A hybrid of long short-term memory neural network and autoregressive integrated moving average model in forecasting HIV incidence and morality of post-neonatal population in East Asia: global burden of diseases 2000–2019

Abstract

Background To forecast the human immunodeficiency virus (HIV) incidence and mortality of post-neonatal population in East Asia including North Korea, South Korea, Mongolia, Japan and China Mainland and Taiwan province. Methods The data on the incidence and mortality of HIV in post-neonatal population from East Asia were obtained from the Global Burden of Diseases (GBD). The morbidity and mortality of post-neonatal HIV population from GBD 2000 to GBD 2013 were applied as the training set and the morbidity and mortality from GBD 2014 to GBD 2019 were used as the testing set. The hybrid of ARIMA and LSTM model was used to construct the model for assessing the morbidity and mortality in the countries and territories of East Asia, and predicting the morbidity and mortality in the next 5 years. Results In North Korea, the incidence and mortality of HIV showed a rapid increase during 2000–2010 and a gradual decrease during 2010–2019. The incidence of HIV was predicted to be increased and the mortality was decreased. In South Korea, the incidence was increased during 2000–2010 and decreased during 2010–2019, while the mortality showed fluctuant trend. As predicted, the incidence of HIV in South Korea might be increased and the mortality might be decreased during 2020–2025. In Mongolia, the incidence and mortality were slowly decreased during 2000–2005, increased during 2005–2015, and rapidly decreased till 2019. The predicted incidence and mortality of HIV showed a decreased trend. As for Japan, the incidence of HIV was rapidly increased till 2010 and then decreased till 2015. The predicted incidence of HIV in Japan was gradually increased. The mortality of HIV in Japan was fluctuant during 2000–2019 and was slowly decreased as predicted. The incidence and mortality of HIV in Taiwan during 2000–2019 was increased on the whole. The predicted incidence of HIV during was stationary and the mortality was decreased. In terms of China Mainland, the incidence and mortality of HIV was fluctuant during 2000–2019. The predicted incidence of HIV in China Mainland was stationary while the mortality was rapidly decreased. Conclusion On the whole, the incidence of HIV combined with other diseases in post-neonatal population was increased before 2010 and then decreased during 2010–2019 while the mortality of those patients was decreased in East Asia.

The predictive accuracy of machine learning for the risk of death in HIV patients: a systematic review and meta-analysis

“…We reviewed 24 studies(Table 1 ), encompassing a total of 401,389 individuals living with HIV. These studies were conducted in various countries and regions, including 7 from the United States [ 15 , 18 , 19 , 21 , 24 , 25 , 28 ], 10 from China [ 7 – 11 , 13 , 14 , 16 , 20 , 23 ], and the rest from Spain [ 12 ], Mozambique [ 17 ], Germany [ 22 ], Congo [ 26 ], Uganda [ 27 ], Switzerland [ 29 ], and Canada [ 30 ].…”

“…These studies comprised 22 cohort studies [ 31 – 52 ]and 2 nested case-control studies [ 7 – 30 ]. In terms of patient sources, 15 studies originated from multicenter sources [ 31 , 33 – 35 , 37 , 39 , 40 , 42 , 44 – 48 , 50 , 51 , 53 ], 2 were drawn from a registered database [ 13 , 18 ], and 7 were conducted at single centers [ 8 , 10 , 15 , 20 , 23 , 27 , 30 ]. In a follow-up report, one study specifically focused on in-hospital deaths resulting from the combination of Talaromyces marneffei and HIV infection [ 8 ], while the remaining studies reported deaths during long-term follow-up, with the longest follow-up period extending to 36 years [ 7 ].…”

“…In statistical analysis, most non-survival analysis studies meet the criterion of EPV ≥ 20, and a sample size of an independent validation set ≥ 100 indicates low bias. However, survival analysis studies using COX regression and the Fine & Gray model (FGR) do not establish independent external validation [ 9 , 13 , 18 , 21 , 22 , 28 , 29 ]. In some studies, the rarity of cases makes it challenging to meet the conditions of EPV > 20 or an independent validation sample size > 100, leading to high bias [ 7 , 10 – 12 , 14 , 16 , 17 , 24 , 26 ] (Fig.…”