The research paper on AI Predictive Diagnosis Algorithm for Stroke (First author: Yosuke Hayashi, Responsible author: Taka-aki Nakada) has been published in the international scientific journal Scientific Reports (published by Nature Research, UK).
The research and development of the AI prediction algorithm for stroke was adopted by the Japan Agency for Medical Development (AMED) under the research and development project "Advanced Medical Devices and Systems Technology Development Project: Research and Development of Emergency Medicine Prediction", and was conducted jointly by Smart119 Inc. and the Department of Emergency and Intensive Care Medicine, Graduate School of Medicine, Chiba University.
This paper reports on the establishment and demonstrated effectiveness of an AI predictive diagnosis algorithm for stroke disease in acute care. This development is expected to be applied to other medical conditions. Smart119 Inc. has applied for a patent for this algorithm.
◆Detailed press release
https://prtimes.jp/main/html/rd/p/000000047.000056624.html
◆Background of the Development Research
The three major diseases ("cancer," "acute myocardial infarction," and "stroke") account for a large percentage of the number of emergency cases brought in.
Stroke, in particular, tends to occur suddenly and is classified into a number of conditions, including subarachnoid hemorrhage, cerebral infarction, cerebral hemorrhage, and occlusion of the main artery. In order to save lives as well as to reduce the aftereffects such as hemiplegia, prompt and optimal acute treatment is required. However, at present, the decisions of the emergency team are not shared with the medical institutions, so the medical condition of the patient is determined by diagnosis after arrival at the receiving hospital.
-Improving the accuracy of the emergency team's judgment based on the condition of the patient.
-Acute stage treatment at medical institutions with specialized doctors and facilities.
We have started to develop AI predictive diagnosis to satisfy the above two points quickly and accurately. The results of the AI predictive diagnosis will be shared between the emergency team and medical institutions.
◆Published in the international scientific journal Scientific Reports
A prehospital diagnostic algorithm for strokes using machine learning: a prospective observational study
https://www.nature.com/articles/s41598-021-99828-2
◆Purpose of Development
＜Purpose of the prediction algorithm＞
To determine the symptoms of stroke, such as "subarachnoid hemorrhage," "cerebral infarction," "cerebral hemorrhage," and "occlusion of the main artery," based on the conditions that exist individually in the background of emergency patients (condition, disease history, weather conditions, etc.).
＜Data formation＞
-Data will be collected from August 2018 with the cooperation of medical institutions in Chiba City and the Chiba City Fire Department.
-The number of data collected is approximately 1,500 emergency patients who may have had a stroke.
-The content of the data includes the condition of the emergency patient, age, gender, and weather conditions at the time.
＜Algorithm calculation method and verification＞
-XG Boost (*1)
-From the data of approximately 1,500 patients, design a classification algorithm and model using 80% (approximately 1,200 patients) for machine learning, and verify it using 20% (approximately 300 patients) for testing.
-As a result of validating the classification algorithm with the data of about 300 people for testing, an AUC value of 0.980(*2) was obtained.
◆Toward practical use
We expect that the AI predictive diagnosis function using the stroke prediction diagnosis algorithm will be added to the application "Smart119," an emergency medical information service, by the end of this year for tablet terminals installed in ambulances owned by the Chiba City Fire Department, which has introduced Smart119.
＜Procedure of AI predictive diagnosis function＞
1) If there is a possibility of stroke, tap the "Stroke Diagnosis Button".
2) On the dedicated diagnosis page, enter the emergency patient's condition according to the options.
3) Check the medical condition from the AI predictive diagnosis.
4) The system automatically selects a medical institution with specialized doctors and facilities, and makes a request for acceptance.
◆Published in the international scientific journal Scientific Reports
A prehospital diagnostic algorithm for strokes using machine learning: a prospective observational study
https://www.nature.com/articles/s41598-021-99828-2
◆Purpose of Development
＜Purpose of the prediction algorithm＞
To determine the symptoms of stroke, such as "subarachnoid hemorrhage," "cerebral infarction," "cerebral hemorrhage," and "occlusion of the main artery," based on the conditions that exist individually in the background of emergency patients (condition, disease history, weather conditions, etc.).
＜Data formation＞
-Data will be collected from August 2018 with the cooperation of medical institutions in Chiba City and the Chiba City Fire Department.
-The number of data collected is approximately 1,500 emergency patients who may have had a stroke.
