Vinicius Monteiro de Paula Guirado

The increasing demand for proactive patient out-reach and follow-up within health insurance providers and large hospital systems has led to the adoption of automated message classification systems. Although state-of-the-art tools like Azure and OpenAI o1 series are available, their costs are prohibitive for small companies. Therefore, using cost-effective traditional tools for text classification is still a valuable alternative. This study investigates how OpenAI's ChatGPT can generate synthetic data to balance class distributions in medical message datasets and improve the performance of binary classification models. The primary aim is to classify messages that indicate medical needs, aiding in patient outreach and efficient resource allocation. We applied Natural Language Processing (NLP) techniques, including Logistic Regression, Naive Bayes, Random Forest, XGBoost, and BERTimbau, a Portuguese transformer-based model. Models were trained on both original and augmented datasets, and results showed a significant increase in classification accuracy, particularly with BERTimbau, whose performance improved from 84% to 99%. Synthetic data also reduced overfitting by narrowing the gap between training and validation accuracies while improving model robustness on unseen data. Our findings demonstrate that synthetic data from ChatGPT effectively addresses class imbalance, improving the robustness and accuracy of medical message classification models. However, challenges remain in correctly classifying non-medical messages, indicating that further refinement in synthetic data generation is necessary for optimal performance in real-world scenarios. These results suggest that such approaches can significantly enhance automated patient engagement efforts.

Chronic pain incurs substantial global healthcare costs, requiring long-term specialized care. However, the variability in treatment approaches hampers the feasibility of value-based healthcare. To advance management and prevention efforts, data science tools like supervised and unsupervised machine learning algorithms offer promising solutions. This study employed data from six questionnaires to evaluate pain conditions in patients. Correlation techniques were applied to determine the questions most strongly correlated with low back pain, back pain, and leg pain. Five machine learning algorithms predicted the presence or absence of pain in the low back region. Seven variables were identified as input for the prediction models, with the XBoost Classifier demonstrating the highest accuracy, precision, recall, and F1-Score (0.8 accuracy, precision, recall; 0.78 F1-Score). By incorporating the machine learning model, it predicts the allocation of chronic back pain patients to integrated practice in a value-based healthcare system. Finally, our findings show that data science methods, such as machine learning, improve chronic pain management, expedite surveys, and improve value-based healthcare through efficient allocation. Highlights Correlation analysis identified pain-related questions (back, leg, chronic low back). 7 characteristics used by ML algorithms to forecast chronic low back pain occurrence. XBoost algorithm and neural network achieved best performance (Precision, Recall ∼0.8). Outcomes aid patient allocation, screening, and reducing costs in value-based healthcare. Streamlining surveys boosts response rates and enables larger datasets for improved modeling.

This descriptive narrative review demonstrates state-of-the-art epidemiological research in glioblastoma (GB). We discussed the case number and deaths worldwide and the intrinsic and extrinsic risk factors (RF) in cancer analytical epidemiology. GB is the most common glioma, with increased cases in recent decades. Despite much research in the last decades, GB is a disease with a poor survival prognosis. The difference in the amount of data between developed and other countries is notable, as shown in our review. Many intrinsic and extrinsic RF have been studied for GB in recent years, resulting in few conclusions, with cases being more common in older, white, and male patients. In contrast to other review articles, which include more than one neuro-oncological disease, this paper concentrates on GB epidemiological data, including neglected countries. Moreover, we demonstrate and discuss GB’s most recent molecular classification for discovering new molecular markers for prognosis and treatment. More studies are needed to understand extrinsic RF and elucidate contradictory results from the literature. While highlighting the differences between developed and in-development countries, this review can provide grounds for future research in neglected regions, helping improve the quality of living in GB patients.

Background: Diffuse axonal injury occurs with high acceleration and deceleration forces in traumatic brain injury (TBI). This lesion leads to disarrangement of the neuronal network, which can result in some degree of deficiency. The Extended Glasgow Outcome Scale (GOS-E) is the primary outcome instrument for the evaluation of TBI victims. Diffusion tensor imaging (DTI) assesses white matter (WM) microstructure based on the displacement distribution of water molecules. Objective: To investigate WM microstructure within the first year after TBI using DTI, the patient’s clinical outcomes, and associations. Methods: We scanned 20 moderate and severe TBI victims at 2 months and 1 year after the event. Imaging processing was done with the FMRIB software library; we used the tract-based spatial statistics software yielding fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) for statistical analyses. We computed the average difference between the two measures across subjects and performed a one-sample t-test and threshold-free cluster enhancement, using a corrected p-value < 0.05. Clinical outcomes were evaluated with the GOS-E. We tested for associations between outcome measures and significant mean FA clusters. Results: Significant clusters of altered FA were identified anatomically using the JHU WM atlas. We found increasing spotted areas of FA with time in the right brain hemisphere and left cerebellum. Extensive regions of increased MD, RD, and AD were observed. Patients presented an excellent overall recovery. Conclusions: There were no associations between FA and outcome scores, but we cannot exclude the existence of a small to moderate association.

