Fujitsu Laboratories Ltd. and Fujitsu Limited have developed a technology to digitize and quantify the walking patterns of patients whose movements vary due to the impact of different diseases.
Medical professionals can identify the symptoms of patients by observing their way of walking. However, it is difficult to digitize symptoms as there are numerous walking characteristics that differ depending on the type and severity of the disease, and as of now, physiotherapists conduct visual inspections in most cases. Now, Fujitsu has developed a technology to automatically and accurately quantify factors such as the swing time and stance time(*) of the right and left leg as well as the difference between the movements of both legs. In the new development, feature points at the time of movement change will be determined using signal waveforms emitted from commercially available gyro sensors attached to the patients’ ankles.
It is said that various symptoms such as musculoskeletal, neural and cardiovascular conditions affect the walking characteristics of patients. The new technology will enable healthcare professionals to quantify the gait of patients walking under the influence of such conditions, and as a result, they will be able to record recovery processes and help with the remote monitoring of patients, thereby improving the efficiency of medical services.
Background
In the medical field, it is essential to analyze the walking of patients to examine their changing symptoms and recovery status. In fact, it is well known that symptoms such as musculoskeletal, neural and cardiovascular conditions cause walking abnormalities. Accordingly, there was a demand for a walking analysis technology that could digitally capture the same information as physiotherapists in detecting early signs of disease symptoms.
Issues
A number of methods based on machine learning and rule-based algorithms have been proposed as conventional techniques for comparing and analyzing walking characteristics as quantitative data, and have attracted the attention of healthcare professionals. Nonetheless, physiotherapists work with patients diagnosed with a wide range of diseases, and the impact on their walking patterns differ significantly depending on such factors as the nature of the disease, its severity, and the location of disabled areas. Therefore, conventional techniques could not quantify various walking characteristics with high accuracy, as they could only analyze a limited number of walking patterns or were unable to prepare sufficient walking data for learning.
About the Newly Developed Technology
Fujitsu has developed a technology that can quantify the characteristics of various walking styles based on signals from gyro sensors attached to the patient’s ankles. This technology makes use of the newly developed model based on the law of motion, such as the relationship between the movements of the left and right legs during walking and how different walking characteristics transition over time, detecting feature points and assigning meaning to the signal waveform emitted from the gyro sensors. In this way, the signal of the walking step alone can be clearly identified, and the feature points of the walking step, when the heel touches the ground or when the toe is off the ground, can be recognized regardless of the walking method. By measuring these feature points, walking characteristics such as stride length and swing time can be quantified with high accuracy.
Outcome
Utilizing a commercially available gyro sensor, the new technology evaluates various ways of walking, including 9 types of walking abnormalities (walking in short steps, circumduction, shuffling, etc.), enabling an accurate calculation of multiple walking characteristics. Specifically, the automatic recognition accuracy of the walking segment for walking motions was 96.5% and the extraction error of stride time (sum of stance time and swing time) was 1.8%. In other words, the new technology reduced the measurement error up to 1/3 times compared to conventional commercial products that require manual input of walking section.
Future Prospects
Fujitsu will continue to develop the new digitization technology for the utilization of walking observation data by medical professionals as well as for the remote monitoring of home patients who are rapidly increasing in number.
(*) Swing time and stance time of the left and right legs The period in which one leg does not touch the ground during one walk cycle is called swing time, and the period in which one leg stays on the ground is called stance time.
Archive
- October 2024(44)
- September 2024(94)
- August 2024(100)
- July 2024(99)
- June 2024(126)
- May 2024(155)
- April 2024(123)
- March 2024(112)
- February 2024(109)
- January 2024(95)
- December 2023(56)
- November 2023(86)
- October 2023(97)
- September 2023(89)
- August 2023(101)
- July 2023(104)
- June 2023(113)
- May 2023(103)
- April 2023(93)
- March 2023(129)
- February 2023(77)
- January 2023(91)
- December 2022(90)
- November 2022(125)
- October 2022(117)
- September 2022(137)
- August 2022(119)
- July 2022(99)
- June 2022(128)
- May 2022(112)
- April 2022(108)
- March 2022(121)
- February 2022(93)
- January 2022(110)
- December 2021(92)
- November 2021(107)
- October 2021(101)
- September 2021(81)
- August 2021(74)
- July 2021(78)
- June 2021(92)
- May 2021(67)
- April 2021(79)
- March 2021(79)
- February 2021(58)
- January 2021(55)
- December 2020(56)
- November 2020(59)
- October 2020(78)
- September 2020(72)
- August 2020(64)
- July 2020(71)
- June 2020(74)
- May 2020(50)
- April 2020(71)
- March 2020(71)
- February 2020(58)
- January 2020(62)
- December 2019(57)
- November 2019(64)
- October 2019(25)
- September 2019(24)
- August 2019(14)
- July 2019(23)
- June 2019(54)
- May 2019(82)
- April 2019(76)
- March 2019(71)
- February 2019(67)
- January 2019(75)
- December 2018(44)
- November 2018(47)
- October 2018(74)
- September 2018(54)
- August 2018(61)
- July 2018(72)
- June 2018(62)
- May 2018(62)
- April 2018(73)
- March 2018(76)
- February 2018(8)
- January 2018(7)
- December 2017(6)
- November 2017(8)
- October 2017(3)
- September 2017(4)
- August 2017(4)
- July 2017(2)
- June 2017(5)
- May 2017(6)
- April 2017(11)
- March 2017(8)
- February 2017(16)
- January 2017(10)
- December 2016(12)
- November 2016(20)
- October 2016(7)
- September 2016(102)
- August 2016(168)
- July 2016(141)
- June 2016(149)
- May 2016(117)
- April 2016(59)
- March 2016(85)
- February 2016(153)
- December 2015(150)