Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Dielectric Properties of Polymer Nanocomposite Interphases Using Electrostatic Force Microscopy and Machine Learning.

In ACS applied electronic materials

Knowing the dielectric properties of the interfacial region in polymer nanocomposites is critical to predicting and controlling dielectric properties. They are, however, difficult to characterize due to their nanoscale dimensions. Electrostatic force microscopy (EFM) provides a pathway to local dielectric property measurements, but extracting local dielectric permittivity in complex interphase geometries from EFM measurements remains a challenge. This paper demonstrates a combined EFM and machine learning (ML) approach to measuring interfacial permittivity in 50 nm silica particles in a PMMA matrix. We show that ML models trained to finite-element simulations of the electric field profile between the EFM tip and nanocomposite surface can accurately determine the interface permittivity of functionalized nanoparticles. It was found that for the particles with a polyaniline brush layer, the interfacial region was detectable (extrinsic interface). For bare silica particles, the intrinsic interface was detectable only in terms of having a slightly higher or lower permittivity. This approach fully accounts for the complex interplay of filler, matrix, and interface permittivity on the force gradients measured in EFM that are missed by previous semianalytic approaches, providing a pathway to quantify and design nanoscale interface dielectric properties in nanodielectric materials.

Gupta Praveen, Ruzicka Eric, Benicewicz Brian C, Sundararaman Ravishankar, Schadler Linda S

2023-Feb-28

General General

Normative model detects abnormal functional connectivity in psychiatric disorders.

In Frontiers in psychiatry

INTRODUCTION : The diagnosis of psychiatric disorders is mostly based on the clinical evaluation of the patient's signs and symptoms. Deep learning binary-based classification models have been developed to improve the diagnosis but have not yet reached clinical practice, in part due to the heterogeneity of such disorders. Here, we propose a normative model based on autoencoders.

METHODS : We trained our autoencoder on resting-state functional magnetic resonance imaging (rs-fMRI) data from healthy controls. The model was then tested on schizophrenia (SCZ), bipolar disorder (BD), and attention-deficit hyperactivity disorder (ADHD) patients to estimate how each patient deviated from the norm and associate it with abnormal functional brain networks' (FBNs) connectivity. Rs-fMRI data processing was conducted within the FMRIB Software Library (FSL), which included independent component analysis and dual regression. Pearson's correlation coefficients between the extracted blood oxygen level-dependent (BOLD) time series of all FBNs were calculated, and a correlation matrix was generated for each subject.

RESULTS AND DISCUSSION : We found that the functional connectivity related to the basal ganglia network seems to play an important role in the neuropathology of BD and SCZ, whereas in ADHD, its role is less evident. Moreover, the abnormal connectivity between the basal ganglia network and the language network is more specific to BD. The connectivity between the higher visual network and the right executive control and the connectivity between the anterior salience network and the precuneus networks are the most relevant in SCZ and ADHD, respectively. The results demonstrate that the proposed model could identify functional connectivity patterns that characterize different psychiatric disorders, in agreement with the literature. The abnormal connectivity patterns from the two independent SCZ groups of patients were similar, demonstrating that the presented normative model was also generalizable. However, the group-level differences did not withstand individual-level analysis implying that psychiatric disorders are highly heterogeneous. These findings suggest that a precision-based medical approach, focusing on each patient's specific functional network changes may be more beneficial than the traditional group-based diagnostic classification.

Oliveira-Saraiva Duarte, Ferreira Hugo Alexandre

2023

deep learning, functional brain network, functional connectivity, normative model, psychiatric disorders

Surgery Surgery

Endometriosis leads to central nervous system-wide glial activation in a mouse model of endometriosis.

In Journal of neuroinflammation

BACKGROUND : Chronic pelvic pain (CPP) is a common symptom of endometriosis. Women with endometriosis are also at a high risk of suffering from anxiety, depression, and other psychological disorders. Recent studies indicate that endometriosis can affect the central nervous system (CNS). Changes in the functional activity of neurons, functional magnetic resonance imaging signals, and gene expression have been reported in the brains of rat and mouse models of endometriosis. The majority of the studies thus far have focused on neuronal changes, whereas changes in the glial cells in different brain regions have not been studied.

