Pitfalls in Developing Machine Learning Models for Predicting Cardiovascular Diseases: Challenge and Solutions.

UNSTRUCTURED: In recent years, there has been an explosive development of artificial intelligence (AI), which has been widely applied in the healthcare field. As a typical AI technology, machine learning (ML) models have emerged as great potential in predicting cardiovascular diseases (CVDs) by leveraging large amounts of medical data for training and optimization, which are expected to play a crucial role in reducing the incidence and mortality rates of CVDs. Although the field has become a research hotspot, there are still many pitfalls that researchers need to pay close attention to. These pitfalls may affect the predictive performance, credibility, reliability, reproducibility of the studied models, ultimately reducing the value of the research and affecting the prospects for clinical application. Therefore, identifying and avoiding these pitfalls is a crucial task before implementing the research. However, there is currently a lack of comprehensive summary on this topic. This viewpoint aims to analyze the existing problems in terms of data quality, dataset characteristics, model design and statistical methods as well as clinic implication, and provide possible solutions to these problems, like gathering objective data, improving training, repeating measurements, increasing sample size, preventing overfitting using statistical methods, utilizing specific AI algorithms to address targeted issues, standardizing outcomes and evaluation criteria, as well as enhancing fairness and replicability, with the goal of offering reference and assistance to researchers, algorithm developers, policy makers, and clinical practitioners.

TM-Score predicts immunotherapy efficacy and improves the performance of the machine learning prognostic model in gastric cancer.

Immunotherapy is becoming increasingly important, but the overall response rate is relatively low in the treatment of gastric cancer (GC). The application of tumor mutational burden (TMB) in predicting immunotherapy efficacy in GC patients is limited and controversial, emphasizing the importance of optimizing TMB-based patient selection. By combining TMB and major histocompatibility complex (MHC) related hub genes, we established a novel TM-Score. This score showed superior performance for immunotherapeutic selection (AUC = 0.808) compared to TMB, MSI status, and EBV status. Additionally, it predicted the prognosis of GC patients. Subsequently, a machine learning model adjusted by the TM-Score further improved the accuracy of survival prediction (AUC > 0.8). Meanwhile, we found that GC patients with low TM-Score had a higher mutation frequency, higher expression of HLA genes and immune checkpoint genes, and higher infiltration of CD8+ T cells, CD4+ helper T cells, and M1 macrophages. This suggests that TM-Score is significantly associated with tumor immunogenicity and tumor immune environment. Notably, based on the RNA-seq and scRNA-seq, it was found that AKAP5, a key component gene of TM-Score, is involved in anti-tumor immunity by promoting the infiltration of CD4+ T cells, NK cells, and myeloid cells. Additionally, siAKAP5 significantly reduced MHC-II mRNA expression in the GC cell line. In addition, our immunohistochemistry assays confirmed a positive correlation between AKAP5 and human leukocyte antigen (HLA) expression. Furthermore, AKAP5 levels were higher in patients with longer survival and those who responded to immunotherapy in GC, indicating its potential value in predicting prognosis and immunotherapy outcomes. In conclusion, TM-Score, as an optimization of TMB, is a more precise biomarker for predicting the immunotherapy efficacy of the GC population. Additionally, AKAP5 shows promise as a therapeutic target for GC.

Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review.

BACKGROUND: A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation. METHODS: PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789). RESULTS: In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively. CONCLUSION: AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

A Comparative Study of the Effects of Electronic Cigarette and Traditional Cigarette on the Pulmonary Functions of C57BL/6 Male Mice.

INTRODUCTION: Electronic cigarettes (E-cigs) are in a controversial state. Although E-cig aerosol generally contains fewer harmful substances than smoke from burned traditional cigarettes, aerosol along with other compounds of the E-cigs may also affect lung functions and promote the development of lung-related diseases. We investigated the effects of E-cig on the pulmonary functions of male C57BL/6 mice and reveal the potential underlying mechanisms. METHODS: A total of 60 male C57BL/6 mice were randomly divided into four groups. They were exposed to fresh-air, traditional cigarette smoke, E-cig vapor with 12 mg/mL of nicotine, and E-cig with no nicotine for 8 weeks. Lung functions were evaluated by using quantitative analysis of the whole body plethysmograph, FlexiVent system, lung tissue histological and morphometric analysis, and RT-PCR analysis of mRNA expression of inflammation-related genes. In addition, the effects of nicotine and acrolein on the survival rate and DNA damage were investigated using cultured human alveolar basal epithelial cells. RESULTS: Exposure to E-cig vapor led to significant changes in lung functions and structures including the rupture of the alveolar cavity and enlarged alveolar space. The pathological changes were also accompanied by increased expression of interleukin-6 and tumor necrosis factor-α. CONCLUSIONS: The findings of the present study indicate that the safety of E-cig should be further evaluated. IMPLICATIONS: Some people currently believe that using nicotine-free E-cigs is a safe way to smoke. However, our research shows that E-cigs can cause lung damage regardless of whether they contain nicotine.

