Specialist hybrid models with asymmetric training for malaria prevalence prediction.
Specialist hybrid models with asymmetric training for malaria prevalence prediction.
复制标题
DOI：
10.3389/fpubh.2023.1207624
复制
发表时间：
2023
影响因子：
5.2
通讯作者：
Fernandez-Reyes, Delmiro
中科院分区：
文献类型：
--
作者：
Fisher, Thomas;Rojas-Galeano, Sergio;Fernandez-Reyes, Delmiro
关键词：
疟疾是一种普遍且严重的疾病，主要影响发展中国家，其传播受到各种环境和人类行为因素的影响。因此，准确的普遍性预测已被确定为2016年至2030年疟疾全球技术策略的关键组成部分。虽然传统的微分方程模型可以执行基本的预测，监督的机器学习算法提供了更准确的预测，如最近的一项使用弹性网络模型（REMPS）的研究所证明的那样。然而，当前的短期预测系统并未达到常规临床实践所需的准确性水平。为了朝这个方向提高，已经提出了堆叠的混合模型，其中通过使用元学习预测模型来汇总几个机器学习模型的输出。在本文中，我们提出了一种替代专家混合方法，该方法结合了一个线性预测模型，该模型专门研究疟疾患病率信号的线性成分和一个专门研究线性预测的非线性残差的复发性神经网络预测模型，该模型训练有新的不对称损失。我们的发现表明，专业混合动力方法的表现优于当前最新的堆叠模型，该模型包含来自尼日利亚西南部伊巴丹市的22年疟疾患病率数据。专业混合方法是当前预测方法的有前途的替代方法，也是改善高风险国家疟疾控制的决策和资源分配的工具。
Malaria is a common and serious disease that primarily affects developing countries and its spread is influenced by a variety of environmental and human behavioral factors; therefore, accurate prevalence prediction has been identified as a critical component of the Global Technical Strategy for Malaria from 2016 to 2030. While traditional differential equation models can perform basic forecasting, supervised machine learning algorithms provide more accurate predictions, as demonstrated by a recent study using an elastic net model (REMPS). Nevertheless, current short-term prediction systems do not achieve the required accuracy levels for routine clinical practice. To improve in this direction, stacked hybrid models have been proposed, in which the outputs of several machine learning models are aggregated by using a meta-learner predictive model. In this paper, we propose an alternative specialist hybrid approach that combines a linear predictive model that specializes in the linear component of the malaria prevalence signal and a recurrent neural network predictive model that specializes in the non-linear residuals of the linear prediction, trained with a novel asymmetric loss. Our findings show that the specialist hybrid approach outperforms the current state-of-the-art stacked models on an open-source dataset containing 22 years of malaria prevalence data from the city of Ibadan in southwest Nigeria. The specialist hybrid approach is a promising alternative to current prediction methods, as well as a tool to improve decision-making and resource allocation for malaria control in high-risk countries.
登录
查看更多内容
影响因子：
5.2
作者：
Martineau, Patrick;Behera, Swadhin K. K.;Nonaka, Masami;Jayanthi, Ratnam;Ikeda, Takayoshi;Minakawa, Noboru;Kruger, Philip;Mabunda, Qavanisi E. E.
通讯作者：
Mabunda, Qavanisi E. E.
影响因子：
4.6
作者：
Brown BJ;Manescu P;Przybylski AA;Caccioli F;Oyinloye G;Elmi M;Shaw MJ;Pawar V;Claveau R;Shawe-Taylor J;Srinivasan MA;Afolabi NK;Rees G;Orimadegun AE;Ajetunmobi WA;Akinkunmi F;Kowobari O;Osinusi K;Akinbami FO;Omokhodion S;Shokunbi WA;Lagunju I;Sodeinde O;Fernandez-Reyes D
通讯作者：
Fernandez-Reyes D
影响因子：
7.9
作者：
Makridakis, Spyros;Spiliotis, Evangelos;Assimakopoulos, Vassilios
通讯作者：
Assimakopoulos, Vassilios
影响因子：
3
作者：
BOZDOGAN, H
通讯作者：
BOZDOGAN, H
影响因子：
7.9
作者：
Smyl, Slawek
通讯作者：
Smyl, Slawek