Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

An excess of amyloid beta (Aβ) led to a rise in ROS production, which in turn caused inflammatory reactions and mitochondrial dysfunction, both of which accelerate the progression of Alzheimer’s disease (AD).Natural flavonoids are proposed as possible agents for neurodegeneration. Pectolinarin is an important flavone mainly found in Cirsium species. In this study, we explored the potential neuroprotective effect of pectolinarin in Aβ25-35 -induced SH-SY5Y cells. The result demonstrated that pectolinarin enhanced cell viability. Pectolinarin treatment inhibited Aβ25-35 -induced ROS generation. Pectolinarin also suppressed NO generation by inhibiting the translocation of NF-ĸB and downregulating protein expression of iNOS and COX-2. Moreover, the expression of Bcl-2 increased while BAX protein decreased when the cells were exposed to pectolinarin, resulting in a decrease in the BAX/Bcl-2 ratio. Pectolinarin treatment also increased BDNF and its receptor TrkB protein expression. In conclusion, pectolinarin neuroprotected Aβ25-35 -induced inflammation and apoptosis. These findings suggest that pectolinarin may be a promising neuroprotective functional food in the protection of the neurodegenerative diseases, including AD.

An excess of amyloid beta (Aβ) led to a rise in ROS production, which in turn caused inflammatory reactions and mitochondrial dysfunction, both of which accelerate the progression of Alzheimer’s disease (AD).Natural flavonoids are proposed as possible agents for neurodegeneration. Pectolinarin is an important flavone mainly found in Cirsium species. In this study, we explored the potential neuroprotective effect of pectolinarin in Aβ25-35 -induced SH-SY5Y cells. The result demonstrated that pectolinarin enhanced cell viability. Pectolinarin treatment inhibited Aβ25-35 -induced ROS generation. Pectolinarin also suppressed NO generation by inhibiting the translocation of NF-ĸB and downregulating protein expression of iNOS and COX-2. Moreover, the expression of Bcl-2 increased while BAX protein decreased when the cells were exposed to pectolinarin, resulting in a decrease in the BAX/Bcl-2 ratio. Pectolinarin treatment also increased BDNF and its receptor TrkB protein expression. In conclusion, pectolinarin neuroprotected Aβ25-35 -induced inflammation and apoptosis. These findings suggest that pectolinarin may be a promising neuroprotective functional food in the protection of the neurodegenerative diseases, including AD.

An excess of amyloid beta (Aβ) led to a rise in ROS production, which in turn caused inflammatory reactions and mitochondrial dysfunction, both of which accelerate the progression of Alzheimer’s disease (AD).Natural flavonoids are proposed as possible agents for neurodegeneration. Pectolinarin is an important flavone mainly found in Cirsium species. In this study, we explored the potential neuroprotective effect of pectolinarin in Aβ25-35 -induced SH-SY5Y cells. The result demonstrated that pectolinarin enhanced cell viability. Pectolinarin treatment inhibited Aβ25-35 -induced ROS generation. Pectolinarin also suppressed NO generation by inhibiting the translocation of NF-ĸB and downregulating protein expression of iNOS and COX-2. Moreover, the expression of Bcl-2 increased while BAX protein decreased when the cells were exposed to pectolinarin, resulting in a decrease in the BAX/Bcl-2 ratio. Pectolinarin treatment also increased BDNF and its receptor TrkB protein expression. In conclusion, pectolinarin neuroprotected Aβ25-35 -induced inflammation and apoptosis. These findings suggest that pectolinarin may be a promising neuroprotective functional food in the protection of the neurodegenerative diseases, including AD.

