Machine learning-based prediction of pulmonary embolism to reduce unnecessary computed tomography scans in gastrointestinal cancer patients: a retrospective multicenter study.

This study aimed to develop a machine learning (ML) model for predicting pulmonary embolism (PE) in patients with gastrointestinal cancers, a group at increased risk for PE. We conducted a retrospective, multicenter study analyzing patients who underwent computed tomographic pulmonary angiography (CTPA) between 2010 and 2020. The study utilized demographic and clinical data, including the Wells score and D-dimer levels, to train a random forest ML model. The model's effectiveness was assessed using the area under the receiver operating curve (AUROC). In total, 446 patients from hospital A and 139 from hospital B were included. The training set consisted of 356 patients from hospital A, with internal validation on 90 and external validation on 139 patients from hospital B. The model achieved an AUROC of 0.736 in hospital A and 0.669 in hospital B. The ML model significantly reduced the number of patients recommended for CTPA compared to the conventional diagnostic strategy (hospital A; 100.0% vs. 91.1%, P < 0.001, hospital B; 100.0% vs. 93.5%, P = 0.003). The results indicate that an ML-based prediction model can reduce unnecessary CTPA procedures in gastrointestinal cancer patients, highlighting its potential to enhance diagnostic efficiency and reduce patient burden.

Comparative analysis of LC-MS/MS and real-time PCR assays for efficient detection of potential allergenic silkworm.

The silkworm (Bombyx mori) has long been valued food and feed in East Asia for its abundant nutritional and medicinal attributes, conversely, it can elicit allergic responses in susceptible individuals. Therefore, the development of silkworm detection method is required to avert allergenic incidents. In this study, two methodologies, tandem mass spectrometry (LC-MS/MS) and real-time PCR, were developed to achieve effective silkworm detection. These methods exhibited exceptional sensitivity in identifying silkworm presence in processed foods. Furthermore, model cookies spiked with silkworm were used to validate the sensitivities of LC-MS/MS (0.0005%) and real-time PCR (0.001%). Overall, these techniques were useful for trace silkworm detection in food products; therefore, they may help prevent allergic reactions. To the best of our knowledge, this study represents the first comparison of LC-MS/MS and real-time PCR methods for silkworm detection, marking an important contribution to the field. Data are available from ProteomeXchange under identifier PXD042494.

Discovery, verification, and validation of walnut protein marker peptides using LC-MS approaches.

A key requirement of liquid chromatography-mass spectrometry (LC-MS)-based allergenic food protein analysis methods is to use protein marker peptides with good analytical performances in LC-MS analysis of commercial processed foods. In this study, we developed a multi-stage walnut protein marker peptide selection strategy involving marker peptide discovery and verification and LC-MS validation of chemically equivalent stable isotope-labeled peptides. This strategy proposed three walnut protein marker peptides, including two new marker peptides. Our LC-MS-based walnut protein analysis method using the three stable isotope-labeled peptides showed acceptable linearity (R2 >0.99), matrix effects (coefficient of variation <±15%), sensitivity (limit of detection >0.3 pg/µL, limit of quantification >0.8 pg/µL), recovery (85.1-103.4%), accuracy, and precision (coefficient of variation <10%). In conclusion, our multi-stage marker peptide selection strategy effectively selects specific protein marker peptides for sensitive detection and absolute quantification of walnut proteins in LC-MS analysis of commercial processed foods.

Acoustic Analysis of Speech for Screening for Suicide Risk: Machine Learning Classifiers for Between- and Within-Person Evaluation of Suicidality.

