CN110689963A - 基于深度学习的分析食物营养成分的慢性病风险预测方法 - Google Patents

基于深度学习的分析食物营养成分的慢性病风险预测方法 Download PDF

Info

Publication number
CN110689963A
CN110689963A CN201910729329.4A CN201910729329A CN110689963A CN 110689963 A CN110689963 A CN 110689963A CN 201910729329 A CN201910729329 A CN 201910729329A CN 110689963 A CN110689963 A CN 110689963A
Authority
CN
China
Prior art keywords
nutrient components
risk prediction
labels
neurons
input layer
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN201910729329.4A
Other languages
English (en)
Inventor
刘昱
李时杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
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 Tianjin University filed Critical Tianjin University
Priority to CN201910729329.4A priority Critical patent/CN110689963A/zh
Publication of CN110689963A publication Critical patent/CN110689963A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/60ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Epidemiology (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Nutrition Science (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本发明公开了一种基于深度学***台搭建一个含有隐藏层的神经网络,将大量标签放入神经网络之中,经过训练得到营养成分对慢性病的风险预测结果。本发明能够提醒用户饮食对慢性病的直面影响,有效及时修改饮食计划,保障身心健康。

Description

基于深度学习的分析食物营养成分的慢性病风险预测方法
技术领域
本发明涉及移动医疗信息化平台领域、机器学习等领域,特别涉及一种基于深度学习的分析食物营养成分的慢性病风险预测方法。
背景技术
机器学习是在近20多年逐渐兴起的一门多领域交叉学科,涉及概率论、统计学、逼近论、凸分析、算法复杂度理论等多门学科。机器学习理论主要是设计、分析一些让计算机可以自动进行“学习”过程的算法,也就是说从数据中自动分析获得其中隐含的规律,并利用该规律对未知数据进行分析预测或判别的算法。它是人工智能的核心,是使计算机具有智能的根本途径,其应用遍及人工智能的各个领域,并在其他领域的数据处理和分析问题上应用广泛。
进入21世纪,生命科学特别是基因科技已经广泛而且深刻影响到每个人的健康生活,于此同时,科学家们借助基因科技史无前例的用一种全新的视角解读生命和探究疾病本质。人工智能(AI)能够处理分析海量医疗健康数据,通过认知分析获取洞察,服务于政府、健康医疗机构、制药企业及患者,实现个性化,可以循证的智慧医疗,推动创新,实现价值。
发明内容
基于上述技术背景,本发明提出了一种基于深度学习的分析食物营养成分的慢性病风险预测方法,利用摄入营养成分与患病情况结合的用户样本,经过神经网络进行训练得到营养成分对慢性病的风险预测结果。
本发明的一种基于深度学习的分析食物营养成分的慢性病风险预测方法,该方法包括以下步骤:
步骤1、用户记录日常饮食的饮食摄入信息以及患病情况,对有关用户的不同患病情况分别做不同的标记;
步骤2、通过食材营养数据库、菜肴营养数据库两个数据库,将步骤1中获得的饮食摄入数据转化为分析所需要的26种营养成分数据,并且将转化得到的营养成分数据与用户的患病情况做一一对应形成标签;
步骤3、重复上述步骤,获得多组用户的有关26种营养成分数据与患病情况对应的标签;
步骤4、对得到的标签使用残差分析的方法,剔除对患病无影响或影响不大的营养成分,从而形成新的标签;
步骤5、利用Keras平台搭建一个含有隐藏层的神经网络,含有一个输入层、两个隐藏层、一个输出层的26-52-52-2神经元结构;输入为26种营养成分为26维,所以输入层设置26个神经元;2个隐藏层神经元个数分别设置为输入层的2倍为52个神经元,输出层设置为2个神经元;
将大量标签放入神经网络之中,经过多次训练,得到营养成分对慢性病的风险预测结果。
与现有技术相比,本发明具有以下优点:
本发明能够提醒用户饮食对慢性病的直面影响,有效及时修改饮食计划,保障身心健康。
附图说明
图1为本发明的一种基于深度学习的分析食物营养成分的慢性病风险预测方法的流程图;
图2为深度神经网络结构示意图。
具体实施方式
下面结合附图和实施例对本发明技术方案进行详细描述。
本发明的整体思路是采用基于互联网智能手机终端结合深度学习技术,实现食物营养成分对慢性病的风险预测,符合营养科学的科学规律。
如图1所示,为本发明的一种基于深度学习的分析食物营养成分的慢性病风险预测方法流程图,该流程包括以下步骤:
步骤1、用户通过智能手机记录日常饮食的饮食摄入信息以及自己的患病情况,饮食摄入数据包括食材或者菜肴的名称以及具体用量,有关用户的不同患病情况以不同的数字做标记;
步骤2、通过食材营养数据库、菜肴营养数据库两个数据库,将步骤1中获得的饮食摄入数据转化为分析所需要的26种营养成分数据,并且将转化得到的营养成分数据与用户的患病情况做一一对应形成标签;
步骤3、重复上述步骤,获得大量用户的(至少1000个)有关26种营养成分数据与患病情况对应的标签;
步骤4、对得到的标签使用残差分析的方法,剔除对患病无影响或影响不大的营养成分,从而形成新的标签;
步骤5、利用Keras平台搭建一个深度神经网络(DNN),含有一个输入层、两个隐藏层、一个输出层的26-52-52-2神经元结构;输入为26种营养成分为26维,所以输入层设置26个神经元;2个隐藏层神经元个数分别设置为输入层的2倍为52个神经元,输出层设置为2个神经元,深度神经网络结构如图2所示。随后将大量标签放入神经网络之中,经过多次训练,得到每个人的营养成分对慢性病的风险预测结果。

