Self-Assembled Origami Neural Probes for Scalable, Multifunctional, Three-Dimensional Neural Interface.

Flexible intracortical neural probes have drawn attention for their enhanced longevity in high-resolution neural recordings due to reduced tissue reaction. However, the conventional monolithic fabrication approach has met significant challenges in: (i) scaling the number of recording sites for electrophysiology; (ii) integrating of other physiological sensing and modulation; and (iii) configuring into three-dimensional (3D) shapes for multi-sided electrode arrays. We report an innovative self-assembly technology that allows for implementing flexible origami neural probes as an effective alternative to overcome these challenges. By using magnetic-field-assisted hybrid self-assembly, multiple probes with various modalities can be stacked on top of each other with precise alignment. Using this approach, we demonstrated a multifunctional device with scalable high-density recording sites, dopamine sensors and a temperature sensor integrated on a single flexible probe. Simultaneous large-scale, high-spatial-resolution electrophysiology was demonstrated along with local temperature sensing and dopamine concentration monitoring. A high-density 3D origami probe was assembled by wrapping planar probes around a thin fiber in a diameter of 80∼105 µm using optimal foldable design and capillary force. Directional optogenetic modulation could be achieved with illumination from the neuron-sized micro-LEDs (µLEDs) integrated on the surface of 3D origami probes. We could identify angular heterogeneous single-unit signals and neural connectivity 360° surrounding the probe. The probe longevity was validated by chronic recordings of 64-channel stacked probes in behaving mice for up to 140 days. With the modular, customizable assembly technologies presented, we demonstrated a novel and highly flexible solution to accommodate multifunctional integration, channel scaling, and 3D array configuration.

Low-parameter supervised learning models can discriminate pseudoprogression and true progression in non-perfusion-based MRI.

Discrimination of pseudoprogression and true progression is one challenge to the treatment of malignant gliomas. Although some techniques such as circulating tumor DNA (ctDNA) and perfusion-weighted imaging (PWI) demonstrate promise in distinguishing PsP from TP, we investigate robust and replicable alternatives to distinguish the two entities based on more widely-available media. In this study, we use low-parametric supervised learning techniques based on geographically-weighted regression (GWR) to investigate the utility of both conventional MRI sequences as well as a diffusion-weighted sequence (apparent diffusion coefficient or ADC) in the discrimination of PsP v TP. GWR applied to MRI modality pairs is a unique approach for small sample sizes and is a novel approach in this arena. From our analysis, all modality pairs involving ADC maps, and those involving post-contrast T1 regressed onto T2 showed potential promise. This work on ADC data adds to a growing body of research suggesting the predictive benefits of ADC, and suggests further research on the relationships between post-contrast T1 and T2.Clinical relevance- Few studies have investigated predictive potential of conventional MRI and ADC to detect PsP. Our study adds to the growing research on the topic and presents a new perspective to research by exploiting the utility of ADC in PsP v TP distinction. In addition, our GWR methodology for low-parametric supervised computer vision models demonstrates a unique approach for image processing of small sample sizes.

Clustering-based spatial analysis (CluSA) framework through graph neural network for chronic kidney disease prediction using histopathology images.

Machine learning applied to digital pathology has been increasingly used to assess kidney function and diagnose the underlying cause of chronic kidney disease (CKD). We developed a novel computational framework, clustering-based spatial analysis (CluSA), that leverages unsupervised learning to learn spatial relationships between local visual patterns in kidney tissue. This framework minimizes the need for time-consuming and impractical expert annotations. 107,471 histopathology images obtained from 172 biopsy cores were used in the clustering and in the deep learning model. To incorporate spatial information over the clustered image patterns on the biopsy sample, we spatially encoded clustered patterns with colors and performed spatial analysis through graph neural network. A random forest classifier with various groups of features were used to predict CKD. For predicting eGFR at the biopsy, we achieved a sensitivity of 0.97, specificity of 0.90, and accuracy of 0.95. AUC was 0.96. For predicting eGFR changes in one-year, we achieved a sensitivity of 0.83, specificity of 0.85, and accuracy of 0.84. AUC was 0.85. This study presents the first spatial analysis based on unsupervised machine learning algorithms. Without expert annotation, CluSA framework can not only accurately classify and predict the degree of kidney function at the biopsy and in one year, but also identify novel predictors of kidney function and renal prognosis.

