Enhancing long-term survival prediction with two short-term events: Landmarking with a flexible varying coefficient model.

Patients with cardiovascular diseases who experience disease-related short-term events, such as hospitalizations, often exhibit diverse long-term survival outcomes compared to others. In this study, we aim to improve the prediction of long-term survival probability by incorporating two short-term events using a flexible varying coefficient landmark model. Our objective is to predict the long-term survival among patients who survived up to a pre-specified landmark time since the initial admission. Inverse probability weighting estimation equations are formed based on the information of the short-term outcomes before the landmark time. The kernel smoothing method with the use of cross-validation for bandwidth selection is employed to estimate the time-varying coefficients. The predictive performance of the proposed model is evaluated and compared using predictive measures: area under the receiver operating characteristic curve and Brier score. Simulation studies confirm that parameters under the landmark models can be estimated accurately and the predictive performance of the proposed method consistently outperforms existing methods that either do not incorporate or only partially incorporate information from two short-term events. We demonstrate the practical application of our model using a community-based cohort from the Atherosclerosis Risk in Communities (ARIC) study.

Loss-of-function mutations in the SIGMAR1 gene cause distal hereditary motor neuropathy by impairing ER-mitochondria tethering and Ca2+ signalling.

Distal hereditary motor neuropathies (dHMNs) are clinically and genetically heterogeneous neurological conditions characterized by degeneration of the lower motor neurons. So far, 18 dHMN genes have been identified, however, about 80% of dHMN cases remain without a molecular diagnosis. By a combination of autozygosity mapping, identity-by-descent segment detection and whole-exome sequencing approaches, we identified two novel homozygous mutations in the SIGMAR1 gene (p.E138Q and p.E150K) in two distinct Italian families affected by an autosomal recessive form of HMN. Functional analyses in several neuronal cell lines strongly support the pathogenicity of the mutations and provide insights into the underlying pathomechanisms involving the regulation of ER-mitochondria tethering, Ca2+ homeostasis and autophagy. Indeed, in vitro, both mutations reduce cell viability, the formation of abnormal protein aggregates preventing the correct targeting of sigma-1R protein to the mitochondria-associated ER membrane (MAM) and thus impinging on the global Ca2+ signalling. Our data definitively demonstrate the involvement of SIGMAR1 in motor neuron maintenance and survival by correlating, for the first time in the Caucasian population, mutations in this gene to distal motor dysfunction and highlight the chaperone activity of sigma-1R at the MAM as a critical aspect in dHMN pathology.

Characterization of the influence of spinopelvic parameters on thoracolumbar trauma.

OBJECTIVE: The current Roussouly classification identifies four groups of "normal" sagittal spine morphology, which has greatly expanded the understanding of normal heterogeneity of the spine. While there has been extensive characterization of the influence of spinopelvic parameters on outcomes after degenerative spine surgery, the influence of spinopelvic parameters on thoracolumbar trauma has yet to be described. The goal of this study was to determine if spinopelvic parameters and global spine morphology influence fracture location, fracture morphology, and rate of neurological deficit in the setting of thoracolumbar trauma. METHODS: Of 2896 patients reviewed in the authors' institutional spine database between January 2014 and April 2020 with an ICD-9/10 diagnosis of thoracolumbar trauma, 514 met the inclusion criteria of acute thoracolumbar fracture on CT and visible femoral heads on sagittal CT. Pelvic incidence (PI) was calculated on sagittal CT. Demographic and clinical data including age, sex, BMI, smoking status, concomitant cervical fracture, mechanism of injury, major fracture location, neurological deficit, AO Spine thoracolumbar injury classification, and management type (operative vs nonoperative) were collected. Patients were stratified into high-PI (≥ 50°) and low-PI (< 50°) groups. RESULTS: Patients with high PI had a lower incidence of fractures in the lower lumbar spine (below L2) compared with patients with low PI (16% vs 8%, p < 0.01). The last lordotic vertebrae were observed between T10 and L4, and of fractures that occurred at these levels, 75% were at the last lordotic vertebrae. Fall from height was the most common cause of neurological deficit, accounting for 47%. Of the patients presenting with a fall from height, AO Spine type B distraction injuries were more common in the high-PI group (41% vs 18%, p = 0.01). Similarly, within the same subgroup, AO Spine type A compression injuries were more common in the low-PI group (73% vs 53%, p = 0.01). CONCLUSIONS: Spinopelvic parameters and sagittal balance influence the location and morphology of thoracolumbar fractures. Fractures of the thoracolumbar junction are strongly associated with the inflection point, which is defined by sagittal alignment. While the importance of considering sagittal balance is known for decision-making in degenerative spinal pathology, further studies are required to determine if spinopelvic parameters and sagittal balance should play a role in the decision-making for management of thoracolumbar fractures.