-The content of the data includes the condition of the emergency patient, age, gender, and weather conditions at the time.
＜Algorithm calculation method and verification＞
-XG Boost (*1)
-From the data of approximately 1,500 patients, design a classification algorithm and model using 80% (approximately 1,200 patients) for machine learning, and verify it using 20% (approximately 300 patients) for testing.
-As a result of validating the classification algorithm with the data of about 300 people for testing, an AUC value of 0.980(*2) was obtained.
◆Toward practical use
We expect that the AI predictive diagnosis function using the stroke prediction diagnosis algorithm will be added to the application "Smart119," an emergency medical information service, by the end of this year for tablet terminals installed in ambulances owned by the Chiba City Fire Department, which has introduced Smart119.
＜Procedure of AI predictive diagnosis function＞
1) If there is a possibility of stroke, tap the "Stroke Diagnosis Button".
2) On the dedicated diagnosis page, enter the emergency patient's condition according to the options.
3) Check the medical condition from the AI predictive diagnosis.
4) The system automatically selects a medical institution with specialized doctors and facilities, and makes a request for acceptance.
＜ AI Predictive Diagnosis Screen＞
*This screen is a demo version and is possibly subject to change in the official release.
Using the tablet device, AI diagnosis can be performed and a request can be made to the most appropriate medical institution. Depending on the medical condition and symptoms, the receiving medical institution can call a specialist or prepare for emergency surgery before the ambulance arrives.
*1: A Scalable Tree Boosting System "Tree" is a thought diagram called a decision tree. A tree is a thought diagram in which branches spread out like a tree according to the branching points (decision points) in the process of reaching a goal. XG boosting is a method of improving accuracy by drawing a decision tree from the analysis of each model and using information on the differences between models.
*2：Area under the curve It is a curve value that indicates the accuracy of the classification algorithm. It is considered highly accurate when it exceeds the threshold value of 0.8.
Smart119 Inc.(Head Office: Chiba City, Chiba Prefecture, President/CEO: Taka-aki Nakada), a medical startup company originating from Chiba University, is pleased to announce that its emergency medical service "Smart119" (Patent No. 6875734) has been selected as a finalist in the ICF Business Acceleration Program 2021, an acceleration program of the Future Vision Initiative (managed by Mitsubishi Research Institute, Inc.).
The final screening will be held on December 10, after two months of mentoring starting in early October.
◆Future Process
Early October to early December: Mentoring program
-Business model building for business development
-Support for industry and business analysis, sales channel development, etc.
-Discussions on business strategies to bring about greater social impact
December 10 (Friday): Final judging session
Our goal is to create a "future healthcare where everyone can rely on" and we started our business to solve social issues in healthcare. We see this selection as an opportunity to enhance our mid- to long-term strategy, development capabilities, and business sustainability through co-creation with the open, multi-stakeholder network infrastructure of ICF and the Mitsubishi Research Institute. We will continue to make further contributions to healthcare that is safe and reliable for consumers.
Press Release Details
https://prtimes.jp/main/html/rd/p/000000056.000056624.html
Kyowakai Medical Corporation is a community-based medical institution with 3,600 employees and 2,521 sickbeds, operating five hospitals in Hyogo Prefecture (four in Kawanishi City (including designated management) and one in Nishinomiya City) and two in Osaka Prefecture (one in Suita City and one in Toyonaka City), as well as four nursing care facilities and providing home support services in each region.
"Smart:DR" was developed in accordance with Business Continuity Planning (BCP), which is designed to help hospitals and companies minimize damage and continue or recover from business operations in the event of a disaster, terrorist attack, or other emergency.In addition, considering COVID-19 as a natural disaster, we have added a "staff health management function" to deter hospital clusters and monitor changes in physical condition before and after vaccination, thereby supporting community medical care under a pandemic.With the release of the app version in July 2021, the system can be used on smartphones and tablet devices, making it even easier to implement.
Kyowakai Medical Corporation is developing a comprehensive regional health care system that includes medical bases that collaborate with each other in a wide area of Hyogo and Osaka, as well as home nursing and other home support services. Having experienced the Great Hanshin-Awaji Earthquake in 1995, Kyowakai needed to strengthen its comprehensive regional disaster medical care, which led to the introduction of Smart:DR. In addition, by adopting an application version of Smart:DR that can be carried around, it is possible to incorporate it into disaster countermeasures even when the staff is dispersed, such as in the case of home nursing.
