WO2021203796A1 - Système de prédiction de pronostic de maladie basé sur une analyse de survie par apprentissage multitâche semi-supervisée profonde - Google Patents

Système de prédiction de pronostic de maladie basé sur une analyse de survie par apprentissage multitâche semi-supervisée profonde Download PDF

Info

Publication number
WO2021203796A1
WO2021203796A1 PCT/CN2021/073136 CN2021073136W WO2021203796A1 WO 2021203796 A1 WO2021203796 A1 WO 2021203796A1 CN 2021073136 W CN2021073136 W CN 2021073136W WO 2021203796 A1 WO2021203796 A1 WO 2021203796A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
loss
prediction
survival
model
Prior art date
Application number
PCT/CN2021/073136
Other languages
English (en)
Chinese (zh)
Inventor
李劲松
池胜强
田雨
周天舒
Original Assignee
之江实验室
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 之江实验室 filed Critical 之江实验室
Publication of WO2021203796A1 publication Critical patent/WO2021203796A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines

Definitions

  • the invention belongs to the technical field of medical treatment and machine learning, and in particular relates to a disease prognosis prediction system based on deep semi-supervised multi-task learning survival analysis.
  • Disease prognosis prediction analysis can provide clinicians with prognostic information for disease treatment, help formulate treatment plans, increase disease cure rate, improve patient prognostic quality of life, and effectively reduce disease burden, which is of great significance for disease control and treatment.
  • Survival analysis is a commonly used data analysis method in the prediction of disease prognosis, which is used to analyze and predict the time of occurrence of an event. In medicine, it plays a key role in determining the course of treatment, developing new drugs, preventing adverse drug reactions and improving hospital procedures.
  • deep neural networks, convolutional neural networks, long- and short-term memory networks and other deep learning network structures have begun to increase in the application of disease prognosis prediction.
  • some advanced machine learning strategies are gradually being applied to survival analysis methods based on deep learning, including active learning, transfer learning, and multi-task learning to improve the performance of disease prognosis prediction.
  • Censored data are common in disease prognosis data. Censored data are not missing data, but incomplete data that can only provide prognostic information from the beginning to the censored time, and cannot provide complete information from the beginning to the occurrence of the event.
  • Existing deep learning-based methods may not make full use of censored data; or in the case of making full use of censored data, they cannot effectively solve the time-dependent phenomenon of features; or the generalization ability of the model is insufficient; or the model is interpretable Poor sex.
  • the existing methods based on multi-task learning cannot make full use of censored data.
  • the purpose of the present invention is to provide a disease prognosis prediction system based on deep semi-supervised multi-task learning survival analysis in view of the deficiencies of the prior art.
  • the present invention is based on a deep neural network model, transforms the survival analysis problem into a multi-task learning model composed of a semi-supervised learning problem of multi-time sequence point survival probability prediction; considering the censored data and the non-increasing trend of survival probability in survival analysis, it is proposed to use
  • the semi-supervised loss function and the ranking loss function fit the data, and can deal with traditional survival analysis problems and survival analysis problems considering competitive risks.
  • it provides a method for evaluating the importance of features, and visualizes the time dependence and nonlinear effects of features.
  • the deep neural network structure in the model contains multiple layers of nonlinear transformation units, which can fit the nonlinear effects of features.
  • the model directly models survival probability, does not rely on proportional hazards assumptions, can fit time-dependent effects, and has better explanatory properties.
  • the model makes full use of complete data and censored data through logarithmic loss function and semi-supervised loss function; utilizes the non-increasing trend of survival probability through sorting loss function; realizes automatic feature selection and prevents model overfitting through L1 and L2 loss functions .
  • the model realizes data sharing between multiple prediction tasks through multi-task learning at multiple time sequence points, and realizes mutual constraints between multiple prediction tasks at the same time, and improves the generalization ability of the model.
  • a disease prognosis prediction system based on deep semi-supervised multi-task learning survival analysis including: a data acquisition module for acquiring disease prognosis data; A data preprocessing module for missing value processing and normalization processing; a prediction model building module for modeling disease prognosis data; a prediction result display module for displaying data prediction results; in the prediction model building module
  • a survival analysis method based on deep semi-supervised multi-task learning, the specific steps are as follows:
  • N is the number of samples and M is the number of features.
  • the input of the deep neural network is the feature X of the data set, the output label is Y, and each output layer corresponds to each of Y y, that is, each output layer corresponds to event prediction tasks at different times.
  • the deep neural network can make predictions for the same task at K different times.