Investigating Useful Features for Overall Survival Prediction in Patients with Low-Grade Glioma Using Histology Slides.

Glioma, characterized by neoplastic growth in the brain, is a life-threatening condition that, in most cases, ultimately leads to death. Typical analysis of glioma development involves observation of brain tissue in the form of a histology slide under a microscope. Although brain histology images have much potential for predicting patient outcomes such as overall survival (OS), they are rarely used as the sole predictors due challenges presented by unique characteristics of brain tissue histology. However, utilizing histology in predicting overall survival can be useful for treatment and quality-of-life for patients with early-stage glioma. In this study, we investigate the use of deep learning models on histology slides combined with simple descriptor data (age and glioma subtype) as a predictor of (OS) in patients with low-grade glioma (LGG). Using novel clinical data, we show that models which are more attentive to discriminative features of the image will confer better predictions than generic models (82.7 and 65.3 AUC RFD-Net and Baseline VGG16 model, respectively). Additionally, we show that adding age and subtype information to a histology image-based model may provide greater robustness in the model than using the image alone (3.8 and 4.3 stds for RFD-Net and Baseline VGG16 model with 3-fold CV, respectively), while a model based on image and age but not subtype may confer the best predictive results (83.7 and 82.0 AUC for RFD-Net + age and RFD-Net + age + subtype, respectively). Clinical relevance- This study establishes important criteria for deep learning models which predict OS using histology and basic clinical data from LGG patients.

Unsupervised machine learning for identifying important visual features through bag-of-words using histopathology data from chronic kidney disease.

Pathologists use visual classification to assess patient kidney biopsy samples when diagnosing the underlying cause of kidney disease. However, the assessment is qualitative, or semi-quantitative at best, and reproducibility is challenging. To discover previously unknown features which predict patient outcomes and overcome substantial interobserver variability, we developed an unsupervised bag-of-words model. Our study applied to the C-PROBE cohort of patients with chronic kidney disease (CKD). 107,471 histopathology images were obtained from 161 biopsy cores and identified important morphological features in biopsy tissue that are highly predictive of the presence of CKD both at the time of biopsy and in one year. To evaluate the performance of our model, we estimated the AUC and its 95% confidence interval. We show that this method is reliable and reproducible and can achieve 0.93 AUC at predicting glomerular filtration rate at the time of biopsy as well as predicting a loss of function at one year. Additionally, with this method, we ranked the identified morphological features according to their importance as diagnostic markers for chronic kidney disease. In this study, we have demonstrated the feasibility of using an unsupervised machine learning method without human input in order to predict the level of kidney function in CKD. The results from our study indicate that the visual dictionary, or visual image pattern, obtained from unsupervised machine learning can predict outcomes using machine-derived values that correspond to both known and unknown clinically relevant features.

Predicting Osteoarthritis of the Temporomandibular Joint Using Random Forest with Privileged Information.

Osteoarthritis of the temporomandibular joint (TMJ OA) is the most common disorder of the TMJ. A clinical decision support (CDS) system designed to detect TMJ OA could function as a useful screening tool as part of regular check-ups to detect early onset. This study implements a CDS concept model based on Random Forest and dubbed RF+ to predict TMJ OA with the hypothesis that a model which leverages high-resolution radiological and biomarker data in training only can improve predictions compared with a baseline model which does not use privileged information. We found that the RF+ model can outperform the baseline model even when privileged features are not of gold standard quality. Additionally, we introduce a novel method for post-hoc feature analysis, finding shortRunHighGreyLevelEmphasis of the lateral condyles and joint distance to be the most important features from the privileged modalities for predicting TMJ OA.

