Novel Domain Knowledge-Encoding Algorithm Enables Label-Efficient Deep Learning for Cardiac CT Segmentation to Guide Atrial Fibrillation Treatment in a Pilot Dataset.

Background: Segmenting computed tomography (CT) is crucial in various clinical applications, such as tailoring personalized cardiac ablation for managing cardiac arrhythmias. Automating segmentation through machine learning (ML) is hindered by the necessity for large, labeled training data, which can be challenging to obtain. This article proposes a novel approach for automated, robust labeling using domain knowledge to achieve high-performance segmentation by ML from a small training set. The approach, the domain knowledge-encoding (DOKEN) algorithm, reduces the reliance on large training datasets by encoding cardiac geometry while automatically labeling the training set. The method was validated in a hold-out dataset of CT results from an atrial fibrillation (AF) ablation study. Methods: The DOKEN algorithm parses left atrial (LA) structures, extracts "anatomical knowledge" by leveraging digital LA models (available publicly), and then applies this knowledge to achieve high ML segmentation performance with a small number of training samples. The DOKEN-labeled training set was used to train a nnU-Net deep neural network (DNN) model for segmenting cardiac CT in N = 20 patients. Subsequently, the method was tested in a hold-out set with N = 100 patients (five times larger than training set) who underwent AF ablation. Results: The DOKEN algorithm integrated with the nn-Unet model achieved high segmentation performance with few training samples, with a training to test ratio of 1:5. The Dice score of the DOKEN-enhanced model was 96.7% (IQR: 95.3% to 97.7%), with a median error in surface distance of boundaries of 1.51 mm (IQR: 0.72 to 3.12) and a mean centroid-boundary distance of 1.16 mm (95% CI: -4.57 to 6.89), similar to expert results (r = 0.99; p < 0.001). In digital hearts, the novel DOKEN approach segmented the LA structures with a mean difference for the centroid-boundary distances of -0.27 mm (95% CI: -3.87 to 3.33; r = 0.99; p < 0.0001). Conclusions: The proposed novel domain knowledge-encoding algorithm was able to perform the segmentation of six substructures of the LA, reducing the need for large training data sets. The combination of domain knowledge encoding and a machine learning approach could reduce the dependence of ML on large training datasets and could potentially be applied to AF ablation procedures and extended in the future to other imaging, 3D printing, and data science applications.

A behavioral and eye movement study on inhibitory processing of action memory.

Recent evidence highlights the critical role of effective interference inhibition for optimal memory performance, yet its function in action memory remains relatively underexplored. The current study investigated inhibitory processes in action memory during encoding and storage stages. In Experiment 1, 100 participants were divided into high and low cognitive inhibition groups using the Stroop color naming task. They performed either a subject-performed task (SPT) or a verbal task (VT) under varying semantic interference levels to assess the interaction between individual inhibitory abilities and the inhibition processing of action memory during encoding. Results indicated no significant difference in inhibition effects (IF) between high and low inhibition groups in SPT under high semantic interference, while in VT, those with high cognitive inhibition demonstrated significantly greater IF than those with low. Experiment 2, involving 57 participants, employed a point detection task and eye-tracking to explore attentional inhibition mechanisms during action memory storage. Behavioral results showed greater IF for SPT than VT under semantic interference. Eye-tracking revealed higher initial fixation rates and shorter durations for SPT subjects during the early processing stage, and significantly fewer and shorter fixations in the later stage compared to VT subjects. These findings imply stronger inhibitory processing in SPT during both encoding and storage stages under semantic interference, with attentional inhibition of action memories occurring predominantly in the later stage.

High Prevalence of Colistin-Resistant Encoding Genes Carriage among Patients and Healthy Residents in Vietnam.