BACKGROUND: Assessing a patient's suicide risk is challenging for health professionals because it depends on voluntary disclosure by the patient and often has limited resources. The application of novel machine learning approaches to determine suicide risk has clinical utility. OBJECTIVE: This study aimed to investigate cross-sectional and longitudinal approaches to assess suicidality based on acoustic voice features of psychiatric patients using artificial intelligence. METHODS: We collected 348 voice recordings during clinical interviews of 104 patients diagnosed with mood disorders at baseline and 2, 4, 8, and 12 months after recruitment. Suicidality was assessed using the Beck Scale for Suicidal Ideation and suicidal behavior using the Columbia Suicide Severity Rating Scale. The acoustic features of the voice, including temporal, formal, and spectral features, were extracted from the recordings. A between-person classification model that examines the vocal characteristics of individuals cross sectionally to detect individuals at high risk for suicide and a within-person classification model that detects considerable worsening of suicidality based on changes in acoustic features within an individual were developed and compared. Internal validation was performed using 10-fold cross validation of audio data from baseline to 2-month and external validation was performed using data from 2 to 4 months. RESULTS: A combined set of 12 acoustic features and 3 demographic variables (age, sex, and past suicide attempts) were included in the single-layer artificial neural network for the between-person classification model. Furthermore, 13 acoustic features were included in the extreme gradient boosting machine learning algorithm for the within-person model. The between-person classifier was able to detect high suicidality with 69% accuracy (sensitivity 74%, specificity 62%, area under the receiver operating characteristic curve 0.62), whereas the within-person model was able to predict worsening suicidality over 2 months with 79% accuracy (sensitivity 68%, specificity 84%, area under receiver operating characteristic curve 0.67). The second model showed 62% accuracy in predicting increased suicidality in external sets. CONCLUSIONS: Within-person analysis using changes in acoustic features within an individual is a promising approach to detect increased suicidality. Automated analysis of voice can be used to support the real-time assessment of suicide risk in primary care or telemedicine.

A machine learning approach to the development and prospective evaluation of a pediatric lung sound classification model.

Auscultation, a cost-effective and non-invasive part of physical examination, is essential to diagnose pediatric respiratory disorders. Electronic stethoscopes allow transmission, storage, and analysis of lung sounds. We aimed to develop a machine learning model to classify pediatric respiratory sounds. Lung sounds were digitally recorded during routine physical examinations at a pediatric pulmonology outpatient clinic from July to November 2019 and labeled as normal, crackles, or wheezing. Ensemble support vector machine models were trained and evaluated for four classification tasks (normal vs. abnormal, crackles vs. wheezing, normal vs. crackles, and normal vs. wheezing) using K-fold cross-validation (K = 10). Model performance on a prospective validation set (June to July 2021) was compared with those of pediatricians and non-pediatricians. Total 680 clips were used for training and internal validation. The model accuracies during internal validation for normal vs. abnormal, crackles vs. wheezing, normal vs. crackles, and normal vs. wheezing were 83.68%, 83.67%, 80.94%, and 90.42%, respectively. The prospective validation (n = 90) accuracies were 82.22%, 67.74%, 67.80%, and 81.36%, respectively, which were comparable to pediatrician and non-pediatrician performance. An automated classification model of pediatric lung sounds is feasible and maybe utilized as a screening tool for respiratory disorders in this pandemic era.

Detection of Depression and Suicide Risk Based on Text From Clinical Interviews Using Machine Learning: Possibility of a New Objective Diagnostic Marker.

Background: Depression and suicide are critical social problems worldwide, but tools to objectively diagnose them are lacking. Therefore, this study aimed to diagnose depression through machine learning and determine whether it is possible to identify groups at high risk of suicide through words spoken by the participants in a semi-structured interview. Methods: A total of 83 healthy and 83 depressed patients were recruited. All participants were recorded during the Mini-International Neuropsychiatric Interview. Through the suicide risk assessment from the interview items, participants with depression were classified into high-suicide-risk (31 participants) and low-suicide-risk (52 participants) groups. The recording was transcribed into text after only the words uttered by the participant were extracted. In addition, all participants were evaluated for depression, anxiety, suicidal ideation, and impulsivity. The chi-square test and student's T-test were used to compare clinical variables, and the Naive Bayes classifier was used for the machine learning text model. Results: A total of 21,376 words were extracted from all participants and the model for diagnosing patients with depression based on this text confirmed an area under the curve (AUC) of 0.905, a sensitivity of 0.699, and a specificity of 0.964. In the model that distinguished the two groups using statistically significant demographic variables, the AUC was only 0.761. The DeLong test result (p-value 0.001) confirmed that the text-based classification was superior to the demographic model. When predicting the high-suicide-risk group, the demographics-based AUC was 0.499, while the text-based one was 0.632. However, the AUC of the ensemble model incorporating demographic variables was 0.800. Conclusion: The possibility of diagnosing depression using interview text was confirmed; regarding suicide risk, the diagnosis accuracy increased when demographic variables were incorporated. Therefore, participants' words during an interview show significant potential as an objective and diagnostic marker through machine learning.

