Progress profile prediction

• Main Authors: MOSINSKA DOMANSKA AGATA JUSTINA, DE ZANETTE SANDRO IVO SEBASTIANO, SILLER RUIZ CARLOS, APOSTOLOPOULOS, STEFANOS
• Format: Patent
• Language: Chinese; English
• Published: 31.05.2024
• Subjects: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

A method of predicting progression of a condition includes obtaining measurement data relating to at least one measurement up to a particular point in time for a subject, where the data is generated based on an output of a sensor configured to perform the at least one measurement with respect to the subject. At least one parameter of a parameterized time correlation function is generated using the trained model and based on the measurement data, where the parameterized time correlation function depends on consecutive time values, where the parameterized time correlation function indicates a predicted progression of the condition of the subject over time after a particular point in time. For at least one point in time after the particular point in time, at least one parameter is used to evaluate the parameterized time correlation function. 一种预测病情的进展的方法，包括获得与针对受试者的直到特定时间点的至少一次测量有关的测量数据，其中数据基于传感器的输出而被生成，传感器被配置为执行关于受试者的至少一次测量。使用经训练的模型并基于测量数据生成参数化时间相关函数的至少一个参数，其中参数化时间相关函数取决于连续的时间值，其中参数化时间相关函数指示在特定时间点之后受试者的病情随时间的预测