  • the objective function of the prediction model is composed of five parts: log loss, L1 loss, L2 loss, semi-supervised loss and ranking loss:
  • the model uses the logarithmic loss to punish the wrong classification to measure the accuracy of the classifier.
  • the label be y, y ⁇ 0,1 ⁇ .
  • the parameter ⁇ is estimated by the maximum likelihood estimation method, and the likelihood function is:
  • l is the sample number label
  • p (X i; ⁇ ) is the posterior probability of the sample X i.
  • the event prediction at each time point is regarded as a multi-classification problem.
  • X i ; ⁇ ), where k 1, 2,...,C, and C is the number of all possible outcomes.
  • the parameter ⁇ is estimated by the maximum likelihood estimation method, and the corresponding log loss function is:
  • unlabeled data For unlabeled data, the use of unlabeled data is realized by adding an entropy-constrained regularization term to the objective function.
  • the event state is a random variable that obeys the Bernoulli distribution and the parameter is p. Its entropy is defined as follows:
  • u is the number of unlabeled samples
  • p is the probability of occurrence of the event. If the category of unlabeled data is determined, the entropy constraint regularization term will be small.
  • the non-increasing trend of survival probability is constrained by adding a ranking loss to the objective function.
  • the ranking loss is defined as follows:
  • p i,p (y i 1
  • X i ; ⁇ ) ⁇ pi ,q (y i 1
  • X i ; ⁇ ), Otherwise, a penalty will be imposed on the probability of occurrence of this pair of events; I(pi ,p (y i 1
  • X i ; ⁇ )>pi ,q (y i 1
  • X i ; ⁇ )) is the indicator function, When p i,p (y i 1
  • X i ; ⁇ )>pi ,q (y i 1
  • the semi-supervised multi-task survival analysis model based on deep learning that is, the objective function of the prediction model is:
  • l( ⁇ ) is the logarithmic loss
  • L1( ⁇ ) is the L1 loss
  • L2( ⁇ ) is the L2 loss
  • ⁇ ( ⁇ ) is the semi-supervised loss
  • R( ⁇ ) is the ranking loss
  • ⁇ 1 , ⁇ 2 , ⁇ 3 , ⁇ 4 are the parameters that control the strength of the regular term.
  • the step (2) transforms the original survival analysis problem into a multi-task learning problem through the process of converting the label information into a vector.
  • the hidden layer parameters in the deep neural network adopt a hard sharing mechanism, thereby reducing the risk of overfitting.
  • step (4) for the deep semi-supervised multi-task learning problem of survival analysis problem transition, there are two important features: unlabeled data caused by censoring and a non-increasing trend of survival probability.
  • semi-supervised learning is performed by using entropy-constrained regularization. Aiming at the non-increasing trend of survival probabilities at different time points, sorting loss is introduced to constrain the survival probabilities of different output layers.
  • L1 loss is introduced into the objective function to realize automatic feature selection, and L2 loss is introduced to avoid overfitting.
  • the prediction result display module is used for feature importance evaluation, and visually displays the time dependence and nonlinear effects of features.
  • the specific steps for calculating the importance of a feature F are as follows:
  • the prediction result display module visually displays the influence of the characteristics on the prognosis by drawing the predicted cumulative incidence curves corresponding to different characteristics. To draw the predicted cumulative incidence curve corresponding to a certain feature F, the specific steps are as follows:
  • All possible values of feature F are: x F,1 ,x F,2 ,...,x F,v ,...,x F,V , where V is the number of all possible values of feature F.
  • x i,o are the values of all the features except the feature F in the i-th data.
  • variable value range is divided into R equal divisions, and the values of all the cut points are used for cumulative incidence estimation and curve drawing, reducing the amount of calculation, R Determine according to the specific characteristic value range.
  • the present invention is based on a deep neural network model, and converts the survival analysis problem into a multi-task learning model composed of a semi-supervised learning problem of survival probability prediction at multiple time series points.
  • the deep neural network structure can fit the nonlinear effects of features.
  • the model directly models survival probability, does not rely on proportional hazards assumptions, can fit time-dependent effects, and has better explanatory properties.
  • the model realizes data sharing between multiple prediction tasks through multi-task learning at multiple time sequence points, and realizes mutual constraints between multiple prediction tasks at the same time, and improves the generalization ability of the model. At the same time, it provides a method for evaluating the importance of features, and visualizes the time dependence and nonlinear effects of features.
  • Figure 1 is a structural diagram of the disease prognosis prediction system based on deep semi-supervised multi-task learning survival analysis of the present invention
  • Figure 2 is a schematic diagram of data set label conversion
  • Figure 3 is a diagram of the neural network structure.
  • the censored data in this application is: If at the specified end time, the data without a result event is called censored data, and the time from the starting point to the censored is called censoring time.
  • the time-dependent phenomenon is: Regardless of the baseline risk, at any point in time, the risk of an event in an exposed individual relative to an exposed individual is constant; the phenomenon that does not meet the above assumptions is considered a characteristic pair The prognosis of the disease is time-dependent.
