Search

Featured Application: This study explores the potential of two popular open-source AI models, ChatGPT 4o (omni) and Gemini Pro, to analyze MRI video sequences depicting a pediatric brain tumor. We aimed to evaluate whether these AI models can accurately identify and analyze the content of MRI videos showing a medulloblastoma in sagittal and coronal planes. Our findings revealed that while Gemini Pro correctly identified the video as an MRI, it did not attempt a detailed analysis, deferring to medical specialists. Conversely, ChatGPT 4o performed some image analysis but failed to recognize the video content as MRI. Both models struggled with tumor identification, suggesting that further improvements and specialized training are needed for these AI models to effectively support medical diagnostics. Over the past year, there has been a significant rise in interest in the application of open-source artificial intelligence models (OSAIM) in the field of medicine. An increasing number of studies focus on evaluating the capabilities of these models in image analysis, including magnetic resonance imaging (MRI). This study aimed to investigate whether two of the most popular open-source AI models, namely ChatGPT 4o and Gemini Pro, can analyze MRI video sequences with single-phase contrast in sagittal and frontal projections, depicting a posterior fossa tumor corresponding to a medulloblastoma in a child. The study utilized video files from single-phase contrast-enhanced head MRI in two planes (frontal and sagittal) of a child diagnosed with a posterior fossa tumor, type medulloblastoma, confirmed by histopathological examination. Each model was separately provided with the video file, first in the sagittal plane, analyzing three different sets of commands from the most general to the most specific. The same procedure was applied to the video file in the frontal plane. The Gemini Pro model did not conduct a detailed analysis of the pathological change but correctly identified the content of the video file, indicating it was a brain MRI, and suggested that a specialist in the field should perform the evaluation. Conversely, ChatGPT 4o conducted image analysis but failed to recognize that the content was MRI. The attempts to detect the lesion were random and varied depending on the plane. These models could not accurately identify the video content or indicate the area of the neoplastic change, even after applying detailed queries. The results suggest that despite their widespread use in various fields, these models require further improvements and specialized training to effectively support medical diagnostics. [ABSTRACT FROM AUTHOR]

Background: Open-source artificial intelligence models (OSAIMs) are increasingly being applied in various fields, including IT and medicine, offering promising solutions for diagnostic and therapeutic interventions. In response to the growing interest in AI for clinical diagnostics, we evaluated several OSAIMs—such as ChatGPT 4, Microsoft Copilot, Gemini, PopAi, You Chat, Claude, and the specialized PMC-LLaMA 13B—assessing their abilities to classify scoliosis severity and recommend treatments based on radiological descriptions from AP radiographs. Methods: Our study employed a two-stage methodology, where descriptions of single-curve scoliosis were analyzed by AI models following their evaluation by two independent neurosurgeons. Statistical analysis involved the Shapiro–Wilk test for normality, with non-normal distributions described using medians and interquartile ranges. Inter-rater reliability was assessed using Fleiss' kappa, and performance metrics, like accuracy, sensitivity, specificity, and F1 scores, were used to evaluate the AI systems' classification accuracy. Results: The analysis indicated that although some AI systems, like ChatGPT 4, Copilot, and PopAi, accurately reflected the recommended Cobb angle ranges for disease severity and treatment, others, such as Gemini and Claude, required further calibration. Particularly, PMC-LLaMA 13B expanded the classification range for moderate scoliosis, potentially influencing clinical decisions and delaying interventions. Conclusions: These findings highlight the need for the continuous refinement of AI models to enhance their clinical applicability. [ABSTRACT FROM AUTHOR]