Integrating Multimeric Threading With High-throughput Experiments for Structural Interactome of Escherichia coli.

Genome-wide protein-protein interaction (PPI) determination remains a significant unsolved problem in structural biology. The difficulty is twofold since high-throughput experiments (HTEs) have often a relatively high false-positive rate in assigning PPIs, and PPI quaternary structures are more difficult to solve than tertiary structures using traditional structural biology techniques. We proposed a uniform pipeline, Threpp, to address both problems. Starting from a pair of monomer sequences, Threpp first threads both sequences through a complex structure library, where the alignment score is combined with HTE data using a naïve Bayesian classifier model to predict the likelihood of two chains to interact with each other. Next, quaternary complex structures of the identified PPIs are constructed by reassembling monomeric alignments with dimeric threading frameworks through interface-specific structural alignments. The pipeline was applied to the Escherichia coli genome and created 35,125 confident PPIs which is 4.5-fold higher than HTE alone. Graphic analyses of the PPI networks show a scale-free cluster size distribution, consistent with previous studies, which was found critical to the robustness of genome evolution and the centrality of functionally important proteins that are essential to E. coli survival. Furthermore, complex structure models were constructed for all predicted E. coli PPIs based on the quaternary threading alignments, where 6771 of them were found to have a high confidence score that corresponds to the correct fold of the complexes with a TM-score >0.5, and 39 showed a close consistency with the later released experimental structures with an average TM-score = 0.73. These results demonstrated the significant usefulness of threading-based homologous modeling in both genome-wide PPI network detection and complex structural construction.

Learning Using Partially Available Privileged Information and Label Uncertainty: Application in Detection of Acute Respiratory Distress Syndrome.

Acute respiratory distress syndrome (ARDS) is a fulminant inflammatory lung injury that develops in patients with critical illnesses, affecting 200,000 patients in the United States annually. However, a recent study suggests that most patients with ARDS are diagnosed late or missed completely and fail to receive life-saving treatments. This is primarily due to the dependency of current diagnosis criteria on chest x-ray, which is not necessarily available at the time of diagnosis. In machine learning, such an information is known as Privileged Information - information that is available at training but not at testing. However, in diagnosing ARDS, privileged information (chest x-rays) are sometimes only available for a portion of the training data. To address this issue, the Learning Using Partially Available Privileged Information (LUPAPI) paradigm is proposed. As there are multiple ways to incorporate partially available privileged information, three models built on classical SVM are described. Another complexity of diagnosing ARDS is the uncertainty in clinical interpretation of chest x-rays. To address this, the LUPAPI framework is then extended to incorporate label uncertainty, resulting in a novel and comprehensive machine learning paradigm - Learning Using Label Uncertainty and Partially Available Privileged Information (LULUPAPI). The proposed frameworks use Electronic Health Record (EHR) data as regular information, chest x-rays as partially available privileged information, and clinicians' confidence levels in ARDS diagnosis as a measure of label uncertainty. Experiments on an ARDS dataset demonstrate that both the LUPAPI and LULUPAPI models outperform SVM, with LULUPAPI performing better than LUPAPI.

Publisher Correction: Age and life expectancy clocks based on machine learning analysis of mouse frailty.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Age and life expectancy clocks based on machine learning analysis of mouse frailty.

The identification of genes and interventions that slow or reverse aging is hampered by the lack of non-invasive metrics that can predict the life expectancy of pre-clinical models. Frailty Indices (FIs) in mice are composite measures of health that are cost-effective and non-invasive, but whether they can accurately predict health and lifespan is not known. Here, mouse FIs are scored longitudinally until death and machine learning is employed to develop two clocks. A random forest regression is trained on FI components for chronological age to generate the FRIGHT (Frailty Inferred Geriatric Health Timeline) clock, a strong predictor of chronological age. A second model is trained on remaining lifespan to generate the AFRAID (Analysis of Frailty and Death) clock, which accurately predicts life expectancy and the efficacy of a lifespan-extending intervention up to a year in advance. Adoption of these clocks should accelerate the identification of longevity genes and aging interventions.