  • the risk of competition is: during the follow-up of the disease prognosis, the patient’s events other than the event of concern did not occur, that is, other events "competed” for the occurrence of the event of concern, and these events are called competitive risks; the competition risk is only Exist in the survival analysis problem where there are multiple end-point events, but only one end-point event will occur at any given time.
  • a disease prognosis prediction system based on deep semi-supervised multi-task learning survival analysis includes: a data acquisition module for acquiring disease prognosis data; and processing missing values for disease prognosis data And a normalized data preprocessing module; a prediction model building module for modeling disease prognosis data; a prediction result display module for visually displaying data prediction results; the prediction model building module uses
  • the survival analysis method of deep semi-supervised multi-task learning its realization principle is as follows:
  • N is the number of samples and M is the number of features.
  • An example of the transformation of data set labels is shown in Figure 2.
  • the label of the converted data set can be expressed as:
  • the original survival analysis problem is transformed into a multi-task learning problem.
  • the input of the deep neural network is the feature X of the data set
  • the output label is Y
  • each output layer corresponds to each y in Y, namely Each output layer corresponds to event prediction tasks at different times.
  • Figure 3 shows a deep neural network with K output layers. If the output k refers to the prediction of the task at time T k , then the network can make predictions for the same task at K different times.
  • the hidden layer parameters in the network adopt a hard sharing mechanism. The hard sharing mechanism reduces the risk of overfitting. Intuitively speaking, the more tasks learn at the same time, the more common features of the model can be captured by the model, so that the risk of overfitting on each task is smaller.
  • the model uses the logarithmic loss to punish the wrong classification to measure the accuracy of the classifier.
  • the label be y, y ⁇ 0,1 ⁇ .
  • the parameter ⁇ is estimated by the maximum likelihood estimation method, and the likelihood function is:
  • l is the sample number label
  • p (X i; ⁇ ) is the posterior probability of the sample X i.
  • L1 loss The definition of L1 loss is as follows:
  • L1 loss that is, adding the sum of the absolute values of all the weight parameters ⁇ to the objective function can make more ⁇ zero and realize automatic feature selection.
  • L2 loss The definition of L2 loss is as follows:
  • unlabeled data For unlabeled data, the use of unlabeled data can be realized by adding an entropy-constrained regularization term to the objective function.
  • the event state is a random variable that obeys the Bernoulli distribution and the parameter is p. Its entropy is defined as follows:
  • u is the number of unlabeled samples
  • p is the probability of occurrence of the event. If the category of unlabeled data is determined, the entropy constraint regularization term will be small.
  • the non-increasing trend of survival probability is constrained by adding a ranking loss to the objective function.
  • the ranking loss is defined as follows:
  • p i,p (y i 1
  • X i ; ⁇ ) ⁇ pi ,q (y i 1
  • X i ; ⁇ ), Otherwise, a penalty will be imposed on the probability of occurrence of this pair of events; I(pi ,p (y i 1
  • X i ; ⁇ )>pi ,q (y i 1
  • X i ; ⁇ )) is the indicator function, When p i,p (y i 1
  • X i ; ⁇ )>pi ,q (y i 1
  • the semi-supervised multi-task survival analysis model based on deep learning that is, the objective function of the prediction model is:
  • l( ⁇ ) is the logarithmic loss
  • L1( ⁇ ) is the L1 loss
  • L2( ⁇ ) is the L2 loss
  • ⁇ ( ⁇ ) is the semi-supervised loss
  • R( ⁇ ) is the ranking loss
  • ⁇ 1 , ⁇ 2 , ⁇ 3 , ⁇ 4 are the parameters that control the strength of the regular term.
  • All possible values of feature F are: x F,1 ,x F,2 ,...,x F,v ,...,x F,V , where V is the number of all possible values of feature F.
  • x i,o are the values of all the features except the feature F in the i-th data.
  • step 2) Combine what you got in step 2) Draw as a curve.
  • the value range of the variable can be divided into R equal parts, and the values of all cut points are used for cumulative incidence estimation and curve drawing to reduce the amount of calculation. R is usually determined according to the specific characteristic value range.
  • This application uses the deep neural network structure to fit the nonlinear effect of the data; according to the dimensionality of the input data, the length of the survival time, and the accuracy of the model, the deep neural network structure can be flexibly expanded; the model directly models the survival probability without relying on The proportional hazard hypothesis can fit the time-dependent effects of features and has better interpretability; through the logarithmic loss function and semi-supervised loss function, it makes full use of the complete data and censored data; through the ranking loss function, the survival probability is not used.
  • Incremental law through the L1 and L2 loss functions, automatic feature selection and prevention of model overfitting are realized; the model can realize data sharing between multiple prediction tasks through multi-task learning at multiple time series points, and between multiple prediction tasks at the same time
  • the model can deal with traditional survival analysis problems and survival analysis problems considering competitive risks; it provides a method for evaluating the importance of features based on deep learning models; and visualizes the prognostic effects of features Time dependence and non-linear effects.

