Intelligence – based decision support system for diagnosing the incidence of hypertensive type

What are the perspectives of patients with hand and wrist conditions, chronic pain, and patients recovering from stroke on the use of patient and outcome information in everyday care? A Mixed-Methods study

PURPOSE

To evaluate the patients' perspectives on the use of patient- and outcome information tools in everyday care and to investigate which characteristics affect general understanding and perceived value of patient- and outcome information.

METHODS

This mixed-methods study included surveys and interviews on understanding, experience, decision-support, and perceived value in patients with hand and wrist conditions and chronic pain. We synthesized our quantitative and qualitative findings using a triangulation protocol and identified factors independently associated with general understanding and perceived value of patient- and outcome information using hierarchical logistic regression.

RESULTS

We included 3379 patients. The data triangulation indicated that patients understand the outcome information, they find it valuable, it supports decision-making, and it improves patient-clinician interaction. The following variables were independently associated with better general understanding: having more difficulty with questionnaires (standardized odds ratio 0.34 [95%-CI 031-0.38]), having a finger condition (0.72 [0.57-0.92]), longer follow-up (0.75 [0.61-0.91]), and undergoing surgical treatment (ref: non-surgical treatment, 1.33 [1.11-1.59]). For more general value, these were: having more difficulty with questionnaires (0.40 [0.36-0.44]), having a wrist condition (0.71 [0.54-0.92]), better hand function (1.12 [1.02-1.22]), and requiring help with questionnaires (1.65 [1.33-2.05]).

CONCLUSION

Patients value the use of patient- and outcome information tools in daily care and find it easy to understand. The factors associated with understanding and value can be targeted to personalized and value-based healthcare. We recommend using outcome information to improve patient independence, empowerment, and involvement in decision-making.

Remote classroom action recognition based on improved neural network and face recognition

In recent years, the field of computer vision is promoted by the development of intelligent technology and computer technology, and has made breakthrough progress. Intelligent hardware technology and computer technology lay the foundation for the development of computer vision field. At the same time, the continuous improvement and development of artificial intelligence technology has also promoted the rapid development of educational video system, and the video tracking of educational video system has made breakthrough progress. By fully using intelligent hardware and computer technology, and combining with artificial intelligence technology, the video tracking and recognition technology of educational video system has been further developed, and new recognition algorithm has been adopted. The accuracy of tracking recognition is greatly improved, which can accurately identify the action of the characters. At the same time, through the use of new action recognition algorithm, not only improve the accuracy of educational video recognition, but also improve the speed of recognition, which can accurately capture the changes of people’s behavior in the classroom. The time consumed by the action recognition algorithm is very short, and the speed of the algorithm is very high. This new algorithm greatly improves the efficiency of the education recording and broadcasting system, and improves the accuracy and accuracy of the education recording and broadcasting system. This paper studies a set of intelligent image recognition system for students’ classroom behavior. It compiles and explains the intelligent system software systematically. The operation of this system is no single. It operates through the joint operation of many modules. It can realize online distributed homework, accurately and quickly identify students’ classroom behavior, and can also help students to identify their classroom behavior accurately and quickly. The classroom behavior of the accurate analysis of students’ incorrect classroom behavior to make timely reminders, greatly improve the efficiency of the classroom, improve the degree of concentration of students. In this paper, many classroom behaviors are simulated, and the performance of this software platform is predicted through many experiments.