Density-based classification in diabetic retinopathy through thickness of retinal layers from optical coherence tomography.

Diabetic retinopathy (DR) is a severe retinal disorder that can lead to vision loss, however, its underlying mechanism has not been fully understood. Previous studies have taken advantage of Optical Coherence Tomography (OCT) and shown that the thickness of individual retinal layers are affected in patients with DR. However, most studies analyzed the thickness by calculating summary statistics from retinal thickness maps of the macula region. This study aims to apply a density function-based statistical framework to the thickness data obtained through OCT, and to compare the predictive power of various retinal layers to assess the severity of DR. We used a prototype data set of 107 subjects which are comprised of 38 non-proliferative DR (NPDR), 28 without DR (NoDR), and 41 controls. Based on the thickness profiles, we constructed novel features which capture the variation in the distribution of the pixel-wise retinal layer thicknesses from OCT. We quantified the predictive power of each of the retinal layers to distinguish between all three pairwise comparisons of the severity in DR (NoDR vs NPDR, controls vs NPDR, and controls vs NoDR). When applied to this preliminary DR data set, our density-based method demonstrated better predictive results compared with simple summary statistics. Furthermore, our results indicate considerable differences in retinal layer structuring based on the severity of DR. We found that: (a) the outer plexiform layer is the most discriminative layer for classifying NoDR vs NPDR; (b) the outer plexiform, inner nuclear and ganglion cell layers are the strongest biomarkers for discriminating controls from NPDR; and (c) the inner nuclear layer distinguishes best between controls and NoDR.

Glycoproteomic markers of hepatocellular carcinoma-mass spectrometry based approaches.

Hepatocellular carcinoma (HCC) is the third most-common cause of cancer-related death worldwide. Most cases of HCC develop in patients that already have liver cirrhosis and have been recommended for surveillance for an early onset of HCC. Cirrhosis is the final common pathway for several etiologies of liver disease, including hepatitis B and C, alcohol, and increasingly non-alcoholic fatty liver disease. Only 20-30% of patients with HCC are eligible for curative therapy due primarily to inadequate early-detection strategies. Reliable, accurate biomarkers for HCC early detection provide the highest likelihood of curative therapy and survival; however, current early-detection methods that use abdominal ultrasound and serum alpha fetoprotein are inadequate due to poor adherence and limited sensitivity and specificity. There is an urgent need for convenient and highly accurate validated biomarkers for HCC early detection. The theme of this review is the development of new methods to discover glycoprotein-based markers for detection of HCC with mass spectrometry approaches. We outline the non-mass spectrometry based methods that have been used to discover HCC markers including immunoassays, capillary electrophoresis, 2-D gel electrophoresis, and lectin-FLISA assays. We describe the development and results of mass spectrometry-based assays for glycan screening based on either MALDI-MS or ESI analysis. These analyses might be based on the glycan content of serum or on glycan screening for target molecules from serum. We describe some of the specific markers that have been developed as a result, including for proteins such as Haptoglobin, Hemopexin, Kininogen, and others. We discuss the potential role for other technologies, including PGC chromatography and ion mobility, to separate isoforms of glycan markers. Analyses of glycopeptides based on new technologies and innovative softwares are described and also their potential role in discovery of markers of HCC. These technologies include new fragmentation methods such as EThcD and stepped HCD, which can identify large numbers of glycopeptide structures from serum. The key role of lectin extraction in various assays for intact glycopeptides or their truncated versions is also described, where various core-fucosylated and hyperfucosylated glycopeptides have been identified as potential markers of HCC. Finally, we describe the role of LC-MRMs or lectin-FLISA MRMs as a means to validate these glycoprotein markers from patient samples. These technological advancements in mass spectrometry have the potential to lead to novel biomarkers to improve the early detection of HCC.