Simple Summary: Lung cancer is the foremost cause of cancer incidence and mortality on a global scale, and effective treatment often involves surgical removal of lung tissue. This study aimed to create a comprehensive version of the International Classification of Functioning, Disability and Health (ICF) tailored for patients with lung cancer after thoracic surgery undergoing pulmonary rehabilitation. By assessing patients' functional profiles and levels of disability using this comprehensive ICF Core Set and the WHO Disability Assessment Schedule (WHODAS 2.0), the research sought to better understand the impact of lung cancer and its treatment on daily life. The findings suggest that the tailored ICF tool effectively captures the functional status of these patients, highlighting its potential utility in improving clinical practice and patient rehabilitation. This research may significantly impact the medical community by providing a comprehensive framework for evaluating and managing the functional health of lung cancer patients post-surgery. Worldwide, lung cancer remains the predominant cause of cancer cases and deaths and poses significant health challenges, with surgical resection being a key treatment. Post-surgery, patients often experience functional impairments. This study aimed to develop a comprehensive ICF version for assessing the functional profile and disability in lung cancer patients post-thoracic surgery undergoing pulmonary rehabilitation using the ICF and WHODAS 2.0 tool. We analyzed the correlation between the ICF Core Set and WHODAS 2.0 data to understand the impact on daily functioning. This study included 50 patients (23 F, 27 M) from the Clinic of Thoracic Surgery and Respiratory Rehabilitation in Lodz. Essential ICF codes were determined using the Delphi method, and assessments were conducted on the third day post-operation. Statistical analyses included various tests with α = 0.05. The results showed no impairments in voice functions (b310), respiration rates (b4400), and diaphragm functions (b4451), but there were significant issues with chest pain (b28011), respiratory muscle functions (b445), exercise tolerance (b455), and muscle endurance (b740). In Activities and Participation and Environmental Factors, most codes were not problematic, except for employment (d845, d850) and atmospheric pressure (e2252). Significant correlations were found between mobility limitations (d410, d460) and self-care (d510, d540) with the WHODAS 2.0 results. The comprehensive ICF Core Set effectively described the functional profile of post-surgery patients, confirming its utility and highlighting the impact of disability on daily functioning. [ABSTRACT FROM AUTHOR]

The application of artificial intelligence (AI) in the analysis of molecular biology data is becoming increasingly widespread. The Western Blot (WB) technique, a cornerstone in proteomic research, facilitates the identification and analysis of proteins, such as the frameshift mutant of ubiquitin B (UBB+1). In our study, we attempted to assess the potential of four different AI models—Gemini, Gemini Advanced, Microsoft Copilot, and ChatGPT 4—in the analysis of WB imagery containing UBB+1, derived from peripheral blood studies of patients suffering from schizophrenia. Participants, all male and diagnosed with schizophrenia, were recruited from the Specialist Psychiatric Care Team of Babinski Hospital in Lodz. After obtaining their informed consent, blood samples were collected and transported to the laboratory of the Department of Medical Biochemistry at the Medical University of Lodz. The samples were processed, synthesis of Ub-48UBB+1 dimers was performed, and the WB technique was applied. The result of the WB analysis, in the form of a photograph with basic labels but without a legend (JPG format), was implemented into ChatGPT 4, Microsoft Copilot, Gemini and Gemini Advanced. Following the implementation of the image, the command 'Could you analyze the attached photo?' was added, along with the protocol from Sample Preparation and Synthesis of Ub-48UBB+1 Dimers. The AI models effectively analyzed and interpreted WB images, with variations in their approaches and depth. Gemini excelled in detailing the WB process and biological significance of bands, while Gemini Advanced focused on specific band identification, especially Ub-48UBB+1 dimers. Microsoft Copilot provided a basic overview with less technicality, and ChatGPT 4 offered comprehensive band interpretations, linking them to patient samples and standards, thus confirming the hypothesis about the differing capabilities of these models. This discovery demonstrates the advanced capabilities of ChatGPT 4 and highlights the growing role of AI in scientific research, including the interpretation of results. [ABSTRACT FROM AUTHOR]

Open-source artificial intelligence models (OSAIM) find free applications in various industries, including information technology and medicine. Their clinical potential, especially in supporting diagnosis and therapy, is the subject of increasingly intensive research. Due to the growing interest in artificial intelligence (AI) for diagnostic purposes, we conducted a study evaluating the capabilities of AI models, including ChatGPT and Microsoft Bing, in the diagnosis of single-curve scoliosis based on posturographic radiological images. Two independent neurosurgeons assessed the degree of spinal deformation, selecting 23 cases of severe single-curve scoliosis. Each posturographic image was separately implemented onto each of the mentioned platforms using a set of formulated questions, starting from 'What do you see in the image?' and ending with a request to determine the Cobb angle. In the responses, we focused on how these AI models identify and interpret spinal deformations and how accurately they recognize the direction and type of scoliosis as well as vertebral rotation. The Intraclass Correlation Coefficient (ICC) with a 'two-way' model was used to assess the consistency of Cobb angle measurements, and its confidence intervals were determined using the F test. Differences in Cobb angle measurements between human assessments and the AI ChatGPT model were analyzed using metrics such as RMSEA, MSE, MPE, MAE, RMSLE, and MAPE, allowing for a comprehensive assessment of AI model performance from various statistical perspectives. The ChatGPT model achieved 100% effectiveness in detecting scoliosis in X-ray images, while the Bing model did not detect any scoliosis. However, ChatGPT had limited effectiveness (43.5%) in assessing Cobb angles, showing significant inaccuracy and discrepancy compared to human assessments. This model also had limited accuracy in determining the direction of spinal curvature, classifying the type of scoliosis, and detecting vertebral rotation. Overall, although ChatGPT demonstrated potential in detecting scoliosis, its abilities in assessing Cobb angles and other parameters were limited and inconsistent with expert assessments. These results underscore the need for comprehensive improvement of AI algorithms, including broader training with diverse X-ray images and advanced image processing techniques, before they can be considered as auxiliary in diagnosing scoliosis by specialists. [ABSTRACT FROM AUTHOR]