METHODS : Endometriosis was induced in female mice (45-day-old; n = 6-11/timepoint) by syngeneic transfer of donor uterine tissue into the peritoneal cavity of recipient animals. Brains, spines, and endometriotic lesions were collected for analysis at 4, 8, 16, and 32 days post-induction. Sham surgery mice were used as controls (n = 6/timepoint). The pain was assessed using behavioral tests. Using immunohistochemistry for microglia marker ionized calcium-binding adapter molecule-1 (IBA1) and machine learning "Weka trainable segmentation" plugin in Fiji, we evaluated the morphological changes in microglia in different brain regions. Changes in glial fibrillary acidic protein (GFAP) for astrocytes, tumor necrosis factor (TNF), and interleukin-6 (IL6) were also evaluated.

RESULTS : We observed an increase in microglial soma size in the cortex, hippocampus, thalamus, and hypothalamus of mice with endometriosis compared to sham controls on days 8, 16, and 32. The percentage of IBA1 and GFAP-positive area was increased in the cortex, hippocampus, thalamus, and hypothalamus in mice with endometriosis compared to sham controls on day 16. The number of microglia and astrocytes did not differ between endometriosis and sham control groups. We observed increased TNF and IL6 expression when expression levels from all brain regions were combined. Mice with endometriosis displayed reduced burrowing behavior and hyperalgesia in the abdomen and hind-paw.

CONCLUSION : We believe this is the first report of central nervous system-wide glial activation in a mouse model of endometriosis. These results have significant implications for understanding chronic pain associated with endometriosis and other issues such as anxiety and depression in women with endometriosis.

Bashir Shah Tauseef, Redden Catherine R, Raj Kishori, Arcanjo Rachel B, Stasiak Sandra, Li Quanxi, Steelman Andrew J, Nowak Romana A

2023-Mar-06

Chronic pelvic pain (CPP), Endometriosis, Glial activation, Hyperalgesia

Public Health Public Health

Science fiction or clinical reality: a review of the applications of artificial intelligence along the continuum of trauma care.

In World journal of emergency surgery : WJES

Artificial intelligence (AI) and machine learning describe a broad range of algorithm types that can be trained based on datasets to make predictions. The increasing sophistication of AI has created new opportunities to apply these algorithms within within trauma care. Our paper overviews the current uses of AI along the continuum of trauma care, including injury prediction, triage, emergency department volume, assessment, and outcomes. Starting at the point of injury, algorithms are being used to predict severity of motor vehicle crashes, which can help inform emergency responses. Once on the scene, AI can be used to help emergency services triage patients remotely in order to inform transfer location and urgency. For the receiving hospital, these tools can be used to predict trauma volumes in the emergency department to help allocate appropriate staffing. After patient arrival to hospital, these algorithms not only can help to predict injury severity, which can inform decision-making, but also predict patient outcomes to help trauma teams anticipate patient trajectory. Overall, these tools have the capability to transform trauma care. AI is still nascent within the trauma surgery sphere, but this body of the literature shows that this technology has vast potential. AI-based predictive tools in trauma need to be explored further through prospective trials and clinical validation of algorithms.

Hunter Olivia F, Perry Frances, Salehi Mina, Bandurski Hubert, Hubbard Alan, Ball Chad G, Morad Hameed S

2023-Mar-06

Artificial intelligence, Machine learning, Trauma

Radiology Radiology

Differentiation of acute and chronic vertebral compression fractures using conventional CT based on deep transfer learning features and hand-crafted radiomics features.

In BMC musculoskeletal disorders ; h5-index 46.0

BACKGROUND : We evaluated the diagnostic efficacy of deep learning radiomics (DLR) and hand-crafted radiomics (HCR) features in differentiating acute and chronic vertebral compression fractures (VCFs).

METHODS : A total of 365 patients with VCFs were retrospectively analysed based on their computed tomography (CT) scan data. All patients completed MRI examination within 2 weeks. There were 315 acute VCFs and 205 chronic VCFs. Deep transfer learning (DTL) features and HCR features were extracted from CT images of patients with VCFs using DLR and traditional radiomics, respectively, and feature fusion was performed to establish the least absolute shrinkage and selection operator. The MRI display of vertebral bone marrow oedema was used as the gold standard for acute VCF, and the model performance was evaluated using the receiver operating characteristic (ROC).To separately evaluate the effectiveness of DLR, traditional radiomics and feature fusion in the differential diagnosis of acute and chronic VCFs, we constructed a nomogram based on the clinical baseline data to visualize the classification evaluation. The predictive power of each model was compared using the Delong test, and the clinical value of the nomogram was evaluated using decision curve analysis (DCA).