Rapid microwave-assisted dispersive micro-solid phase extraction of mycotoxins in food using zirconia nanoparticles.

Mycotoxins are a group of secondary fungi metabolites present in foods that cause adverse effects in humans and animals. The objective of this study was to develop and validate a reliable and sensitive method to determine the presence of fumonisin B1, aflatoxin B1, ochratoxin B, T-2 toxin, ochratoxin A and zearalenone. A rapid, effective process, which involves microwave-assisted dispersive micro-solid phase extraction (MA-d-µ-SPE), has been proposed for the extraction and detection of 6 mycotoxins in peach seed, milk powder, corn flour and beer sample matrixes, for subsequent analysis by ultra-high-performance liquid chromatography coupled with quadrupole time-of-flight tandem mass spectrometry (UHPLC-Q-TOF/MS). Several experimental parameters (type of dispersant, concentration of dispersant, vortex time, type of desorption solvent and pH) affecting the extraction efficiency were systematically studied and optimized. The optimum extraction conditions involved immersing 2.5 µg/mL of nano zirconia (as dispersant) in a 5 mL sample solution. After 2 min of extraction by vigorous shaking, the target analytes were desorbed by 100 µL of chloroform at pH 4.5. The results indicated good linearity in the range of 0.0074-3.6 µg/mL (r ≥ 0.9982), low limits of detection (0.0036-0.033 µg/kg for solid samples and 0.0022-0.017 ng/mL for beer), acceptable reproducibility (relative standard deviation (RSD%) 2.08-2.76% for retention time and 3.51-4.59% for peak area, n = 3), and satisfactory spiked recoveries (84.27-104.96%) for studied mycotoxins in sample matrixes, which demonstrated that MA-d-µ-SPE coupled with UHPLC-Q-TOF/MS is a useful tool for analysis of multi-mycotoxin.

A nomogram incorporating six easily obtained parameters to discriminate intrahepatic cholangiocarcinoma and hepatocellular carcinoma.

Intrahepatic cholangiocarcinoma (ICC) and hepatocellular carcinoma (HCC) are the most prevalent histologic types of primary liver cancer (PLC). Although ICC and HCC share similar risk factors and clinical manifestations, ICC usually bears poorer prognosis than HCC. Confidently discriminating ICC and HCC before surgery is beneficial to both treatment and prognosis. Given the lack of effective differential diagnosis biomarkers and methods, construction of models based on available clinicopathological characteristics is in need. Nomograms present a simple and efficient way to make a discrimination. A total of 2894 patients who underwent surgery for PLC were collected. Of these, 1614 patients formed the training cohort for nomogram construction, and thereafter, 1280 patients formed the validation cohort to confirm the model's performance. Histopathologically confirmed ICC was diagnosed in 401 (24.8%) and 296 (23.1%) patients in these two cohorts, respectively. A nomogram integrating six easily obtained variables (Gender, Hepatitis B surface antigen, Aspartate aminotransferase, Alpha-fetoprotein, Carcinoembryonic antigen, Carbohydrate antigen 19-9) is proposed in accordance with Akaike's Information Criterion (AIC). A score of 15 was determined as the cut-off value, and the corresponding discrimination efficacy was sufficient. Additionally, patients who scored higher than 15 suffered poorer prognosis than those with lower scores, regardless of the subtype of PLC. A nomogram for clinical discrimination of ICC and HCC has been established, where a higher score indicates ICC and poor prognosis. Further application of this nomogram in multicenter investigations may confirm the practicality of this tool for future clinical use.

Serum N-glycans outperform CA19-9 in diagnosis of extrahepatic cholangiocarcinoma.