Introduction Deficits in episodic memory following traumatic brain injury (TBI) are common and affect independence in activities of daily living. Transcranial direct current stimulation (tDCS) and concurrent cognitive training may contribute to improve episodic memory in patients with TBI. Although previous studies have shown the potential of tDCS to improve cognition, the benefits of the tDCS applied simultaneously to cognitive training in participants with neurological disorders are inconsistent. This study aims to (1) investigate whether active tDCS combined with computer-assisted cognitive training enhances episodic memory compared with sham tDCS; (2) compare the differences between active tDCS applied over the left dorsolateral prefrontal cortex (lDLPFC) and bilateral temporal cortex (BTC) on episodic memory and; (3) investigate inter and intragroup changes on cortical activity measured by quantitative electroencephalogram (qEEG). Methods and analysis A randomised, parallel-group, double-blind placebo-controlled study is conducted. Thirty-six participants with chronic, moderate and severe closed TBI are being recruited and randomised into three groups (1:1:1) based on the placement of tDCS sponges and electrode activation (active or sham). TDCS is applied for 10 consecutive days for 20 min, combined with a computer-based cognitive training. Cognitive scores and qEEG are collected at baseline, on the last day of the stimulation session, and 3 months after the last tDCS session. We hypothesise that (1) the active tDCS group will improve episodic memory scores compared with the sham group; (2) differences on episodic memory scores will be shown between active BTC and lDLPFC and; (3) there will be significant delta reduction and an increase in alpha waves close to the location of the active electrodes compared with the sham group. Ethics and dissemination This study was approved by Hospital das Clínicas, University of São Paulo Ethical Institutional Review Border (CAAE: 87954518.0.0000.0068). Trial registration number NCT04540783.

Background and aim Diffusion tensor imaging (DTI) parameters in the corpus callosum have been suggested to be a biomarker for prognostic outcomes in individuals with diffuse axonal injury (DAI). However, differences between the DTI parameters on moderate and severe trauma in DAI over time are still unclear. A secondary goal was to study the association between the changes in the DTI parameters, anxiety, and depressive scores in DAI over time. Methods Twenty subjects were recruited from a neurological outpatient clinic and evaluated at 2, 6, and 12 months after the brain injury and compared to matched age and sex healthy controls regarding the DTI parameters in the corpus callosum. State-Trace Anxiety Inventory and Beck Depression Inventory were used to assess psychiatric outcomes in the TBI group over time. Results Differences were observed in the fractional anisotropy and mean diffusivity of the genu, body, and splenium of the corpus callosum between DAI and controls (p < 0.02). Differences in both parameters in the genu of the corpus callosum were also detected between patients with moderate and severe DAI (p < 0.05). There was an increase in the mean diffusivity values and the fractional anisotropy decrease in the DAI group over time (p < 0.02). There was no significant correlation between changes in the fractional anisotropy and mean diffusivity across the study and psychiatric outcomes in DAI. Conclusion DTI parameters, specifically the mean diffusivity in the corpus callosum, may provide reliable characterization and quantification of differences determined by the brain injury severity. No correlation was observed with DAI parameters and the psychiatric outcome scores.

A qualidade de vida consiste na percepção do indivíduo de sua posição na vida, no contexto da cultura e do sistema de valores nos quais vive, incluindo suas metas, expectativas, padrões e interesses. Objetivo: Avaliar a qualidade de vida de trabalhadores por meio do Instrumento SF-36, antes e durante a pandemia de COVID-19, buscando identificar quais dimensões destas relações foram influenciadas pela situação. Método: Os sujeitos escolhidos foram os trabalhadores de uma empresa do Vale do Paraíba Paulista. O questionário foi aplicado no período de trabalho por um único avaliador. Primeiramente, foi realizada a seleção de horários e dias possíveis para a aplicação do SF36, que ocorreu no ambulatório da empresa, apenas com funcionários voluntários. Foi estabelecido rapport (motivação, esclarecimento sobre a pesquisa, não obrigatoriedade da participação e sigilo), com posterior tratamento estatístico dos dados. Resultados: A empresa possui 136 funcionários, sendo 26 mulheres e 110 homens. Destes, 92% responderam ao questionário SF-36 em duas ocasiões, sendo a primeira no início do ano de 2020 e a outra durante o período de pandemia COVID-19 (a partir de abril de 2020). Conclusão: A condicionante da pandemia apresentou grande interferência nos processos de interpretação da qualidade de vida dos funcionários avaliados. Propõe-se uma futura pesquisa após a pandemia para avaliar a amplitude dos resultados aqui observados.  

Autops Case Rep, vol.9, n4, e2019105, 2019