Aiming at the problem that the small samples of critical disease in clinic may lead to prognostic models with poor performance of overfitting, large prediction error and instability, the long short-term memory transferring algorithm (transLSTM) was proposed. Based on the idea of transfer learning, the algorithm leverages the correlation between diseases to transfer information of different disease prognostic models, constructs the effictive model of target disease of small samples with the aid of large data of related diseases, hence improves the prediction performance and reduces the requirement for target training sample quantity. The transLSTM algorithm firstly uses the related disease samples to pretrain partial model parameters, and then further adjusts the whole network with the target training samples. The testing results on MIMIC-Ⅲ database showed that compared with traditional LSTM classification algorithm, the transLSTM algorithm had 0.02-0.07 higher AUROC and 0.05-0.14 larger AUPRC, while its number of training iterations was only 39%-64% of the traditional algorithm. The results of application on sepsis revealed that the transLSTM model of only 100 training samples had comparable mortality prediction performance to the traditional model of 250 training samples. In small sample situations, the transLSTM algorithm has significant advantages with higher prediciton accuracy and faster training speed. It realizes the application of transfer learning in the prognostic model of critical disease with small samples.
Objective To compare the similarities and differences in the policy frameworks of outpatient chronic diseases and special critical diseases of urban employed basic medical insurance across 22 regions (including the provincial-level region) in Sichuan Province, and provide reference for promoting unified planning of basic medical insurance at the provincial level. Methods Policy documents and relevant materials related to outpatient chronic diseases and special critical diseases which were released as of December 31, 2024 were retrieved from the official websites of the Sichuan Provincial Medical Security Administration and those regions. A structured database was constructed, and content analysis was employed to compare regional policy variations in terms of disease coverage, identification and management criteria, and benefit levels. Results Considerable disparities were observed across regions in insured disease scope, identification management and benefit levels. The number of insured diseases ranged from 37 to 66, with a range of 29. While 14 diseases were covered by all regions, the identification criteria for the same diseases were inconsistent. Moreover, the deductible standards, reimbursement ratios, and reimbursement cap lines varied among regions. The deductible standards ranged from 0 to 1000 yuan, the reimbursement ratios ranged from 50% to 100%, and the cap lines ranged from 800 to 36000 yuan. Conclusions There are pronounced regional disparities in the benefit levels for outpatient chronic diseases and special critical diseases under Sichuan Province’s urban employed basic medical insurance scheme, raising concerns regarding horizontal equity. Given that benefit levels are influenced by regional economic development and the financial levels of insurance funds, it is recommended to gradually standardize the disease list and identification criteria at the provincial level, and to develop appropriate benefit policies to narrow regional gaps.