Background and Objectives: We aimed to investigate the carriage of colistin-resistant genes among both patients with a history of antibiotic exposure and apparently healthy adults with no recent healthcare contact. Materials and Methods: Stool swabs were collected from healthy people, and specimens were collected at the infection foci from the patients. Eleven primer/probe sets were used to perform the Multiplex Real-Time PCR assay with the QuantiNova Multiplex Probe PCR kit for screening the carriage of colistin-resistant genes (mcr-1 to mcr-10) and 16S rRNA gene as internal control. Results: In total, 86 patients and 96 healthy residents were included. Twenty two patients (25.9%) were positive with at least one colistin-resistance encoding gene. The mcr-1 gene was the most frequent (16.5%), followed by mcr-9, mcr-6, and mcr-4 genes, where the prevalence was 11.8%, 10.6%, and 9.4%, respectively. No patient was positive with mcr-3, mcr-7, and mcr-8 genes. Eight patients (9.4%) were positive with multiple colistin-encoding genes. Twenty-three healthy people (24.0%) were positive with at least one colistin-resistance encoding gene, and the mcr-10 gene was the most frequent (27.0%), followed by the mcr-1, mcr-8, and mcr-9 genes, where the prevalence was 24.3%, 21.6%, and 13.5%, respectively. No person was positive with the mcr-2 and mcr-5 genes. Conclusions: Our findings underscore the urgent need for enhanced surveillance, infection control measures, and stewardship interventions to mitigate the spread of colistin resistance in Vietnam.

A Novel Detection Method for High-Order SNP Epistatic Interactions Based on Explicit-Encoding-Based Multitasking Harmony Search.

To elucidate the genetic basis of complex diseases, it is crucial to discover the single-nucleotide polymorphisms (SNPs) contributing to disease susceptibility. This is particularly challenging for high-order SNP epistatic interactions (HEIs), which exhibit small individual effects but potentially large joint effects. These interactions are difficult to detect due to the vast search space, encompassing billions of possible combinations, and the computational complexity of evaluating them. This study proposes a novel explicit-encoding-based multitasking harmony search algorithm (MTHS-EE-DHEI) specifically designed to address this challenge. The algorithm operates in three stages. First, a harmony search algorithm is employed, utilizing four lightweight evaluation functions, such as Bayesian network and entropy, to efficiently explore potential SNP combinations related to disease status. Second, a G-test statistical method is applied to filter out insignificant SNP combinations. Finally, two machine learning-based methods, multifactor dimensionality reduction (MDR) as well as random forest (RF), are employed to validate the classification performance of the remaining significant SNP combinations. This research aims to demonstrate the effectiveness of MTHS-EE-DHEI in identifying HEIs compared to existing methods, potentially providing valuable insights into the genetic architecture of complex diseases. The performance of MTHS-EE-DHEI was evaluated on twenty simulated disease datasets and three real-world datasets encompassing age-related macular degeneration (AMD), rheumatoid arthritis (RA), and breast cancer (BC). The results demonstrably indicate that MTHS-EE-DHEI outperforms four state-of-the-art algorithms in terms of both detection power and computational efficiency. The source code is available at https://github.com/shouhengtuo/MTHS-EE-DHEI.git .

Modeling the contribution of theta-gamma coupling to sequential memory, imagination, and dreaming.

Gamma oscillations nested in a theta rhythm are observed in the hippocampus, where are assumed to play a role in sequential episodic memory, i.e., memorization and retrieval of events that unfold in time. In this work, we present an original neurocomputational model based on neural masses, which simulates the encoding of sequences of events in the hippocampus and subsequent retrieval by exploiting the theta-gamma code. The model is based on a three-layer structure in which individual Units oscillate with a gamma rhythm and code for individual features of an episode. The first layer (working memory in the prefrontal cortex) maintains a cue in memory until a new signal is presented. The second layer (CA3 cells) implements an auto-associative memory, exploiting excitatory and inhibitory plastic synapses to recover an entire episode from a single feature. Units in this layer are disinhibited by a theta rhythm from an external source (septum or Papez circuit). The third layer (CA1 cells) implements a hetero-associative net with the previous layer, able to recover a sequence of episodes from the first one. During an encoding phase, simulating high-acetylcholine levels, the network is trained with Hebbian (synchronizing) and anti-Hebbian (desynchronizing) rules. During retrieval (low-acetylcholine), the network can correctly recover sequences from an initial cue using gamma oscillations nested inside the theta rhythm. Moreover, in high noise, the network isolated from the environment simulates a mind-wandering condition, randomly replicating previous sequences. Interestingly, in a state simulating sleep, with increased noise and reduced synapses, the network can "dream" by creatively combining sequences, exploiting features shared by different episodes. Finally, an irrational behavior (erroneous superimposition of features in various episodes, like "delusion") occurs after pathological-like reduction in fast inhibitory synapses. The model can represent a straightforward and innovative tool to help mechanistically understand the theta-gamma code in different mental states.