RESULTS : Fifty DTL features were obtained from DLR, 41 HCR features were obtained from traditional radiomics, and 77 features fusion were obtained after feature screening and fusion of the two. The area under the curve (AUC) of the DLR model in the training cohort and test cohort were 0.992 (95% confidence interval (CI), 0.983-0.999) and 0.871 (95% CI, 0.805-0.938), respectively. While the AUCs of the conventional radiomics model in the training cohort and test cohort were 0.973 (95% CI, 0.955-0.990) and 0.854 (95% CI, 0.773-0.934), respectively. The AUCs of the features fusion model in the training cohort and test cohort were 0.997 (95% CI, 0.994-0.999) and 0.915 (95% CI, 0.855-0.974), respectively. The AUCs of nomogram constructed by the features fusion in combination with clinical baseline data were 0.998 (95% CI, 0.996-0.999) and 0.946 (95% CI, 0.906-0.987) in the training cohort and test cohort, respectively. The Delong test showed that the differences between the features fusion model and the nomogram in the training cohort and the test cohort were not statistically significant (P values were 0.794 and 0.668, respectively), and the differences in the other prediction models in the training cohort and the test cohort were statistically significant (P < 0.05). DCA showed that the nomogram had high clinical value.

CONCLUSION : The features fusion model can be used for the differential diagnosis of acute and chronic VCFs, and its differential diagnosis ability is improved when compared with that when either radiomics is used alone. At the same time, the nomogram has a high predictive value for acute and chronic VCFs and can be a potential decision-making tool to assist clinicians, especially when a patient is unable to undergo spinal MRI examination.

Zhang Jun, Liu Jiayi, Liang Zhipeng, Xia Liang, Zhang Weixiao, Xing Yanfen, Zhang Xueli, Tang Guangyu

2023-Mar-06

Deep learning, Differential diagnosis, Radiomics, Tomography, X-ray computed, Vertebral compression fracture (VCF)

General General

Decision tree learning in Neo4j on homogeneous and unconnected graph nodes from biological and clinical datasets.

In BMC medical informatics and decision making ; h5-index 38.0

BACKGROUND : Graph databases enable efficient storage of heterogeneous, highly-interlinked data, such as clinical data. Subsequently, researchers can extract relevant features from these datasets and apply machine learning for diagnosis, biomarker discovery, or understanding pathogenesis.

METHODS : To facilitate machine learning and save time for extracting data from the graph database, we developed and optimized Decision Tree Plug-in (DTP) containing 24 procedures to generate and evaluate decision trees directly in the graph database Neo4j on homogeneous and unconnected nodes.

RESULTS : Creation of the decision tree for three clinical datasets directly in the graph database from the nodes required between 0.059 and 0.099 s, while calculating the decision tree with the same algorithm in Java from CSV files took 0.085-0.112 s. Furthermore, our approach was faster than the standard decision tree implementations in R (0.62 s) and equal to Python (0.08 s), also using CSV files as input for small datasets. In addition, we have explored the strengths of DTP by evaluating a large dataset (approx. 250,000 instances) to predict patients with diabetes and compared the performance against algorithms generated by state-of-the-art packages in R and Python. By doing so, we have been able to show competitive results on the performance of Neo4j, in terms of quality of predictions as well as time efficiency. Furthermore, we could show that high body-mass index and high blood pressure are the main risk factors for diabetes.

CONCLUSION : Overall, our work shows that integrating machine learning into graph databases saves time for additional processes as well as external memory, and could be applied to a variety of use cases, including clinical applications. This provides user with the advantages of high scalability, visualization and complex querying.

Mondal Rahul, Do Minh Dung, Ahmed Nasim Uddin, Walke Daniel, Micheel Daniel, Broneske David, Saake Gunter, Heyer Robert

2023-Mar-06

Cypher, Decision tree, Graph database, Java, Neo4j, Python, R