Abstract

La présente invention concerne un système de prédiction de pronostic de maladie basé sur une analyse de survie par apprentissage multitâche semi-supervisée profonde, comprenant un module d'acquisition de données, un module de prétraitement de données et un module de construction de modèle de prédiction. Le système, en utilisant un modèle de réseau neuronal profond en tant que base, convertit un problème d'analyse de survie en modèle d'apprentissage multitâche composé d'un problème d'apprentissage semi-supervisé de prédiction de probabilité de survie à des temps de séquence multiples ; le modèle modélise directement une probabilité de survie, ne dépend pas d'une hypothèse de risque proportionnel, peut s'ajuster à un effet dépendant du temps, et présente une meilleure interprétabilité ; il est proposé qu'une fonction de perte semi-supervisée et une fonction de perte de tri soient utilisées pour ajuster les données, les données complètes et les données censées sont complètement utilisées, et les problèmes d'analyse de survie conventionnels et les problèmes d'analyse de survie compte tenu des risques de compétition peuvent être résolus ; selon le modèle, au moyen d'un apprentissage multitâche de temps de séquence multiples, un partage de données entre des tâches de prédiction multiples est obtenu, une contrainte mutuelle entre les tâches de prédiction multiples est obtenue, et la capacité de généralisation du modèle est améliorée.
PCT/CN2021/073136 2020-04-09 2021-01-21 Système de prédiction de pronostic de maladie basé sur une analyse de survie par apprentissage multitâche semi-supervisée profonde WO2021203796A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010273957.9 2020-04-09
CN202010273957.9A CN111640510A (zh) 2020-04-09 2020-04-09 一种基于深度半监督多任务学习生存分析的疾病预后预测系统

Publications (1)

Publication Number Publication Date
WO2021203796A1 true WO2021203796A1 (fr) 2021-10-14