Effect of levels-of-processing on rates of forgetting.

The levels-of-processing (LOP) framework, proposing that deep processing yields superior retention, has provided an important paradigm for memory research and a practical means of improving learning. However, the available levels-of-processing literature focuses on immediate memory performance. It is assumed within the LOP framework that deep processing will lead to slower forgetting than will shallow processing. However, it is unclear whether, or how, the initial level of processing affects the forgetting slopes over longer retention intervals. The present three experiments were designed to explore whether items encoded at qualitatively different LOP are forgotten at different rates. In the first two experiments, depth of processing was manipulated within-participants at encoding under deep and shallow conditions (semantic vs. rhyme judgement in Experiment 1; semantic vs. consonant-vowel pattern decision in Experiment 2). Recognition accuracy (d prime) was measured between-participants immediately after learning and at 30-min, 2-h, and 24-h delays. The third experiment employed a between-participants design, contrasting the rates of forgetting following semantic and phonological (rhyme) processing at immediate, 30-min, 2-h, and 6-h delays. Results from the three experiments consistently demonstrated a large effect size of levels of processing on immediate performance and a medium-to-large level effect size on delayed recognition, but crucially no LOP × delay group interaction. Analysis of the retention curves revealed no significant differences between the slopes of forgetting for deep and shallow processing. These results suggest that the rates of forgetting are independent of the qualitatively distinct encoding operations manipulated by levels of processing.

Tuned exchange imaging: Can the filter exchange imaging pulse sequence be adapted for applications with thin slices and restricted diffusion?

Filter exchange imaging (FEXI) is a double diffusion-encoding (DDE) sequence that is specifically sensitive to exchange between sites with different apparent diffusivities. FEXI uses a diffusion-encoding filtering block followed by a detection block at varying mixing times to map the exchange rate. Long mixing times enhance the sensitivity to exchange, but they pose challenges for imaging applications that require a stimulated echo sequence with crusher gradients. Thin imaging slices require strong crushers, which can introduce significant diffusion weighting and bias exchange rate estimates. Here, we treat the crushers as an additional encoding block and consider FEXI as a triple diffusion-encoding sequence. This allows the bias to be corrected in the case of multi-Gaussian diffusion, but not easily in the presence of restricted diffusion. Our approach addresses challenges in the presence of restricted diffusion and relies on the ability to independently gauge sensitivities to exchange and restricted diffusion for arbitrary gradient waveforms. It follows two principles: (i) the effects of crushers are included in the forward model using signal cumulant expansion; and (ii) timing parameters of diffusion gradients in filter and detection blocks are adjusted to maintain the same level of restriction encoding regardless of the mixing time. This results in the tuned exchange imaging (TEXI) protocol. The accuracy of exchange mapping with TEXI was assessed through Monte Carlo simulations in spheres of identical sizes and gamma-distributed sizes, and in parallel hexagonally packed cylinders. The simulations demonstrate that TEXI provides consistent exchange rates regardless of slice thickness and restriction size, even with strong crushers. However, the accuracy depends on b-values, mixing times, and restriction geometry. The constraints and limitations of TEXI are discussed, including suggestions for protocol adaptations. Further studies are needed to optimize the precision of TEXI and assess the approach experimentally in realistic, heterogeneous substrates.

Encoding temporal information in deep convolution neural network.

A recent development in deep learning techniques has attracted attention to the decoding and classification of electroencephalogram (EEG) signals. Despite several efforts to utilize different features in EEG signals, a significant research challenge is using time-dependent features in combination with local and global features. Several attempts have been made to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information. These features are usually either handcrafted features, such as power ratios, or splitting data into smaller-sized windows related to specific properties, such as a peak at 300 ms. However, these approaches partially solve the problem but simultaneously hinder CNNs' capability to learn from unknown information that might be present in the data. Other approaches, like recurrent neural networks, are very suitable for learning time-dependent information from EEG signals in the presence of unrelated sequential data. To solve this, we have proposed an encoding kernel (EnK), a novel time-encoding approach, which uniquely introduces time decomposition information during the vertical convolution operation in CNNs. The encoded information lets CNNs learn time-dependent features in addition to local and global features. We performed extensive experiments on several EEG data sets-physical human-robot collaborations, P300 visual-evoked potentials, motor imagery, movement-related cortical potentials, and the Dataset for Emotion Analysis Using Physiological Signals. The EnK outperforms the state of the art with an up to 6.5% reduction in mean squared error (MSE) and a 9.5% improvement in F1-scores compared to the average for all data sets together compared to base models. These results support our approach and show a high potential to improve the performance of physiological and non-physiological data. Moreover, the EnK can be applied to virtually any deep learning architecture with minimal effort.