Claims (1)

1.一种基于深度学习的分析食物营养成分的慢性病风险预测方法,其特征在于:该方法包括以下步骤:
步骤1、用户记录日常饮食的饮食摄入信息以及患病情况,对有关用户的不同患病情况分别做不同的标记;
步骤2、通过食材营养数据库、菜肴营养数据库两个数据库,将步骤1中获得的饮食摄入数据转化为分析所需要的26种营养成分数据,并且将转化得到的营养成分数据与用户的患病情况做一一对应形成标签;
步骤3、重复上述步骤,获得多组用户的有关26种营养成分数据与患病情况对应的标签;
步骤4、对得到的标签使用残差分析的方法,剔除对患病无影响或影响不大的营养成分,从而形成新的标签;
步骤5、利用Keras平台搭建一个含有隐藏层的神经网络,含有一个输入层、两个隐藏层、一个输出层的26-52-52-2神经元结构;输入为26种营养成分为26维,所以输入层设置26个神经元;2个隐藏层神经元个数分别设置为输入层的2倍为52个神经元,输出层设置为2个神经元;
将大量标签放入神经网络之中,经过多次训练,得到营养成分对慢性病的风险预测结果。
CN201910729329.4A 2019-08-08 2019-08-08 基于深度学习的分析食物营养成分的慢性病风险预测方法 Pending CN110689963A (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910729329.4A CN110689963A (zh) 2019-08-08 2019-08-08 基于深度学习的分析食物营养成分的慢性病风险预测方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910729329.4A CN110689963A (zh) 2019-08-08 2019-08-08 基于深度学习的分析食物营养成分的慢性病风险预测方法

Publications (1)

Publication Number Publication Date
CN110689963A true CN110689963A (zh) 2020-01-14

Family

ID=69108237

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910729329.4A Pending CN110689963A (zh) 2019-08-08 2019-08-08 基于深度学习的分析食物营养成分的慢性病风险预测方法

Country Status (1)

