Semi-supervised Double Deep Learning Temporal Risk Prediction (SeDDLeR) with Electronic Health Records.

BACKGROUND: Risk prediction plays a crucial role in planning for prevention, monitoring, and treatment. Electronic Health Records (EHRs) offer an expansive repository of temporal medical data encompassing both risk factors and outcome indicators essential for effective risk prediction. However, challenges emerge due to the lack of readily available gold-standard outcomes and the complex effects of various risk factors. Compounding these challenges are the false positives in diagnosis codes, and formidable task of pinpointing the onset timing in annotations. OBJECTIVE: We develop a Semi-supervised Double Deep Learning Temporal Risk Prediction (SeDDLeR) algorithm based on extensive unlabeled longitudinal Electronic Health Records (EHR) data augmented by a limited set of gold standard labels on the binary status information indicating whether the clinical event of interest occurred during the follow-up period. METHODS: The SeDDLeR algorithm calculates an individualized risk of developing future clinical events over time using each patient's baseline EHR features via the following steps: (1) construction of an initial EHR-derived surrogate as a proxy for the onset status; (2) deep learning calibration of the surrogate along gold-standard onset status; and (3) semi-supervised deep learning for risk prediction combining calibrated surrogates and gold-standard onset status. To account for missing onset time and heterogeneous follow-up, we introduce temporal kernel weighting. We devise a Gated Recurrent Units (GRUs) module to capture temporal characteristics. We subsequently assess our proposed SeDDLeR method in simulation studies and apply the method to the Massachusetts General Brigham (MGB) Biobank to predict type 2 diabetes (T2D) risk. RESULTS: SeDDLeR outperforms benchmark risk prediction methods, including Semi-parametric Transformation Model (STM) and DeepHit, with consistently best accuracy across experiments. SeDDLeR achieved the best C-statistics ( 0.815, SE 0.023; vs STM +.084, SE 0.030, P-value .004; vs DeepHit +.055, SE 0.027, P-value .024) and best average time-specific AUC (0.778, SE 0.022; vs STM + 0.059, SE 0.039, P-value .067; vs DeepHit + 0.168, SE 0.032, P-value <0.001) in the MGB T2D study. CONCLUSION: SeDDLeR can train robust risk prediction models in both real-world EHR and synthetic datasets with minimal requirements of labeling event times. It holds the potential to be incorporated for future clinical trial recruitment or clinical decision-making.

The effects of social comparison and depressive mood on adolescent social decision-making.

BACKGROUND: Based on social comparison theory, two experiments were conducted to explore the effects of depression and social comparison on adolescents, using the ultimatum game (UG). METHODS: Before the formal experiment began, a preliminary experiment tested the effectiveness of social comparison settings. This study used the UG paradigm to explore adolescents' social decision-making in the context of gain and loss through two experiments. These experiments were designed as a 2 (group: depressive mood group, normal mood group) × 2 (social comparison: upward, downward) × 3 (fairness level: fair 5:5, unfair 3:7, extremely unfair 1:9) three-factor hybrid study. RESULTS: (1) The fairer the proposal was, the higher the sense of fairness participants felt, and the higher their acceptance rate. (2) The acceptance rate of the participants for downward social comparison was significantly higher than that for upward social comparison, but there was no difference in fairness perception between the two social comparisons. (3) Under the context of gain, the acceptance rate of the depressive mood group was higher than that of the normal mood group, but there was no difference in the acceptance rate between the depressive mood group and the normal mood group under the loss context. Depressive mood participants had more feelings of unfairness in the contexts of both gain and loss. (4) The effects of depressive mood, social comparison and the fairness level of distribution on social decision-making interact. CONCLUSIONS: The interaction of social comparison, depressive mood and proposal type demonstrates that besides one's emotion, cognitive biases and social factors can also have an effect on social decision-making. These findings indicate that behavioral decision boosting may provide an avenue for appropriate interventions in helping to guide adolescents to make social decisions.

Optimization Algorithm for Kalman Filter Exploiting the Numerical Characteristics of SINS/GPS Integrated Navigation Systems.

Aiming at addressing the problem of high computational cost of the traditional Kalman filter in SINS/GPS, a practical optimization algorithm with offline-derivation and parallel processing methods based on the numerical characteristics of the system is presented in this paper. The algorithm exploits the sparseness and/or symmetry of matrices to simplify the computational procedure. Thus plenty of invalid operations can be avoided by offline derivation using a block matrix technique. For enhanced efficiency, a new parallel computational mechanism is established by subdividing and restructuring calculation processes after analyzing the extracted "useful" data. As a result, the algorithm saves about 90% of the CPU processing time and 66% of the memory usage needed in a classical Kalman filter. Meanwhile, the method as a numerical approach needs no precise-loss transformation/approximation of system modules and the accuracy suffers little in comparison with the filter before computational optimization. Furthermore, since no complicated matrix theories are needed, the algorithm can be easily transplanted into other modified filters as a secondary optimization method to achieve further efficiency.

Job Insecurity and Safety Behaviour: The Mediating Role of Insomnia and Work Engagement.

From the perspective of resource conservation theory, this study selected 568 enterprise employees as subjects and conducted data collection using a random sampling method to explore the relationship between job insecurity and safe behaviours as well as the role of insomnia and job engagement in this relationship. The results show that (1) job insecurity is negatively correlated with safety behaviour, (2) insomnia mediates the relationship between job insecurity and safety behaviour, (3) work engagement plays a mediating role in the relationship between job insecurity and safety behaviour, and (4) insomnia and work engagement play a serial mediating role in the relationship between job insecurity and safety behaviour.