Correlation between maximum heart distance and thoracic diameter changes and diaphragmatic descent in left-sided breast cancer patients during deep inspiration breath-hold (DIBH).

BACKGROUND: Cardioprotection is valued in radiotherapy for patients with left-sided breast cancer. Deep inspiration breath-hold (DIBH) technique can achieve cardioprotection well. However, during DIBH, the extent to which the heart enters the radiation field is affected by the movement of the thorax and diaphragm. The aim of this study was to analyze the correlation between the maximum distance of the heart entering the field (maximum heart distance, MHD) and thoracic diameter changes and diaphragmatic descent in left-sided breast cancer patients during DIBH. PATIENTS AND METHODS: Ninety-eight patients with left-sided breast cancer were included in this retrospective study. They performed simulation in Sentinel-guided DIBH, and two sets of CT images were collected under both free breathing (FB) and DIBH, and diaphragm positions, anteroposterior thoracic diameter (ATD), transverse thoracic diameter (TTD), gating window level (GWL), and MHD were measured, and the change (Δ) of each parameter in DIBH relative to that in FB were calculated. Pearson or Spearman test were used to analyze the correlation between ΔMHD and the changes in other parameters. RESULTS: For all patients with DIBH, the average of ΔMHD was -8.3 mm, and the average of ΔATD and ΔTTD were 11.0 and 8.6 mm, and the median of both left diaphragmatic descent (LDD) and right diaphragmatic descent (RDD) were 35.0 mm, and the median of GWL was 11.1 mm. The correlation coefficients between MHD decrease (ΔMHD) and LDD, RDD, and ΔTTD were -0.430 (p = 0.000), -0.592 (p = 0.000) and 0.208 (p = 0.040), respectively, but not significantly correlated with ΔATD or GWL. CONCLUSIONS: The MHD decrease showed a moderate correlation with diaphragmatic descent In Sentinel-guided DIBH for patients with left-sided breast cancer, while there was a weak or no correlation with thoracic diameter changes or GWL. Abdominal breathing can lower diaphragm more and may be more beneficial to the heart stay away from tangential field.

Enhancement and contextual modulation of visuospatial processing by thalamocollicular projections from ventral lateral geniculate nucleus.

In the mammalian visual system, the ventral lateral geniculate nucleus (vLGN) of the thalamus receives salient visual input from the retina and sends prominent GABAergic axons to the superior colliculus (SC). However, whether and how vLGN contributes to fundamental visual information processing remains largely unclear. Here, we report in mice that vLGN facilitates visually-guided approaching behavior mediated by the lateral SC and enhances the sensitivity of visual object detection. This can be attributed to the extremely broad spatial integration of vLGN neurons, as reflected in their much lower preferred spatial frequencies and broader spatial receptive fields than SC neurons. Through GABAergic thalamocollicular projections, vLGN specifically exerts prominent surround suppression of visuospatial processing in SC, leading to a fine tuning of SC preferences to higher spatial frequencies and smaller objects in a context-dependent manner. Thus, as an essential component of the central visual processing pathway, vLGN serves to refine and contextually modulate visuospatial processing in SC-mediated visuomotor behaviors via visually-driven long-range feedforward inhibition.

The "Trinity" smart hospital construction policy promotes the development of hospitals and health management in China.

Recently, in order to comprehensively promote the development of medical institutions and solve the nationwide problems in the healthcare fields, the government of China developed an innovative national policy of "Trinity" smart hospital construction, which includes "smart medicine," "smart services," and "smart management". The prototype of the evaluation system has been established, and a large number of construction achievements have emerged in many hospitals. In this article, the summary of this field was performed to provide a reference for medical workers, managers of hospitals, and policymakers.

Sensory processing deficits and related cortical pathological changes in Alzheimer's disease.