Episodic-like memory in wild free-living blue tits and great tits.

Episodic-like memory in non-human animals represents the behavioral characteristics of human episodic memory-the ability to mentally travel backward in time to "re-live" past experiences. A focus on traditional model species of episodic-like memory may overlook taxa possessing this cognitive ability and consequently its evolution across species. Experiments conducted in the wild have the potential to broaden the scope of episodic-like memory research under the natural conditions in which they evolved. We combine two distinct yet complementary episodic-like memory tasks (the what-where-when memory and incidental encoding paradigms), each targeting a different aspect of human episodic memory, namely the content (what-where-when) and process (incidental encoding), to comprehensively test the memory abilities of wild, free-living, non-caching blue tits (Cyanistes caeruleus) and great tits (Parus major). Automated feeders with custom-built programs allowed for experimental manipulation of spatiotemporal experiences on an individual-level basis. In the what-where-when memory experiment, after learning individualized temporal feeder rules, the birds demonstrated their ability to recall the "what" (food type), "where" (feeder location), and "when" (time since their initial visit of the day) of previous foraging experiences. In the incidental encoding experiment, the birds showed that they were able to encode and recall incidental spatial information regarding previous foraging experiences ("where" test), and juveniles, but not adults, were also able to recall incidentally encoded visual information ("which" test). Consequently, this study presents multiple lines of converging evidence for episodic-like memory in a wild population of generalist foragers, suggesting that episodic-like memory may be more taxonomically widespread than previously assumed.

Adult Neurogenesis, Context Encoding, and Pattern Separation: A Pathway for Treating Overgeneralization.

In mammals, the subgranular zone of the dentate gyrus is one of two brain regions (with the subventricular zone of the olfactory bulb) that continues to generate new neurons throughout adulthood, a phenomenon known as adult hippocampal neurogenesis (AHN) (Eriksson et al., Nat Med 4:1313-1317, 1998; García-Verdugo et al., J Neurobiol 36:234-248, 1998). The integration of these new neurons into the dentate gyrus (DG) has implications for memory encoding, with unique firing and wiring properties of immature neurons that affect how the hippocampal network encodes and stores attributes of memory. In this chapter, we will describe the process of AHN and properties of adult-born cells as they integrate into the hippocampal circuit and mature. Then, we will discuss some methodological considerations before we review evidence for the role of AHN in two major processes supporting memory that are performed by the DG. First, we will discuss encoding of contextual information for episodic memories and how this is facilitated by AHN. Second, will discuss pattern separation, a major role of the DG that reduces interference for the formation of new memories. Finally, we will review clinical and translational considerations, suggesting that stimulation of AHN may help decrease overgeneralization-a common endophenotype of mood, anxiety, trauma-related, and age-related disorders.

Event-related potentials during encoding coincide with subsequent forced-choice mnemonic discrimination.

Computational models and eye-tracking research suggest that encoding variability accounts for the reduced recognition of targets (A) when paired with non-corresponding lures (B') relative to corresponding lures (A'). The current study examined whether neural activity during learning coincided with subsequent performance on the forced-choice Mnemonic Similarity Task (MST). Event-related potential responses were collected during encoding while young adults completed A-B' and A-A' trials of the forced-choice MST. Consistent with previous research, performance was lower on A-B' trials than A-A' trials. The subsequent memory effect was not significant for the A-A' test format. However, for A-B' trials, we observed a significant Accuracy × Stimulus interaction 1000-1200 ms poststimulus onset across frontal and fronto-central electrodes. As hypothesized, subsequently correct A-B' trials were associated with a larger amplitude response at encoding to the target (A) than the original version of the non-corresponding lure (B). However, subsequently incorrect trials were associated with a larger amplitude response to the non-corresponding lure (B) than the target stimulus (A). These findings provide additional support for the effect of encoding variability on mnemonic discrimination.