Family

ID=72331086

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/073136 WO2021203796A1 (fr) 2020-04-09 2021-01-21 Système de prédiction de pronostic de maladie basé sur une analyse de survie par apprentissage multitâche semi-supervisée profonde

Country Status (2)

Country Link
CN (1) CN111640510A (fr)
WO (1) WO2021203796A1 (fr)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114141366A (zh) * 2021-12-31 2022-03-04 杭州电子科技大学 基于语音多任务学习的脑卒中康复评估辅助分析方法
CN114566289A (zh) * 2022-04-26 2022-05-31 之江实验室 一种基于多中心临床数据防作弊分析的疾病预测系统
CN114821337A (zh) * 2022-05-20 2022-07-29 武汉大学 基于时相一致性伪标签的半监督sar图像建筑区提取方法
CN115184054A (zh) * 2022-05-30 2022-10-14 深圳技术大学 机械设备半监督故障检测分析方法、装置、终端及介质
CN115458158A (zh) * 2022-09-23 2022-12-09 深圳大学 一种针对脓毒症患者的急性肾损伤预测系统
CN116072298A (zh) * 2023-04-06 2023-05-05 之江实验室 一种基于层级标记分布学习的疾病预测系统
CN116206755A (zh) * 2023-05-06 2023-06-02 之江实验室 一种基于神经主题模型的疾病检测与知识发现装置
CN116504423A (zh) * 2023-06-26 2023-07-28 北京大学 一种药物有效性评估方法
CN116564524A (zh) * 2023-06-30 2023-08-08 之江实验室 一种伪标签演变趋势正则的预后预测装置
CN116832285A (zh) * 2023-09-01 2023-10-03 吉林大学 基于云平台的呼吸机运行异常监测预警系统
CN116959715A (zh) * 2023-09-18 2023-10-27 之江实验室 一种基于时序演进过程解释的疾病预后预测系统
CN117558414A (zh) * 2023-11-23 2024-02-13 之江实验室 多任务肝细胞癌早期复发预测系统、电子设备、介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111640510A (zh) * 2020-04-09 2020-09-08 之江实验室 一种基于深度半监督多任务学习生存分析的疾病预后预测系统
TWI810510B (zh) * 2021-01-04 2023-08-01 鴻海精密工業股份有限公司 多模態資料處理方法及裝置、電子裝置及存儲介質
CN112819768B (zh) * 2021-01-26 2022-06-17 复旦大学 基于dcnn的癌症全视野数字病理切片生存分析方法
CN112906994B (zh) * 2021-04-19 2023-04-07 拉扎斯网络科技（上海）有限公司 订单出餐时间预测方法、装置、电子设备及存储介质
CN113314218B (zh) * 2021-06-22 2022-12-23 浙江大学 基于对比的包含竞争风险的动态生存分析设备
CN115620902A (zh) * 2021-07-15 2023-01-17 华为云计算技术有限公司 预测生存风险率的方法及装置
CN115565669B (zh) * 2022-10-11 2023-05-16 电子科技大学 一种基于gan和多任务学习的癌症生存分析方法
CN116403714B (zh) * 2023-04-07 2024-01-26 大连市中心医院 脑卒中end风险预测模型建立方法、装置、end风险预测系统、电子设备及介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897545A (zh) * 2017-01-05 2017-06-27 浙江大学 一种基于深度置信网络的肿瘤预后预测系统
CN107944479A (zh) * 2017-11-16 2018-04-20 哈尔滨工业大学 基于半监督学习的疾病预测模型建立方法及装置
CN108053398A (zh) * 2017-12-19 2018-05-18 南京信息工程大学 一种半监督特征学习的黑色素瘤自动检测方法
CN108564039A (zh) * 2018-04-16 2018-09-21 北京工业大学 一种基于半监督深层生成对抗网络的癫痫发作预测方法
CN110556178A (zh) * 2018-05-30 2019-12-10 西门子医疗有限公司 用于医学疗法规划的决策支持系统
CN110580695A (zh) * 2019-08-07 2019-12-17 深圳先进技术研究院 一种多模态三维医学影像融合方法、系统及电子设备
US10559386B1 (en) * 2019-04-02 2020-02-11 Kpn Innovations, Llc Methods and systems for an artificial intelligence support network for vibrant constituional guidance
CN111640510A (zh) * 2020-04-09 2020-09-08 之江实验室 一种基于深度半监督多任务学习生存分析的疾病预后预测系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897545A (zh) * 2017-01-05 2017-06-27 浙江大学 一种基于深度置信网络的肿瘤预后预测系统
CN107944479A (zh) * 2017-11-16 2018-04-20 哈尔滨工业大学 基于半监督学习的疾病预测模型建立方法及装置
CN108053398A (zh) * 2017-12-19 2018-05-18 南京信息工程大学 一种半监督特征学习的黑色素瘤自动检测方法
CN108564039A (zh) * 2018-04-16 2018-09-21 北京工业大学 一种基于半监督深层生成对抗网络的癫痫发作预测方法
CN110556178A (zh) * 2018-05-30 2019-12-10 西门子医疗有限公司 用于医学疗法规划的决策支持系统
US10559386B1 (en) * 2019-04-02 2020-02-11 Kpn Innovations, Llc Methods and systems for an artificial intelligence support network for vibrant constituional guidance
CN110580695A (zh) * 2019-08-07 2019-12-17 深圳先进技术研究院 一种多模态三维医学影像融合方法、系统及电子设备
CN111640510A (zh) * 2020-04-09 2020-09-08 之江实验室 一种基于深度半监督多任务学习生存分析的疾病预后预测系统