Alzheimer's disease (AD) is a progressive neurodegenerative disorder primarily affecting cognitive functions. However, sensory deficits in AD start to draw attention due to their high prevalence and early onsets which suggest that they could potentially serve as diagnostic biomarkers and even contribute to the disease progression. This literature review examines the sensory deficits and cortical pathological changes observed in visual, auditory, olfactory, and somatosensory systems in AD patients, as well as in various AD animal models. Sensory deficits may emerge at the early stages of AD, or even precede the cognitive decline, which is accompanied by cortical pathological changes including amyloid-beta deposition, tauopathy, gliosis, and alterations in neuronal excitability, synaptic inputs, and functional plasticity. Notably, these changes are more pronounced in sensory association areas and superficial cortical layers, which may explain the relative preservation of basic sensory functions but early display of deficits of higher sensory functions. We propose that sensory impairment and the progression of AD may establish a cyclical relationship that mutually perpetuates each condition. This review highlights the significance of sensory deficits with or without cortical pathological changes in AD and emphasizes the need for further research to develop reliable early detection and intervention through sensory systems.

Space Charge Characteristics and Breakdown Properties of Nanostructured SiO2/PP Composites.

Polypropylene (PP) has gained attention in the industry as an environmentally friendly material. However, its electrical properties are compromised due to space charge accumulation during operation, limiting its application in high-voltage DC cable insulation. This study investigates the effect and mechanism of SiO2 with a DDS surface hydrophobic treatment on space charge suppression and the electrical properties of PP composites. The PP matrix was doped with SiO2 nanostructures, both with a DDS surface hydrophobic treatment and untreated as a control group. The functional group structure and dispersion of nanostructured SiO2 in the matrix were characterized. The findings reveal that the incorporation of SiO2 nanostructures effectively mitigates charge accumulation in PP composites. However, a high concentration of unsurfaced nanostructures tends to agglomerate, resulting in inadequate space charge suppression and a diminished DC breakdown field strength. Nonetheless, surface treatment improves the dispersion of SiO2 within the matrix. Notably, the composite containing 1.0 wt% of surface hydrophobic SiO2 exhibits the least space charge accumulation. Compared to the base material PP, the average charge density is reduced by 83.9% after the 1800 s short-circuit discharges. Moreover, its DC breakdown field strength reaches 3.45 × 108 V/m, surpassing pure PP by 19.4% and untreated SiO2/PP composites of the same proportion by 24.0%.

The medial preoptic area mediates depressive-like behaviors induced by ovarian hormone withdrawal through distinct GABAergic projections.

Fluctuations in reproductive hormone levels are associated with mood disruptions in women, such as in postpartum and perimenopausal depression. However, the neural circuit mechanisms remain unclear. Here we report that medial preoptic area (MPOA) GABAergic neurons mediate multifaceted depressive-like behaviors in female mice after ovarian hormone withdrawal (HW), which can be attributed to downregulation of activity in Esr1 (estrogen receptor-1)-expressing GABAergic neurons. Enhancing activity of these neurons ameliorates depressive-like behaviors in HW-treated mice, whereas reducing their activity results in expression of these behaviors. Two separate subpopulations mediate different symptoms: a subpopulation projecting to the ventral tegmental area (VTA) mediates anhedonia and another projecting to the periaqueductal gray mediates immobility. These projections enhance activity of dopaminergic neurons in the VTA and serotonergic neurons in the dorsal raphe, respectively, with increased release of dopamine and serotonin, possibly through disinhibition mechanisms. Thus, the MPOA is a hub that mediates depressive-like behaviors resulting from transitions in reproductive hormone levels.

Glutamatergic and GABAergic neurons in pontine central gray mediate opposing valence-specific behaviors through a global network.

Extracting the valence of environmental cues is critical for animals' survival. How valence in sensory signals is encoded and transformed to produce distinct behavioral responses remains not well understood. Here, we report that the mouse pontine central gray (PCG) contributes to encoding both negative and positive valences. PCG glutamatergic neurons were activated selectively by aversive, but not reward, stimuli, whereas its GABAergic neurons were preferentially activated by reward signals. The optogenetic activation of these two populations resulted in avoidance and preference behavior, respectively, and was sufficient to induce conditioned place aversion/preference. Suppression of them reduced sensory-induced aversive and appetitive behaviors, respectively. These two functionally opponent populations, receiving a broad range of inputs from overlapping yet distinct sources, broadcast valence-specific information to a distributed brain network with distinguishable downstream effectors. Thus, PCG serves as a critical hub to process positive and negative valences of incoming sensory signals and drive valence-specific behaviors with distinct circuits.