Country Link
CN (1) CN110689963A (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113539427A (zh) * 2020-04-22 2021-10-22 深圳市前海高新国际医疗管理有限公司 基于卷积神经网络的营养干预分析***及分析方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070106129A1 (en) * 2005-11-07 2007-05-10 Cardiac Pacemakers, Inc. Dietary monitoring system for comprehensive patient management
CN101772769A (zh) * 2007-08-02 2010-07-07 诺沃-诺迪斯克有限公司 用于辅助胰岛素给药的营养参数估计
CN107680652A (zh) * 2017-09-13 2018-02-09 天津大学 一种基于机器学习的营养饮食推荐及评价方法
CN107742533A (zh) * 2017-09-13 2018-02-27 天津大学 一种基于食物营养素预测痛风的方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070106129A1 (en) * 2005-11-07 2007-05-10 Cardiac Pacemakers, Inc. Dietary monitoring system for comprehensive patient management
CN101772769A (zh) * 2007-08-02 2010-07-07 诺沃-诺迪斯克有限公司 用于辅助胰岛素给药的营养参数估计
CN107680652A (zh) * 2017-09-13 2018-02-09 天津大学 一种基于机器学习的营养饮食推荐及评价方法
CN107742533A (zh) * 2017-09-13 2018-02-27 天津大学 一种基于食物营养素预测痛风的方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
M. CHEN等: "Disease prediction by machine learning over big data from healthcare communities" *
刘玥主编, 电子科技大学出版社 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113539427A (zh) * 2020-04-22 2021-10-22 深圳市前海高新国际医疗管理有限公司 基于卷积神经网络的营养干预分析***及分析方法

Similar Documents

Publication Publication Date Title
Barnard et al. Applications of multiple imputation in medical studies: from AIDS to NHANES
Lilhore et al. Enhanced convolutional neural network model for cassava leaf disease identification and classification
Chakradar et al. A non-invasive approach to identify insulin resistance with triglycerides and HDL-c ratio using machine learning
Wang et al. Deep learning in systems medicine
Kaur et al. Deep neural network for food image classification and nutrient identification: A systematic review
Chhabra et al. A hybrid deep learning approach for automatic fish classification
Mohammedqasim et al. Real-time data of COVID-19 detection with IoT sensor tracking using artificial neural network
Kaushik et al. Ensemble of multi-headed machine learning architectures for time-series forecasting of healthcare expenditures
Ispirova et al. P-nut: Predicting nutrient content from short text descriptions
Abdulrahman et al. A novel approach for emotion recognition based on EEG signal using deep learning
Li et al. Dietary nutritional information autonomous perception method based on machine vision in smart homes
CN110689963A (zh) 基于深度学习的分析食物营养成分的慢性病风险预测方法
Klüver Steering clustering of medical data in a self-enforcing network (SEN) with a cue validity factor
Pigni et al. Digital twins: Representing the future
Alshamrani et al. Investigation of hepatitis disease diagnosis using different types of neural network algorithms
Seitanidis et al. Identification of heart arrhythmias by utilizing a deep learning approach of the ECG signals on edge devices
Liu et al. An automatic ECG signal quality assessment method based on resnet and self-attention
Oh et al. Detecting events of daily living using multimodal data
Bizzego et al. Improving the efficacy of deep-learning models for heart beat detection on heterogeneous datasets
Tanaka AI-Driven Clinical Trials Optimization for Accelerated Drug Development
Rekha Sivakumar et al. Deep Neural Artificial Intelligence for IoT Based Tele Health Data Analytics.
Jérémie et al. Ultrafast image categorization in biology and neural models
Fisher et al. Deep learning for comprehensive forecasting of Alzheimer's Disease progression
Kaushik et al. Evaluating single-and multi-headed neural architectures for time-series forecasting of healthcare expenditures
Nesari Artificial intelligence in the sector of Ayurveda: Scope and opportunities

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200114

WD01 Invention patent application deemed withdrawn after publication