BACKGROUND/OBJECTIVES: There is growing interest in herbal medicines for managing age-related diseases, such as Alzheimer's and Parkinson’s. Safflower seeds (Carthamus tinctorius L. seeds, CTS) and dandelions (Taraxacum coreanum, TC) are widely used to treat bone- or inflammation-related diseases in Oriental countries. This study investigated the protective effect of the CTS–TC combination on scopolamine (Sco)-induced memory deficits through inflammatory response and cholinergic function. Moreover, marker components such as serotonin, N-(p-coumaroyl) serotonin, N-feruloylserotonin, chlorogenic acid, and chicoric acid in the CTS–TC combination were analyzed for their potential benefits on memory function.MATERIALS/METHODS: Water extracts of CTS, TC, and the CTS–TC combination at various ratios (4:1, 1:1, and 1:4) (100 mg/kg) were orally administered to mice for 14 days. Sco (1 mg/kg) was intraperitoneally injected into the mice before each behavioral test. T-maze and novel object recognition tests were conducted to monitor behavioral changes after the treatment.Western blotting was performed to detect protein expression. In addition, the presence of 5 biomarkers, serotonin, N-(p-coumaroyl) serotonin, N-feruloylserotonin, chlorogenic acid, and chicoric acid, was analyzed using high-performance liquid chromatography (HPLC). RESULTS: Behavioral tests showed that the CTS–TC combination enhanced memory function in Sco-injected mice. Inflammation-related proteins (inducible nitric oxide synthase, cyclooxygenase-2, and glial fibrillary acidic protein) were downregulated after treatment with the CTS–TC combination. The acetylcholinesterase protein expression was also downregulated.HPLC analysis revealed that N-feruloylserotonin and chicoric acid were the predominant components, followed by N-(p-coumaroyl) serotonin, chlorogenic acid, and serotonin. CONCLUSION These findings suggest that the CTS–TC combination protects against Sco-induced memory deficits by inhibiting inflammatory responses and cholinergic dysfunction. N-feruloylserotonin and chicoric acid, along with N-(p-coumaroyl) serotonin, chlorogenic acid, and serotonin, might be biomarkers for the CTS–TC combination, and their effects on memory protection warrant further study.

An excess of amyloid beta (Aβ) led to a rise in ROS production, which in turn caused inflammatory reactions and mitochondrial dysfunction, both of which accelerate the progression of Alzheimer’s disease (AD).Natural flavonoids are proposed as possible agents for neurodegeneration. Pectolinarin is an important flavone mainly found in Cirsium species. In this study, we explored the potential neuroprotective effect of pectolinarin in Aβ25-35 -induced SH-SY5Y cells. The result demonstrated that pectolinarin enhanced cell viability. Pectolinarin treatment inhibited Aβ25-35 -induced ROS generation. Pectolinarin also suppressed NO generation by inhibiting the translocation of NF-ĸB and downregulating protein expression of iNOS and COX-2. Moreover, the expression of Bcl-2 increased while BAX protein decreased when the cells were exposed to pectolinarin, resulting in a decrease in the BAX/Bcl-2 ratio. Pectolinarin treatment also increased BDNF and its receptor TrkB protein expression. In conclusion, pectolinarin neuroprotected Aβ25-35 -induced inflammation and apoptosis. These findings suggest that pectolinarin may be a promising neuroprotective functional food in the protection of the neurodegenerative diseases, including AD.

An excess of amyloid beta (Aβ) led to a rise in ROS production, which in turn caused inflammatory reactions and mitochondrial dysfunction, both of which accelerate the progression of Alzheimer’s disease (AD).Natural flavonoids are proposed as possible agents for neurodegeneration. Pectolinarin is an important flavone mainly found in Cirsium species. In this study, we explored the potential neuroprotective effect of pectolinarin in Aβ25-35 -induced SH-SY5Y cells. The result demonstrated that pectolinarin enhanced cell viability. Pectolinarin treatment inhibited Aβ25-35 -induced ROS generation. Pectolinarin also suppressed NO generation by inhibiting the translocation of NF-ĸB and downregulating protein expression of iNOS and COX-2. Moreover, the expression of Bcl-2 increased while BAX protein decreased when the cells were exposed to pectolinarin, resulting in a decrease in the BAX/Bcl-2 ratio. Pectolinarin treatment also increased BDNF and its receptor TrkB protein expression. In conclusion, pectolinarin neuroprotected Aβ25-35 -induced inflammation and apoptosis. These findings suggest that pectolinarin may be a promising neuroprotective functional food in the protection of the neurodegenerative diseases, including AD.