Rare pulmonary embolism in a pregnant patient: A primary diffused pulmonary artery myxofibrosarcoma case report.

A 37-year-old female patient presented with shortness of breath, cough, and chest pain complaints from the 12th week of her first pregnancy. At the 28th week, labor induction had to be performed because of severe dyspnea and hyoxemia. Thereafter, a diffused pulmonary embolism was detected by echocardiography and CT angiography, without histological diagnosis. Pulmonary endarterectomy was performed, and it was found during operation that a huge, lobular mass originated in the posterior wall and extended throughout the vasculature of both lungs, and a mucinous pellicle covered the entire pulmonary endothelium. Pathology revealed a low-grade myxofibrosarcoma with positive vimentin and SMA, partially positive CD-34.

The Correlation Between MicroRNAs and Diabetic Retinopathy.

Micro ribonucleic acids (miRNAs), as a category of post-transcriptional gene inhibitors, have a wide range of biological functions, are involved in many pathological processes, and are attractive therapeutic targets. Considerable evidence in ophthalmology indicates that miRNAs play an important role in diabetic retinopathy (DR), especially in inflammation, oxidative stress, and neurodegeneration. Targeting specific miRNAs for the treatment of DR has attracted much attention. This is a review focusing on the pathophysiological roles of miRNAs in DR, diabetic macular edema, and proliferative DR complex multifactorial retinal diseases, with particular emphasis on how miRNAs regulate complex molecular pathways and underlying pathomechanisms. Moreover, the future development potential and application limitations of therapy that targets specific miRNAs for DR are discussed.

A bottom-up reward pathway mediated by somatostatin neurons in the medial septum complex underlying appetitive learning.

Valence detection and processing are essential for the survival of animals and their life quality in complex environments. Neural circuits underlying the transformation of external sensory signals into positive valence coding to generate appropriate behavioral responses remain not well-studied. Here, we report that somatostatin (SOM) subtype of GABAergic neurons in the mouse medial septum complex (MS), but not parvalbumin subtype or glutamatergic neurons, specifically encode reward signals and positive valence. Through an ascending pathway from the nucleus of solitary tract and then parabrachial nucleus, the MS SOM neurons receive rewarding taste signals and suppress the lateral habenula. They contribute essentially to appetitive associative learning via their projections to the lateral habenula: learning enhances their responses to reward-predictive sensory cues, and suppressing their responses to either conditioned or unconditioned stimulus impairs acquisition of reward learning. Thus, MS serves as a critical hub for transforming bottom-up sensory signals to mediate appetitive behaviors.

Medial preoptic area antagonistically mediates stress-induced anxiety and parental behavior.

Anxiety is a negative emotional state that is overly displayed in anxiety disorders and depression. Although anxiety is known to be controlled by distributed brain networks, key components for its initiation, maintenance and coordination with behavioral state remain poorly understood. Here, we report that anxiogenic stressors elicit acute and prolonged responses in glutamatergic neurons of the mouse medial preoptic area (mPOA). These neurons encode extremely negative valence and mediate the induction and expression of anxiety-like behaviors. Conversely, mPOA GABA-containing neurons encode positive valence and produce anxiolytic effects. Such opposing roles are mediated by competing local interactions and long-range projections of neurons to the periaqueductal gray. The two neuronal populations antagonistically regulate anxiety-like and parental behaviors: anxiety is reduced, while parenting is enhanced and vice versa. Thus, by evaluating negative and positive valences through distinct but interacting circuits, the mPOA coordinates emotional state and social behavior.

Corticostriatal control of defense behavior in mice induced by auditory looming cues.

Animals exhibit innate defense behaviors in response to approaching threats cued by the dynamics of sensory inputs of various modalities. The underlying neural circuits have been mostly studied in the visual system, but remain unclear for other modalities. Here, by utilizing sounds with increasing (vs. decreasing) loudness to mimic looming (vs. receding) objects, we find that looming sounds elicit stereotypical sequential defensive reactions: freezing followed by flight. Both behaviors require the activity of auditory cortex, in particular the sustained type of responses, but are differentially mediated by corticostriatal projections primarily innervating D2 neurons in the tail of the striatum and corticocollicular projections to the superior colliculus, respectively. The behavioral transition from freezing to flight can be attributed to the differential temporal dynamics of the striatal and collicular neurons in their responses to looming sound stimuli. Our results reveal an essential role of the striatum in the innate defense control.

Green Synthesis of Metallic Nanoparticles and Their Potential Applications to Treat Cancer.