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
HASSANZADEH HAMID REZA; PHAN JOHN H.; WANG MAY D.: "A semi-supervised method for predicting cancer survival using incomplete clinical data", 2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), IEEE, 25 August 2015 (2015-08-25), pages 210 - 213, XP032810166, DOI: 10.1109/EMBC.2015.7318337 *
HOU LI, GUI WEI: "Research on infrared breast cancer detection method based on semi-supervised ladder network", INFORMATION TECHNOLOGY AND INFORMATIZATION - XINXI JISHU YU XINXIHUA, SHANDONG DIANZI XUEHUI, CN, no. 6, 25 June 2018 (2018-06-25), CN , pages 179 - 182, XP055856783, ISSN: 1672-9528, DOI: 10.3969/j.issn.1672-9528.2018.06.056 *
SHENGQIANG CHI: "Doctoral Dissertation", 25 April 2019, ZHEJIANG UNIVERSITY, CN, article SHENGQIANG CHI: "Study on Machine Learning-based Colorectal Cancer Prognosis Model and Its Generalization", pages: 1 - 122, XP055856778, DOI: 10.27461/d.cnki.gzjdx.2019.000967 *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114141366A (zh) * 2021-12-31 2022-03-04 杭州电子科技大学 基于语音多任务学习的脑卒中康复评估辅助分析方法
CN114141366B (zh) * 2021-12-31 2024-03-26 杭州电子科技大学 基于语音多任务学习的脑卒中康复评估辅助分析方法
CN114566289A (zh) * 2022-04-26 2022-05-31 之江实验室 一种基于多中心临床数据防作弊分析的疾病预测系统
CN114821337A (zh) * 2022-05-20 2022-07-29 武汉大学 基于时相一致性伪标签的半监督sar图像建筑区提取方法
CN114821337B (zh) * 2022-05-20 2024-04-16 武汉大学 基于时相一致性伪标签的半监督sar图像建筑区提取方法
CN115184054A (zh) * 2022-05-30 2022-10-14 深圳技术大学 机械设备半监督故障检测分析方法、装置、终端及介质
CN115184054B (zh) * 2022-05-30 2022-12-27 深圳技术大学 机械设备半监督故障检测分析方法、装置、终端及介质
CN115458158A (zh) * 2022-09-23 2022-12-09 深圳大学 一种针对脓毒症患者的急性肾损伤预测系统
CN115458158B (zh) * 2022-09-23 2023-09-15 深圳大学 一种针对脓毒症患者的急性肾损伤预测系统
CN116072298B (zh) * 2023-04-06 2023-08-15 之江实验室 一种基于层级标记分布学习的疾病预测系统
CN116072298A (zh) * 2023-04-06 2023-05-05 之江实验室 一种基于层级标记分布学习的疾病预测系统
CN116206755B (zh) * 2023-05-06 2023-08-22 之江实验室 一种基于神经主题模型的疾病检测与知识发现装置
CN116206755A (zh) * 2023-05-06 2023-06-02 之江实验室 一种基于神经主题模型的疾病检测与知识发现装置
CN116504423A (zh) * 2023-06-26 2023-07-28 北京大学 一种药物有效性评估方法
CN116504423B (zh) * 2023-06-26 2023-09-26 北京大学 一种药物有效性评估方法
CN116564524A (zh) * 2023-06-30 2023-08-08 之江实验室 一种伪标签演变趋势正则的预后预测装置
CN116564524B (zh) * 2023-06-30 2023-10-03 之江实验室 一种伪标签演变趋势正则的预后预测装置
CN116832285A (zh) * 2023-09-01 2023-10-03 吉林大学 基于云平台的呼吸机运行异常监测预警系统
CN116832285B (zh) * 2023-09-01 2023-11-07 吉林大学 基于云平台的呼吸机运行异常监测预警系统
CN116959715A (zh) * 2023-09-18 2023-10-27 之江实验室 一种基于时序演进过程解释的疾病预后预测系统
CN116959715B (zh) * 2023-09-18 2024-01-09 之江实验室 一种基于时序演进过程解释的疾病预后预测系统
CN117558414A (zh) * 2023-11-23 2024-02-13 之江实验室 多任务肝细胞癌早期复发预测系统、电子设备、介质