Cross-correlation adjustment full-waveform inversion with source encoding in ultrasound computed tomography.

Full-waveform inversion (FWI) is one of the leading-edge techniques in ultrasound computed tomography (USCT). FWI reconstructs the images of sound speed by iteratively minimizing the difference between the predicted and measured signals. The challenges of FWI are to improve its stability and reduce its computational cost. In this paper, a new USCT algorithm based on cross-correlation adjustment FWI with source encoding (CCAFWI-SE) is proposed. In this algorithm, the gradient is adjusted using the intermediate signals as the inversion target rather than the measured signals during iteration. The intermediate signals are generated using the travel time difference calculated by cross-correlation. In the case of conventional FWI failure, using the proposed algorithm, the estimated sound speed can converge toward the ground truth. To reduce the computational cost, an intermittent update strategy is implemented. This strategy only requires one time for the calculation of the travel time difference per stage, so that the source encoding can be used. Simulation and laboratory experiments are implemented to validate this approach. The experiment results show it has successfully recovered the sound speed model, while conventional FWI failed when the initial model greatly differed from the ground truth. This verifies that our approach improves the stability of the reconstruction in USCT. In practice, additional computational costs can be reduced by combining our approach with existing methods. The proposed approach increases the robustness of the FWI and expands its application.

Mental state decoders: game-changers or wishful thinking?

Decoding mental and perceptual states using fMRI has become increasingly popular over the past two decades, with numerous highly-cited studies published in high-profile journals. Nevertheless, what have we learned from these decoders? In this opinion, we argue that fMRI-based decoders are not neurophysiologically informative and are not, and likely cannot be, applicable to real-world decision-making. The former point stems from the fact that decoding models cannot disentangle neural mechanisms from their epiphenomena. The latter point stems from both logical and ethical constraints. Constructing decoders requires precious time and resources that should instead be directed toward scientific endeavors more likely to yield meaningful scientific progress.

Coexistence of multidrug resistance and ESBL encoding genes - blaTEM, blaSHV, and blaCTX-M; its amplification and dispersion in the environment via municipal wastewater treatment plant.

Municipal wastewater treatment plants (MWWTPs) are a global source of antibiotic resistance genes (ARGs), collecting wastewater from a variety of sources, including hospital wastewater, domestic wastewater, runoff from agricultural and livestock farms, etc. These sources are contaminated with organic and inorganic pollutants, ARGs and antibiotic-resistant bacteria (ARB). Such pollutants aided eutrophication and encouraged bacterial growth. During bacterial growth horizontal gene transfer (HGT) and vertical gene transfer (VGT) of ARGs and extended-spectrum ß-lactamase (ESBL) encoding genes may facilitate, resulting in the spread of antibiotic resistance exponentially. The current study investigated the prevalence of multidrug resistance (MDR) and ESBL encoding genes in various treatment units of MWWTP and their spread in the environment. A total of three sampling sites (BUT, BRO, and BFB) were chosen, and 33 morphologically distinct bacterial colonies were isolated. 14 of the 33 isolates tested positive for antibiotic resistance and were further tested for the coexistence of MDR and ESBL production. The selected 14 isolates showed the highest resistance to trimethoprim (85.71%), followed by ciprofloxacin, azithromycin, and ampicillin (71.42%), tetracycline (57.14%), and vancomycin, gentamicin, and colistin sulphate (50%). A total of 9 isolates (64.28%) were phenotypically positive for ESBL production (BUT2, BUT3, BUT5, BRO1, BRO2, BRO3, BRO4, BRO5 and BFB1). The molecular detection of ESBL encoding genes, i.e. blaTEM, blaSHV, and blaCTX-M was carried out. The most prevalent gene was blaTEM (69.23%), followed by blaSHV (46.15%), and blaCTX-M (23.07%). In this study, 9 isolates (64.28%) out of 14 showed the coexistence of MDR and ESBL encoding genes, namely BUT3, BUT4, BUT5, BUT6, BUT7, BRO1, BRO2, BRO4, and BFB1. The coexistence of ESBL encoding genes and resistance to other antibiotic classes exacerbates human health and the environment.

Large-scale parameters framework with large convolutional kernel for encoding visual fMRI activity information.