A host dTMP-bound structure of T4 phage dCMP hydroxymethylase mutant using an X-ray free electron laser.

The hydroxymethylation of cytosine bases plays a vital role in the phage DNA protection system inside the host Escherichia coli. This modification is known to be catalyzed by the dCMP hydroxymethylase from bacteriophage T4 (T4dCH); structural information on the complexes with the substrate, dCMP and the co-factor, tetrahydrofolate is currently available. However, the detailed mechanism has not been understood clearly owing to a lack of structure in the complex with a reaction intermediate. We have applied the X-ray free electron laser (XFEL) technique to determine a high-resolution structure of a T4dCH D179N active site mutant. The XFEL structure was determined at room temperature and exhibited several unique features in comparison with previously determined structures. Unexpectedly, we observed a bulky electron density at the active site of the mutant that originated from the physiological host (i.e., E. coli). Mass-spectrometric analysis and a cautious interpretation of an electron density map indicated that it was a dTMP molecule. The bound dTMP mimicked the methylene intermediate from dCMP to 5'-hydroxymethy-dCMP, and a critical water molecule for the final hydroxylation was convincingly identified. Therefore, this study provides information that contributes to the understanding of hydroxymethylation.

A curcumin-based molecular probe for near-infrared fluorescence imaging of tau fibrils in Alzheimer's disease.

In recent years, there has been growing interest in the near-infrared (NIR) fluorescence imaging of tau fibrils for the early diagnosis of Alzheimer's disease (AD). In order to develop a curcumin-based NIR fluorescent probe for tau fibrils, structural modification of the curcumin scaffold was attempted by combining the following rationales: the curcumin derivative should preserve its binding affinity to tau fibrils, and, upon binding to tau fibrils, the probe should show favorable fluorescence properties. To meet these requirements, we designed a novel curcumin scaffold with various aromatic substituents. Among the series, the curcumin derivative with a (4-dimethylamino-2,6-dimethoxy)phenyl moiety showed a significant change in its fluorescence properties (22.9-fold increase in quantum yield; Kd, 0.77 µM; λem, 620 nm; Φ, 0.32) after binding to tau fibrils. In addition, fluorescence imaging of tau-green fluorescent protein-transfected SHSY-5Y cells with confirmed that detected tau fibrils in live cells.

Localization of peripheral dopamine D1 and D2 receptors in rat and human seminal vesicles.

Dopamine, an established neurotransmitter in the central nervous system, is recognized for its role in penile erection and ejaculation in rats. However, its complete mechanism of action in the genitourinary tract is unknown. The objective of this study was to investigate the existence and expression of peripheral dopamine D1 and D2 receptor messenger RNAs (mRNAs) and corresponding proteins in rat and human seminal vesicles. The seminal vesicle tissues of male Sprague-Dawley rats and human radical prostatectomy specimens were used to extract total RNA and proteins, and to prepare slide sections. Rat hypothalamus tissue served as a control for dopamine D1 and D2 receptors. Testing for the presence and expression of peripheral dopamine D1 and D2 receptor mRNAs in rat and human seminal vesicle tissues was performed by reverse transcription-polymerase chain reaction. Western blotting was used to detect corresponding proteins of D1 and D2 receptors. Immunohistochemical staining using rabbit antipeptide polyclonal antibodies was employed to identify and anatomically localize dopamine D1 and D2 receptor proteins in rat and human seminal vesicles. Dopamine D1 and D2 receptor transcripts were detected in both human and rat seminal vesicle tissues. Western blot analysis demonstrated that peripheral dopamine D1 and D2 receptor proteins exist in both human and rat seminal vesicle tissues. Immunohistochemical analysis demonstrated the localization of peripheral dopamine D1 and D2 receptors to the smooth muscle layer of human and rat seminal vesicles. The results of this study demonstrate that peripheral dopamine D1 and D2 receptors are present in the seminal vesicle tissue in both rats and humans. Although these results suggest that seminal emission may be mediated in part by the stimulation of peripheral dopamine receptors located in the seminal vesicles, the functional significance of dopamine in male reproductive tract has yet to be fully defined.