Also Published As

Publication number Publication date
CN111640510A (zh) 2020-09-08

Similar Documents

Publication Publication Date Title
WO2021203796A1 (fr) Système de prédiction de pronostic de maladie basé sur une analyse de survie par apprentissage multitâche semi-supervisée profonde
WO2022160902A1 (fr) Procédé de détection d'anomalies pour données en séries chronologiques multivariées à grande échelle dans un environnement en nuage
Jiang et al. Modified genetic algorithm-based feature selection combined with pre-trained deep neural network for demand forecasting in outpatient department
CN109659033B (zh) 一种基于循环神经网络的慢性疾病病情变化事件预测装置
CN113040711B (zh) 一种脑卒中发病风险预测系统、设备、存储介质
Sisodia et al. Stock market analysis and prediction for NIFTY50 using LSTM Deep Learning Approach
CN111144542A (zh) 油井产能预测方法、装置和设备
CN113486578B (zh) 一种工业过程中设备剩余寿命的预测方法
Farbmacher et al. An explainable attention network for fraud detection in claims management
CN111626785A (zh) 一种基于结合注意力的cnn-lstm网络基金价格预测方法
Jiang et al. A hybrid intelligent model for acute hypotensive episode prediction with large-scale data
CN116340796B (zh) 时序数据分析方法、装置、设备及存储介质
Li et al. Multi-task spatio-temporal augmented net for industry equipment remaining useful life prediction
Liu et al. An explainable knowledge distillation method with XGBoost for ICU mortality prediction
US11847389B2 (en) Device and method for optimizing an input parameter in a processing of a semiconductor
Wang et al. Time-series forecasting of mortality rates using transformer
US20220405640A1 (en) Learning apparatus, classification apparatus, learning method, classification method and program
CN115565669A (zh) 一种基于gan和多任务学习的癌症生存分析方法
CN115660871A (zh) 医学临床过程无监督建模方法、计算机设备、存储介质
CN114529063A (zh) 一种基于机器学习的金融领域数据预测方法、设备及介质
Guan et al. A new hybrid deep learning model for monthly oil prices forecasting
Lv et al. Multi-feature generation network-based imputation method for industrial data with high missing rate
Alshenawy et al. A COMPARATIVE STUDY OF STATISTICAL AND INTELLIGENT CLASSIFICATION MODELS FOR PREDICTING DIABETES
Tu et al. A novel grey relational clustering model under sequential three-way decision framework
TWM590743U (zh) 核保風險評估系統

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21784817

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21784817

Country of ref document: EP

Kind code of ref document: A1