Visual encoding models often use deep neural networks to describe the brain's visual cortex response to external stimuli. Inspired by biological findings, researchers found that large receptive fields built with large convolutional kernels improve convolutional encoding model performance. Inspired by scaling laws in recent years, this article investigates the performance of large convolutional kernel encoding models on larger parameter scales. This paper proposes a large-scale parameters framework with a sizeable convolutional kernel for encoding visual functional magnetic resonance imaging activity information. The proposed framework consists of three parts: First, the stimulus image feature extraction module is constructed using a large-kernel convolutional network while increasing channel numbers to expand the parameter size of the framework. Second, enlarging the input data during the training stage through the multi-subject fusion module to accommodate the increase in parameters. Third, the voxel mapping module maps from stimulus image features to functional magnetic resonance imaging signals. Compared to sizeable convolutional kernel visual encoding networks with base parameter scale, our visual encoding framework improves by approximately 7% on the Natural Scenes Dataset, the dedicated dataset for the Algonauts 2023 Challenge. We further analyze that our encoding framework made a trade-off between encoding performance and trainability. This paper confirms that expanding parameters in visual coding can bring performance improvements.

The combination operation of grouping and ensemble coding for structured biological motion crowds in working memory.

Massive studies have explored biological motion (BM) crowds processing for their remarkable social significance, primarily focused on uniformly distributed ones. However, real-world BM crowds often exhibit hierarchical structures rather than uniform arrangements. How such structured BM crowds are processed remains a subject of inquiry. This study investigates the representation of structured BM crowds in working memory (WM), recognizing the pivotal role WM plays in our social interactions involving BM. We propose the group-based ensemble hypothesis and test it through a member identification task. Participants were required to discern whether a presented BM belonged to a prior memory display of eight BM, each with distinct walking directions. Drawing on prominent Gestalt principles as organizational cues, we constructed structured groups within BM crowds by applying proximity and similarity cues in Experiments 1 and 2, respectively. In Experiment 3, we deliberately weakened the visibility of stimuli structures by increasing the similarity between subsets, probing the robustness of results. Consistently, our findings indicate that BM aligned with the mean direction of the subsets was more likely to be recognized as part of the memory stimuli. This suggests that WM inherently organizes structured BM crowds into separate ensembles based on organizational cues. In essence, our results illuminate the simultaneous operation of grouping and ensemble encoding mechanisms for BM crowds within WM.

How L2 Learners Process Different Means of Time Encoding in a Tenseless Language: An ERP Study of Mandarin.

In the past, research on the cognitive neural mechanism of second language (L2) learners' processing time information has focused on Indo-European languages. It has also focused on the temporal category expressed by morphological changes. However, there has been a lack of research on L2 learners' various time coding means, especially for Mandarin, which lacks morphological changes. Using event-related potentials (ERPs), we investigated the cognitive neural mechanism of L2 learners with native Indonesian background in processing two time coding means (time adverbs and aspect markers) in Chinese. Indonesian has time adverb encoding time information similar to that of Chinese, but there are no aspect markers similar to Chinese in Indonesian. We measured ERPs time locked to the time adverb " (cengjing)" and the aspect marker "verb + (verb + guo)" in two different conditions, i.e., a control condition (the correct sentence) and a temporal information violation. The experimental results showed that the native speaker group induced the biphasic N400-P600 effect under the condition of time adverb violation, and induced P600 under the condition of the aspect marker "verb + (verb + guo)" violation. Indonesian L2 learners of Chinese only elicited P600 for the violation of time adverbs, and there was no statistically significant N400 similar to that of Chinese native speakers. In the case of aspect marker violation, we observed no significant ERPs component for the Indonesian L2 learners of Chinese. Both groups of subjects induced elicited a widely distributed and sustained negativity on the post-critical words after "verb + (verb + guo)" and "(cengjing)". This showed that the neural mechanism of Indonesian L2 learners of Chinese processing Chinese time coding differs from that of Chinese native speakers.

Tensor-valued diffusion MRI detects brain microstructure changes in HIV infected individuals with cognitive impairment.