Nanoparticle synthesis using microorganisms and plants by green synthesis technology is biologically safe, cost-effective, and environment-friendly. Plants and microorganisms have established the power to devour and accumulate inorganic metal ions from their neighboring niche. The biological entities are known to synthesize nanoparticles both extra and intracellularly. The capability of a living system to utilize its intrinsic organic chemistry processes in remodeling inorganic metal ions into nanoparticles has opened up an undiscovered area of biochemical analysis. Nanotechnology in conjunction with biology gives rise to an advanced area of nanobiotechnology that involves living entities of both prokaryotic and eukaryotic origin, such as algae, cyanobacteria, actinomycetes, bacteria, viruses, yeasts, fungi, and plants. Every biological system varies in its capabilities to supply metallic nanoparticles. However, not all biological organisms can produce nanoparticles due to their enzymatic activities and intrinsic metabolic processes. Therefore, biological entities or their extracts are used for the green synthesis of metallic nanoparticles through bio-reduction of metallic particles leading to the synthesis of nanoparticles. These biosynthesized metallic nanoparticles have a range of unlimited pharmaceutical applications including delivery of drugs or genes, detection of pathogens or proteins, and tissue engineering. The effective delivery of drugs and tissue engineering through the use of nanotechnology exhibited vital contributions in translational research related to the pharmaceutical products and their applications. Collectively, this review covers the green synthesis of nanoparticles by using various biological systems as well as their applications.

Transforming Sensory Cues into Aversive Emotion via Septal-Habenular Pathway.

Emotions evoked by environmental cues are important for animal survival and life quality. However, neural circuits responsible for transforming sensory signals to aversive emotion and behavioral avoidance remain unclear. Here, we found that medial septum (MS) mediates aversion induced by both auditory and somatosensory stimuli. Ablation of glutamatergic or GABAergic MS neurons results in impaired or strengthened aversion, respectively. Optogenetic activation of the two cell types results in place avoidance and preference, respectively. Cell-type-specific screening reveals that glutamatergic MS projections to the lateral habenula (LHb) are responsible for the induction of aversion, which can be antagonized by GABAergic MS projections to LHb. Additionally, the sensory-induced place avoidance is facilitated by enhanced locomotion mediated by glutamatergic MS projections to the preoptic area. Thus, MS can transmit innately aversive signals via a bottom-up multimodal sensory pathway and produce concurrent emotional and motional effects, allowing animals to efficiently avoid unfavorable environments.

Down-regulation of ETS2 inhibits the invasion and metastasis of renal cell carcinoma cells by inducing EMT via the PI3K/Akt signaling pathway.

V-ets erythroblastosis virus E26 oncogene homolog 2 (ETS2), belonging to the ETS family of transcription factors, is implicated in a broad range of cellular functions. Recently, ETS2 has been found playing an important role in the progression of some types of cancers. However, it remains unclear whether ETS2 has any effects on renal cell carcinoma (RCC). In this study, we investigated the biological functions of ETS2 in RCC. The results showed that ETS2 was highly expressed in RCC tissues and cell lines and its expression had an association with clinicopathological characteristics of RCC patients. In addition, down-regulation of ETS2 significantly inhibited RCC cell invasion in vitro and metastasis in vivo as well as suppressed the epithelial-mesenchymal transition (EMT) process. We also found that ETS2 down-regulation significantly reduced the levels of PI3K and Akt phosphorylation in RCC cells. Taken together, we suggest that ETS2 is of potential value as a molecular target for RCC treatment.

A Non-canonical Reticular-Limbic Central Auditory Pathway via Medial Septum Contributes to Fear Conditioning.

In the mammalian brain, auditory information is known to be processed along a central ascending pathway leading to auditory cortex (AC). Whether there exist any major pathways beyond this canonical auditory neuraxis remains unclear. In awake mice, we found that auditory responses in entorhinal cortex (EC) cannot be explained by a previously proposed relay from AC based on response properties. By combining anatomical tracing and optogenetic/pharmacological manipulations, we discovered that EC received auditory input primarily from the medial septum (MS), rather than AC. A previously uncharacterized auditory pathway was then revealed: it branched from the cochlear nucleus, and via caudal pontine reticular nucleus, pontine central gray, and MS, reached EC. Neurons along this non-canonical auditory pathway responded selectively to high-intensity broadband noise, but not pure tones. Disruption of the pathway resulted in an impairment of specifically noise-cued fear conditioning. This reticular-limbic pathway may thus function in processing aversive acoustic signals.