Search for: All records

IntroductionEarly and accurate diagnosis of autism spectrum disorder (ASD) is crucial for effective intervention, yet it remains a significant challenge due to its complexity and variability. Micro-expressions are rapid, involuntary facial movements indicative of underlying emotional states. It is unknown whether micro-expression can serve as a valid bio-marker for ASD diagnosis. MethodsThis study introduces a novel machine-learning (ML) framework that advances ASD diagnostics by focusing on facial micro-expressions. We applied cutting-edge algorithms to detect and analyze these micro-expressions from video data, aiming to identify distinctive patterns that could differentiate individuals with ASD from typically developing peers. Our computational approach included three key components: (1) micro-expression spotting using Shallow Optical Flow Three-stream CNN (SOFTNet), (2) feature extraction via Micron-BERT, and (3) classification with majority voting of three competing models (MLP, SVM, and ResNet). ResultsDespite the sophisticated methodology, the ML framework's ability to reliably identify ASD-specific patterns was limited by the quality of video data. This limitation raised concerns about the efficacy of using micro-expressions for ASD diagnostics and pointed to the necessity for enhanced video data quality. DiscussionOur research has provided a cautious evaluation of micro-expression diagnostic value, underscoring the need for advancements in behavioral imaging and multimodal AI technology to leverage the full capabilities of ML in an ASD-specific clinical context. 

Abstract Diagnosing language disorders associated with autism is a complex and nuanced challenge, often hindered by the subjective nature and variability of traditional assessment methods. Traditional diagnostic methods not only require intensive human effort but also often result in delayed interventions due to their lack of speed and specificity. In this study, we explored the application of ChatGPT, a state-of-the-art large language model, to overcome these obstacles by enhancing diagnostic accuracy and profiling specific linguistic features indicative of autism. Leveraging ChatGPT's advanced natural language processing capabilities, this research aims to streamline and refine the diagnostic process. Specifically, we compared ChatGPT's performance with that of conventional supervised learning models, including BERT, a model acclaimed for its effectiveness in various natural language processing tasks. We showed that ChatGPT substantially outperformed these models, achieving over 13\% improvement in both accuracy and F1-score in a zero-shot learning configuration. This marked enhancement highlights the model’s potential as a superior tool for neurological diagnostics. Additionally, we identified ten distinct features of autism-associated language disorders that vary significantly across different experimental scenarios. These features, which included echolalia, pronoun reversal, and atypical language usage, were crucial for accurately diagnosing ASD and customizing treatment plans. Together, our findings advocate for adopting sophisticated AI tools like ChatGPT in clinical settings to assess and diagnose developmental disorders. Our approach not only promises greater diagnostic precision but also aligns with the goals of personalized medicine, potentially transforming the evaluation landscape for autism and similar neurological conditions. 

Raw wood was subjected to sequential oxidation to produce 2,3,6-tricarboxycellulose (TCC) nanofibers with a high surficial charge of 1.14 mmol/g in the form of carboxylate groups. Three oxidation steps, including nitro-oxidation, periodate, and sodium chlorite oxidation, were successfully applied to generate TCC nanofibers from raw wood. The morphology of extracted TCC nanofibers measured using TEM and AFM indicated the average length, width, and thickness were in the range of 750 ± 110, 4.5 ± 1.8, and 1.23 nm, respectively. Due to high negative surficial charges on TCC, it was studied for its absorption capabilities against Pb2+ ions. The remediation results indicated that a low concentration of TCC nanofibers (0.02 wt%) was able to remove a wide range of Pb2+ ion impurities from 5–250 ppm with an efficiency between 709–99%, whereby the maximum adsorption capacity (Qm) was 1569 mg/g with R2 0.69531 calculated from Langmuir fitting. It was observed that the high adsorption capacity of TCC nanofibers was due to the collective effect of adsorption and precipitation confirmed by the FTIR and SEM/EDS analysis. The high carboxylate content and fiber morphology of TCC has enabled it as an excellent substrate to remove Pb2+ ions impurities. 

In this study, granulated activated charcoal (GAC) and bio charcoal (BC) is used as a filler in P3 biosand bag filter to study their filtration performance against a range of fluoride impurities from 1–1400 mg/L. A set of experiments are done to analyze the filtration efficiency of the sandbag filter against fluoride impurities after incorporating different amounts (e.g., 0.2, 2 kg) and a combination of GAC and BC. A combination of filler GAC and BC (1 kg each) have exhibited excellent results with 100% fluoride removal efficiency against 5 mg/L fluoride impurities for an entire experimental time of 165 min. It is because of the synergetic effect of adsorption caused by the high surface area (739 m2/g) of GAC and hydroxyapatite groups in BC. The data from remediation experiments using individual GAC and BC are fitted into the Langmuir and Freundlich Isotherm Models to check their adsorption mechanism and determine GAC and BC’s maximum adsorption capacity (Qm). The remediation data for both GAC and BC have shown the better fitting to the Langmuir Isotherm Model with a high R2 value of 0.994 and 0.970, respectively, showing the excellent conformity with monolayer adsorption. While the GAC and BC have presented negative Kf values of −1.08 and −0.72, respectively, for Freundlich Model, showing the non-conformity to multilayer adsorption. The Qm values obtained from Langmuir Model for GAC is 6.23 mg/g, and for BC, it is 9.13 mg/g. The pH study on adsorption efficiency of individual GAC and BC against 5 mg/L of fluoride impurities indicates the decrease in removal efficiency with an increase in pH from 3 to 9. For example, BC has shown removal efficiency of 99.8% at pH 3 and 99.5% at pH 9, while GAC has exhibited removal efficiency of 96.1% at pH 3 and 95.9% at pH 9. Importantly, this study presents the significance of the synergetic application of GAC and BC in the filters, where GAC and BC are different in their origin, functionalities, and surface characteristics.