AI Aided Analysis on Saliva Crystallization of Pregnant Women for Accurate Estimation of Delivery Date and Fetal Status.

Saliva contains similar molecular components to serum. Analysis of saliva can provide important diagnostic information about the body. Here we report an artificial intelligence (AI) aided home-based method that can let pregnant women perform daily monitoring on their pregnant status and accurate prediction on their delivery date by the pattern analysis of their salivary crystals. The method was developed based on the information obtained from our investigation on the saliva samples of 170 pregnant women about the correlation of the salivary crystal pattern with pregnant age and fetal status. It demonstrated that the patterns of salivary crystallization could act as indicators of the pregnant age, fetal state, and some medical conditions of pregnant women. On this basis, with the aid of AI recognition and analysis of the fractal dimension and some characteristic crystals in the salivary crystallization, we performed estimation on the delivery date in both quantitative and qualitative manners. The accuracy of the prediction on 15 pregnant women was satisfactory: 100% delivering in the predicted week, 93.3% within the estimated three days, and 86.7% on the day as the prediction. We also developed a simple smartphone-based AI-aided salivary crystal imaging and analysis device as an auxiliary means to let pregnant women monitor their fetal status daily at home and predict their delivery date with adequate accuracy.

Predictive serum markers for unexplained infertility in child-bearing aged women.

PROBLEM: Unexplained infertility (UI) represents about 25%-40% of all infertility and is a formidable obstacle for successful pregnancy for child-bearing aged women. However, up to now, there is no reliable method to predict this condition with high accuracy, thereby hindering early management of this condition. METHOD OF STUDY: Our prospective study consists of 84 child-bearing aged women that were clinically diagnosed UI. Forty-four matched healthy fertility (HF) women were served as controls. We examined the profiles of 25 hormones and cytokines that were likely related to pathogeneses and molecular pathways involved in UI with the technique of protein array. The samples were randomly stratified 7:3 into a training set and a testing set. We used the SMOTEboost model with 10 serum proteins in a clinical verification study to identify UI cases. RESULTS: The predictor had an area under the receiver operating characteristic curve (AUC) of 0.788 with 24 serum protein features. The predictive performance in terms of AUC of the model with the top 10 important serum proteins in the clinical verification study to classify UI cases was 0.809. Three most significantly differentially expressed proteins (DEPs) were prolactin, monocyte chemotactic protein-1 (MCP-1), and leptin. CONCLUSION: Examination of serum-based protein profile changes could help to identify child-bearing aged women at risk of UI. This would enable early detection and facilitate development of clinical strategies to treat UI and guide their planned parenthood. It may also give clues to pathogeneses of the condition of test subjects.

Deep Feature Selection and Causal Analysis of Alzheimer's Disease.

Deep convolutional neural networks (DCNNs) have achieved great success for image classification in medical research. Deep learning with brain imaging is the imaging method of choice for the diagnosis and prediction of Alzheimer's disease (AD). However, it is also well known that DCNNs are "black boxes" owing to their low interpretability to humans. The lack of transparency of deep learning compromises its application to the prediction and mechanism investigation in AD. To overcome this limitation, we develop a novel general framework that integrates deep leaning, feature selection, causal inference, and genetic-imaging data analysis for predicting and understanding AD. The proposed algorithm not only improves the prediction accuracy but also identifies the brain regions underlying the development of AD and causal paths from genetic variants to AD via image mediation. The proposed algorithm is applied to the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with diffusion tensor imaging (DTI) in 151 subjects (51 AD and 100 non-AD) who were measured at four time points of baseline, 6 months, 12 months, and 24 months. The algorithm identified brain regions underlying AD consisting of the temporal lobes (including the hippocampus) and the ventricular system.