◆Main background of the introduction at Kyowakai Medical Corporation
(1) We want to manage the health of our employees throughout the corporation in COVID-19 pandemic.
(2) In the event of a disaster, we would like to confirm the safety of our employees and quickly request a gathering.
(3) We want to maintain a means of contacting each staff member in case of emergency from medical facilities and home support businesses that operate in a wide area.
◆Features of Smart:DR
-Emergency communication and safety confirmation for staff
-Real-time grasp of the status of the group in an emergency, and support for optimal staffing
-Automatic aggregation of health management information based on a medical point of view
-Replies can be completed with a single click, and no login is required.
-The system has a bulletin board function that can be used even during normal times.
-An application version is available for smartphones and tablet devices to utilize the above functions.
Smart:DR supports the disaster countermeasures for medical institutions that provide comprehensive health care, such as medical centers in a wide area and home support services such as home nursing visiting each patient's home, by using ICT.
◆Smart:DR" website
https://smart119.biz/dr/
Last month, in Kashiwa City, Chiba Prefecture, a pregnant woman with COVID-19 could not find a place to be hospitalized, and her baby died after being delivered at home.
In response this case, Smart119 has developed a new system to share information on pregnant women who need to be transported urgently with obstetricians, etc., and to quickly coordinate hospitalization.
Chiba Prefecture to Introduce New System to Promptly Adjust Hospitalization of Pregnant Women in Need of Transport
https://www3.nhk.or.jp/shutoken-news/20210917/1000070291.html
Detailed press release
https://prtimes.jp/main/html/rd/p/000000054.000056624.html
In the demonstration experiment to be conducted under this project, we will develop and operate an optimized system for the purpose of improving the efficiency of emergency delivery in Yamanashi Prefecture (shortening the time required and improving the lifesaving rate). We will analyze the data obtained from the demonstration experiment and propose the development of Smart119 optimized for Yamanashi Prefecture.
［Background]
Yamanashi Prefecture is aiming to become a center of cutting-edge technology, as a new station is expected to be established when the Linear Central Shinkansen Line opens in the near future, improving accessibility to the area to 25 minutes from central Tokyo and 45 minutes from Nagoya. As a part of this effort, the "Open Platform Yamanashi: Creating the Future with Cutting-Edge Technology Using Test Beds as a Starting Point" was formulated, and the "TRY! YAMANASHI! Demonstration Experiment Support Project" was established. In this demonstration experiment support project, demonstration experiments of cutting-edge technologies (medical care, energy, mobility, agriculture, etc.) will be conducted in the entire prefecture with the aim of implementing them in society.
Smart119, the emergency medical information service approved for this project, was developed from the perspective of emergency and medical care and is currently in operation in Chiba City as a system that supports "selection of an appropriate hospital," "prompt delivery," and "prompt and accurate treatment after delivery," which are essential for acute care. Emergency medical care is largely dependent on medical resources (medical institutions, personnel, etc.) and regional characteristics. In urban areas where the number of medical institutions is large but the number of emergency calls is high, there is a chronic overload of work for emergency teams.
Through this demonstration experiment in Yamanashi Prefecture, we will develop a system that is close to the local community and verify its operation in order to solve the difficulty of bringing in emergency medical services and improve the delivery time.
We will analyze the data obtained from the demonstration experiment, as well as regional characteristics such as population composition, climate, fire stations, number of ambulances owned, and number of medical facilities, and propose the development of Smart119 optimized for Yamanashi Prefecture. Smart119 will utilize the results of this demonstration experiment in the development of its business to local governments nationwide, and contribute to medical care that is safe and reliable for consumers.
◆Implementation and support period of the demonstration experiment
From late September 2021 to the end of February 2022
◆Details of the Smart119 verification experiment
-Each fire department command center and ambulance team will be equipped with tablet terminals, and patient information will be entered in emergency cases, and the information will be used to request hospitals to accept patients.
-Hospitals will check the patient information sent from the ambulance corps on their PC screens, decide whether or not to accept the patient, reply, and if so, prepare to accept the patient.
-The system will be implemented with the cooperation of the Command Section, Security Section, and Emergency Section of the Fire Department in Yamanashi Prefecture, the Medical Control Council in Yamanashi Prefecture, and the emergency departments of hospitals designated as secondary or tertiary emergency.