Despite advancements, the prevalence of HIV-associated neurocognitive impairment remains at approximately 40%, attributed to factors like pre-cART (combination antiretroviral therapy) irreversible brain injury. People with HIV (PWH) treated with cART do not show significant neurocognitive changes over relatively short follow-up periods. However, quantitative neuroimaging may be able to detect ongoing subtle microstructural changes. This study aimed to investigate the sensitivity of tensor-valued diffusion encoding in detecting such changes in brain microstructural integrity in cART-treated PWH. Additionally, it explored relationships between these metrics, neurocognitive scores, and plasma levels of neurofilament light (NFL) chain and glial fibrillary acidic protein (GFAP). Using MRI at 3T, 24 PWH and 31 healthy controls underwent cross-sectional examination. The results revealed significant variations in b-tensor encoding metrics across white matter regions, with associations observed between these metrics, cognitive performance, and blood markers of neuronal and glial injury (NFL and GFAP). Moreover, a significant interaction between HIV status and imaging metrics was observed, particularly impacting total cognitive scores in both gray and white matter. These findings suggest that b-tensor encoding metrics offer heightened sensitivity in detecting subtle changes associated with axonal injury in HIV infection, underscoring their potential clinical relevance in understanding neurocognitive impairment in PWH.

"Using network analysis modularity to group health code systems and decrease dimensionality in machine learning models".

Background: Machine learning (ML) prediction models in healthcare and pharmacy-related research face challenges with encoding high-dimensional Healthcare Coding Systems (HCSs) such as ICD, ATC, and DRG codes, given the trade-off between reducing model dimensionality and minimizing information loss. Objectives: To investigate using Network Analysis modularity as a method to group HCSs to improve encoding in ML models. Methods: The MIMIC-III dataset was utilized to create a multimorbidity network in which ICD-9 codes are the nodes and the edges are the number of patients sharing the same ICD-9 code pairs. A modularity detection algorithm was applied using different resolution thresholds to generate 6 sets of modules. The impact of four grouping strategies on the performance of predicting 90-day Intensive Care Unit readmissions was assessed. The grouping strategies compared: 1) binary encoding of codes, 2) encoding codes grouped by network modules, 3) grouping codes to the highest level of ICD-9 hierarchy, and 4) grouping using the single-level Clinical Classification Software (CCS). The same methodology was also applied to encode DRG codes but limiting the comparison to a single modularity threshold to binary encoding.The performance was assessed using Logistic Regression, Support Vector Machine with a non-linear kernel, and Gradient Boosting Machines algorithms. Accuracy, Precision, Recall, AUC, and F1-score with 95% confidence intervals were reported. Results: Models utilized modularity encoding outperformed ungrouped codes binary encoding models. The accuracy improved across all algorithms ranging from 0.736 to 0.78 for the modularity encoding, to 0.727 to 0.779 for binary encoding. AUC, recall, and precision also improved across almost all algorithms. In comparison with other grouping approaches, modularity encoding generally showed slightly higher performance in AUC, ranging from 0.813 to 0.837, and precision, ranging from 0.752 to 0.782. Conclusions: Modularity encoding enhances the performance of ML models in pharmacy research by effectively reducing dimensionality and retaining necessary information. Across the three algorithms used, models utilizing modularity encoding showed superior or comparable performance to other encoding approaches. Modularity encoding introduces other advantages such as it can be used for both hierarchical and non-hierarchical HCSs, the approach is clinically relevant, and can enhance ML models' clinical interpretation. A Python package has been developed to facilitate the use of the approach for future research.

Autosomal Recessive Hypophosphatemic Rickets Type 2 Associated with a Novel ENPP1 Variant in a Taiwanese Girl.

Autosomal recessive hypophosphatemic rickets (HR) type 2 (ARHR2) is a rare form of HR caused by variant of the gene encoding ectonucleotide pyrophosphatase/phosphodiesterase 1 (ENPP1). Our patient presented with a history of unsteady gait and progressively bowing legs that had commenced at the age of 1 year. Laboratory tests revealed an elevated level of fibroblast growth factor 23 (FGF23), hypophosphatemia, and a high urine phosphate level. Radiography revealed the typical features of rickets. Next-generation sequencing identified a previously reported c.783C>G (p.Tyr261Ter) and a novel c.1092-42A>G variant in the ENPP1 gene. The patient was prescribed oral phosphates and active vitamin D and underwent guided growth of both distal femora and proximal tibiae commencing at the age of 3 years. No evidence of generalized arterial calcification was apparent during follow-up, and growth rate was satisfactory.