The ubiquitin-proteasome system (UPS) is a pivotal cellular mechanism responsible for the selective degradation of proteins, playing an essential role in proteostasis, protein quality control, and regulating various cellular processes, with ubiquitin marking proteins for degradation through a complex, multi-stage process. The shuttle proteins family is a very unique group of proteins that plays an important role in the ubiquitin-proteasome system. Ddi1, Dsk2, and Rad23 are shuttle factors that bind ubiquitinated substrates and deliver them to the 26S proteasome. Besides mediating the delivery of ubiquitinated proteins, they are also involved in many other biological processes. Ddi1, the least-studied shuttle protein, exhibits unique physicochemical properties that allow it to play non-canonical functions in the cells. It regulates cell cycle progression and response to proteasome inhibition and defines MAT type of yeast cells. The Ddi1 contains UBL and UBA domains, which are crucial for binding to proteasome receptors and ubiquitin respectively, but also an additional domain called RVP. Additionally, much evidence has been provided to question whether Ddi1 is a classical shuttle protein. For many years, the true nature of this protein remained unclear. Here, we highlight the recent discoveries, which shed new light on the structure and biological functions of the Ddi1 protein. [ABSTRACT FROM AUTHOR]

Open-source artificial intelligence models are finding free application in various industries, including computer science and medicine. Their clinical potential, especially in assisting diagnosis and therapy, is the subject of increasingly intensive research. Due to the growing interest in AI for diagnostics, we conducted a study evaluating the abilities of AI models, including ChatGPT, Microsoft Bing, and Scholar AI, in classifying single-curve scoliosis based on radiological descriptions. Fifty-six posturographic images depicting single-curve scoliosis were selected and assessed by two independent neurosurgery specialists, who classified them as mild, moderate, or severe based on Cobb angles. Subsequently, descriptions were developed that accurately characterized the degree of spinal deformation, based on the measured values of Cobb angles. These descriptions were then provided to AI language models to assess their proficiency in diagnosing spinal pathologies. The artificial intelligence models conducted classification using the provided data. Our study also focused on identifying specific sources of information and criteria applied in their decision-making algorithms, aiming for a deeper understanding of the determinants influencing AI decision processes in scoliosis classification. The classification quality of the predictions was evaluated using performance evaluation metrics such as sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and balanced accuracy. Our study strongly supported our hypothesis, showing that among four AI models, ChatGPT 4 and Scholar AI Premium excelled in classifying single-curve scoliosis with perfect sensitivity and specificity. These models demonstrated unmatched rater concordance and excellent performance metrics. In comparing real and AI-generated scoliosis classifications, they showed impeccable precision in all posturographic images, indicating total accuracy (1.0, MAE = 0.0) and remarkable inter-rater agreement, with a perfect Fleiss' Kappa score. This was consistent across scoliosis cases with a Cobb's angle range of 11–92 degrees. Despite high accuracy in classification, each model used an incorrect angular range for the mild stage of scoliosis. Our findings highlight the immense potential of AI in analyzing medical data sets. However, the diversity in competencies of AI models indicates the need for their further development to more effectively meet specific needs in clinical practice. [ABSTRACT FROM AUTHOR]