Extensive efforts have been devoted to improve the diagnosis of extrahepatic cholangiocarcinoma (ECCA) due to its silent clinical character and lack of effective diagnostic biomarkers. Specific alterations in N-glycosylation of glycoproteins are considered a key component in cancer progression, which can serve as a distinct molecular signature for cancer detection. This study aims to find potential serum N-glycan markers for ECCA. In total, 255 serum samples from patients with ECCA (n = 106), benign bile tract disease (BBD, n = 60) and healthy controls (HC, n = 89) were recruited. Only 2 µL of serum from individual patients was used in this assay where the N-glycome of serum glycoproteins was profiled by DNA sequencer-assisted fluorophore-assisted capillary electrophoresis (DSA-FACE) technology. Multi-parameter models were constructed by combining the N-glycans and carbohydrate antigen 19-9 (CA19-9) which is currently used clinically. Quantitative analyses showed that among 13 N-glycan structures, the bifucosylated triantennary N-glycan (peak10, NA3F2) presented the best diagnostic performance for distinguishing ECCA from BBD and HC. Two diagnostic models (Glycotest1 and Glycotest2) performed better than single N-glycan or CA19-9. Additionally, two N-glycan structures (peak9, NA3Fb; peak12, NA4Fb) were tightly related to lymph node metastasis in ECCA patients. In conclusion, sera of ECCA showed relatively specific N-glycome profiling patterns. Serum N-glycan markers and models are novel, valuable and noninvasive alternatives in ECCA diagnosis and progression monitoring.

Extraction and enrichment of natural pigments from solid samples using ionic liquids and chitosan nanoparticles.

A green and economical method for the extraction and preconcentration of natural pigments (curcumin, demethoxycurcumin and bisdemethoxycurcumin) was developed using ultrasound-assisted extraction combined with dispersive micro solid-phase extraction. In this work, Ionic liquids (ILs) were used for the pre-extraction of natural pigments. The pure chitosan nanoparticles (CS NPs) were then used as a sorbent for the microextraction mode. The method involves the use of ultrahigh-performance liquid chromatography coupled with quadrupole time-of-flight tandem mass spectrometry. Operating parameters influencing the performance of extraction steps such as type and concentration of ILs, concentration of CS NPs, type of elution solvent, agitation time and pH of sample-extracting solution were investigated. Under the optimum conditions, the proposed method exhibited a low detection limit in the range of 0.11-0.36ng/mL at S/N=3, and good linearities with coefficients of determination (R(2)) higher than 0.9990. The recoveries of turmeric samples were ranging from 90.45% to 105.04% for the three studied curcuminoids with SD of 3.27-6.58. The experimental results indicated that the ILs and CS NPs were the promising materials for the extraction and enrichment of target curcuminoids from complex solid samples.

Community-based surveillance of maternal deaths in rural Ghana.

OBJECTIVE: To examine the feasibility and effectiveness of community-based maternal mortality surveillance in rural Ghana, where most information on maternal deaths usually comes from retrospective surveys and hospital records. METHODS: In 2013, community-based surveillance volunteers used a modified reproductive age mortality survey (RAMOS 4+2) to interview family members of women of reproductive age (13-49 years) who died in Bosomtwe district in the previous five years. The survey comprised four yes-no questions and two supplementary questions. Verbal autopsies were done if there was a positive answer to at least one yes-no question. A mortality review committee established the cause of death. FINDINGS: Survey results were available for 357 women of reproductive age who died in the district. A positive response to at least one yes-no question was recorded for respondents reporting on the deaths of 132 women. These women had either a maternal death or died within one year of termination of pregnancy. Review of 108 available verbal autopsies found that 64 women had a maternal or late maternal death and 36 died of causes unrelated to childbearing. The most common causes of death were haemorrhage (15) and abortion (14). The resulting maternal mortality ratio was 357 per 100 000 live births, compared with 128 per 100 000 live births derived from hospital records. CONCLUSION: The community-based mortality survey was effective for ascertaining maternal deaths and identified many deaths not included in hospital records. National surveys could provide the information needed to end preventable maternal mortality by 2030.