling, neural network selection, and others, before even training AI visual models, the company explained.
Chooch AI is in HIMSS21 booth C100-78.
Sensyne Health reaches AI milestone
Sensyne Health, a clinical AI company, has reached a milestone of access to a combined clinical research, clinical trial, and real-world, de-identified and anonymized dataset of more than 60 million patients. This enlarged dataset results from both Sensyne’s investment in virtual clinical development company Phesi in January 2021 and the progress made by Sensyne and Phesi in building their respective data platforms.
Between December 2020 and July 2021, Phesi grew its clinical research and clinical trial dataset from 13 million to 42 million patients through a concerted effort in acquiring and structuring data registries of de-identified data. At the same time, Sensyne, through its ethical strategic research agreement model that partners with health systems, grew its real-world patient dataset from 6 million to more than 18 million patients.
The combined international dataset now contains a high-quality, deep, longitudinal variety of structured de-identified and anonymized data in more than 4,000 indications, including rare diseases, the company reported.
The combined dataset, together with Sensyne’s machine learning expertise, provides deeper understanding of clinical trial and real-world patient populations, which can improve the ability to select the right patients for synthetic control arm clinical trials as comparators to traditional clinical studies, the company explained.
Specifically, the data can help in identifying relationships between one disease and another and help in building predictive models that contribute toward the development of synthetic control arms, creating early warning systems for drugs in development by helping indicate the drugs that may or may not work.
Such activity can de-risk trials, lower life-science R&D costs and reduce the time to market for effective drugs, the company said. Also, critically, it can begin to limit the number of patients enrolled in clinical trials that are exposed to placebos, the company added.
“Sixty million patients is an important milestone in our journey to create the world’s best data resource for medical research,” said Lord Paul Drayson, CEO of Sensyne Health. “However, it is the quality and depth of the data across many disease areas and the combination of … clinical research data, clinical trials data and longitudinal real-world data from electronic patient records that [make] the database such a powerful tool for research professionals in both the life sciences and healthcare sectors.”