Lung cancer often presents with pain and breathlessness, frequently necessitating surgical procedures, such as lung lobectomy. A pivotal component of postoperative care is rehabilitation, aimed not only at improving the clinical condition but also at influencing the patient's functional profile. In a study conducted at the Clinic of Thoracic Surgery and Respiratory Rehabilitation in the Regional Multispecialist Center for Oncology and Traumatology of the Nicolaus Copernicus Memorial Hospital in Lodz, the effectiveness of rehabilitation intervention was assessed in 50 patients (n = 27 M, n = 23 F) postlobectomy due to early stage nonsmall cell lung cancer (NSCLC). The International Classification of Functioning, Disability, and Health—ICF Rehabilitation Core Set was used to evaluate the functional profile, the modified Laitinen scale for pain assessment, and the modified Borg scale for breathlessness evaluation. Additionally, lung-expansion time was monitored. The significance level of the statistical tests in this analysis was set at α = 0.05. The study employed an analysis of the normality of the distributions of the numerical variables, reporting of variable distributions, estimation of differences between groups, estimation of differences within groups, estimation of the independence of categorical variables, and regression analysis. The research confirmed that rehabilitation partially improves the functional profile of patients and reduces the sensation of breathlessness postsurgery. The study highlighted the need for future research with a larger number of participants and an extended observation period to gain a deeper understanding of the impact of rehabilitation on patients after lung lobectomy procedures. [ABSTRACT FROM AUTHOR]

Assessing severe scoliosis requires the analysis of posturographic X-ray images. One way to analyse these images may involve the use of open-source artificial intelligence models (OSAIMs), such as the contrastive language–image pretraining (CLIP) system, which was designed to combine images with text. This study aims to determine whether the CLIP model can recognise visible severe scoliosis in posturographic X-ray images. This study used 23 posturographic images of patients diagnosed with severe scoliosis that were evaluated by two independent neurosurgery specialists. Subsequently, the X-ray images were input into the CLIP system, where they were subjected to a series of questions with varying levels of difficulty and comprehension. The predictions obtained using the CLIP models in the form of probabilities ranging from 0 to 1 were compared with the actual data. To evaluate the quality of image recognition, true positives, false negatives, and sensitivity were determined. The results of this study show that the CLIP system can perform a basic assessment of X-ray images showing visible severe scoliosis with a high level of sensitivity. It can be assumed that, in the future, OSAIMs dedicated to image analysis may become commonly used to assess X-ray images, including those of scoliosis. [ABSTRACT FROM AUTHOR]

We present a case of a child who was transported to the Neurosurgery Clinic from another hospital for the purpose of performing a surgical procedure of the spinal myelomeningocele. On the first day of the stay, a set of tests was performed, including an anterior-posterior (AP) projection X-ray, which clearly showed a developmental defect in the lumbar-sacral section of the spine. In the follow-up physical examination, there was a depression of the skin on the right side of the surgical scar after closing the open myelomeningocele. In the follow-up MRI of the lumbar-sacral section, an extremely rare congenital anterior dislocation of the sacrococcygeal bone was unexpectedly visualized. Despite recommendations for further diagnostics, the patient did not attend the required follow-up examinations. In the final section, we provide a general summary of the literature on rare developmental defects of the spine in children. [ABSTRACT FROM AUTHOR]

Numerous molecular factors disrupt the correctness of the cell cycle process leading to the development of cancer due to increased cell proliferation. Among known causative factors of such process is abnormal gene expression. Nowadays in the light of current knowledge such alterations are frequently considered in the context of mRNA–miRNA correlation. One of the molecular factors with potential value in tumorigenesis is the feedback loop between MYC and E2F genes in which miR-17-5p and miR-20a from the miR-17-92 cluster are involved. The current literature shows that overexpression of the members of the OncomiR-1 are involved in the development of many solid tumors. In the present work, we investigated the expression of components of the MYC/E2F/miR-17-92 network and their closely related elements including members of MYC and E2F families and miRNAs from two paralogs of miR-17-92: miR-106b-25 and miR-106a-363, in the most common brain tumors of childhood, pilocytic astrocytoma (PA), WHO grade 1; ependymoma (EP), WHO grade 2; and medulloblastoma (MB), WHO grade 4. We showed that the highest gene expression was observed in the MYC family for MYCN and in the E2F family for E2F2. Positive correlation was observed between the gene expression and tumor grade and type, with the highest expression being noted for medulloblastomas, followed by ependymomas, and the lowest for pilocytic astrocytomas. Most members of miR-17-92, miR-106a-363 and miR-106b-25 clusters were upregulated and the highest expression was noted for miR-18a and miR-18b. The rest of the miRNAs, including miR-19a, miR-92a, miR-106a, miR-93, or miR-25 also showed high values. miR-17-5p, miR-20a obtained a high level of expression in medulloblastomas and ependymomas, while close to the control in the pilocytic astrocytoma samples. miRNA expression also depended on tumor grade and histology. [ABSTRACT FROM AUTHOR]