Prediction of hemorrhage in placenta previa: Radiomics analysis of pelvic MRI images.

INTRODUCTION: Prediction of intraoperative massive hemorrhage is still challenging in placenta previa. Radiomics analysis has been investigated as a new evaluation method for analyzing medical images. We used radiomics analysis on placental magnetic resonance imaging (MRI) images to predict intraoperative hemorrhage in placenta previa. METHODS: We used the sagittal MRI T2-weighted sequence in placenta previa. Using the rectangular region from the uterine os to the anterior wall, we extracted 97 radiomics features. We also collected patient demographics and blood test data as clinical variables. Combining these radiomics features and clinical variables, logistic regression models with a stepwise method were built to predict the risk of hemorrhage, defined as blood loss of > 2000 ml. We evaluated the prediction performance of the models using accuracy and area under the curve (AUC), also analyzing the important variables for the prediction by stepwise methods. RESULTS: We enrolled a total of 63 placenta previa cases including 30 hemorrhage cases from two institutes. The model combining clinical variables and radiomics features showed the best prediction performance with an accuracy of 0.70 and an AUC of 0.69 in the internal validation data, and accuracy of 0.41 and an AUC of 0.70 in the external validation data, compared with human experts (accuracy of 0.62). Regarding variable selection, two radiomics features. 'original_glrlm_LowGrayLevelRunEmphasis,' and 'diagnostics_Image-original_Minimum,' were important predictors for hemorrhage by the stepwise method. DISCUSSION: Radiomics features based on MRI could be used as effective predictive variables for hemorrhage in placenta previa. Radiomics analysis of placental imaging could lead to further analysis of quantitative variables related to obstetric diseases.

Deep learning algorithm for predicting preterm birth in the case of threatened preterm labor admissions using transvaginal ultrasound.

PURPOSE: Preterm birth presents a major challenge in perinatal care, and predicting preterm birth remains a major challenge. If preterm birth cases can be accurately predicted during pregnancy, preventive interventions and more intensive prenatal monitoring may be possible. Deep learning has the capability to extract image parameters or features related to diseases. We constructed a deep learning model to predict preterm births using transvaginal ultrasound images. METHODS: Patients who were hospitalized for threatened preterm labor or shortened cervical length were enrolled. We used images of the cervix obtained via transvaginal ultrasound examination at admission to predict cases of preterm birth. We used convolutional neural networks (CNNs) and Vision Transformer (Vit) for the model construction. We compared the prediction performance of deep learning models with two human experts. RESULTS: A total of 59 patients were enrolled in the study, including 30 cases in the preterm group and 29 cases in the full-term group. Statistical analysis of clinical variables including cervical length showed no significant differences between the two groups. For accuracy, the best CNN model had the highest accuracy of 0.718 with an area under the curve (AUC) of 0.704, followed by Vision Transformer with accuracy of 0.645 and AUC of 0.587. The accuracy of two human experts was 0.465 and 0.517, respectively. CONCLUSIONS: Deep learning models have important implications for extraction of features that provide more accurate assessment of preterm birth than traditional visual assessment by the human eye.

A case of carotid-axillary bypass for subclavian steal syndrome in an 83-year-old female undergoing hemodialysis.

INTRODUCTION: Patients undergoing hemodialysis exhibit a high incidence of subclavian steal syndrome. Many cases of endovascular treatment for subclavian artery stenosis were only reported recently; however, the long-term results of surgical treatment are also important. Herein, we report a case of subclavian steal syndrome treated with common carotid-axillary bypass surgery in a patient undergoing hemodialysis. PRESENTATION OF CASE: An 83-year-old woman experienced dizziness and pain in her left hand during hemodialysis. Computed tomography and angiography revealed severe stenosis and calcified lesions in the left subclavian artery. Ultrasonography revealed a retrograde blood flow waveform in the left vertebral artery. The patient was diagnosed with subclavian steal syndrome. We performed common carotid-axillary bypass for lesions that were difficult to revascularize via endovascular therapy. The post-operative course was uneventful, and the dizziness and numbness in the patient's left hand during dialysis disappeared. Post-operative ultrasonography revealed an antegrade blood flow waveform in the left vertebral artery. DISCUSSION: Subclavian steal syndrome is an indication for revascularization in symptomatic patients. Endovascular treatment should be considered the first choice; however, surgery should be considered for patients in whom endovascular treatment is difficult, such as those with severe calcification. We chose common carotid-axillary artery bypass because the subclavian approach is a more familiar technique. Until 1 year post-operatively, the patient had not experienced any symptom recurrence, and the shunt flow was well maintained. CONCLUSION: Common carotid-axillary bypass can be useful for revascularization of lesions for which endovascular therapy is considered difficult in patients with subclavian steal syndrome.

A multimodal deep learning model for predicting severe hemorrhage in placenta previa.

Placenta previa causes life-threatening bleeding and accurate prediction of severe hemorrhage leads to risk stratification and optimum allocation of interventions. We aimed to use a multimodal deep learning model to predict severe hemorrhage. Using MRI T2-weighted image of the placenta and tabular data consisting of patient demographics and preoperative blood examination data, a multimodal deep learning model was constructed to predict cases of intraoperative blood loss > 2000 ml. We evaluated the prediction performance of the model by comparing it with that of two machine learning methods using only tabular data and MRI images, as well as with that of two human expert obstetricians. Among the enrolled 48 patients, 26 (54.2%) lost > 2000 ml of blood and 22 (45.8%) lost < 2000 ml of blood. Multimodal deep learning model showed the best accuracy of 0.68 and AUC of 0.74, whereas the machine learning model using tabular data and MRI images had a class accuracy of 0.61 and 0.53, respectively. The human experts had median accuracies of 0.61. Multimodal deep learning models could integrate the two types of information and predict severe hemorrhage cases. The model might assist human expert in the prediction of intraoperative hemorrhage in the case of placenta previa.

Preliminary Results of Deep Learning Approach for Preoperative Diagnosis of Ovarian Cancer Based on Pelvic MRI Scans.

BACKGROUND/AIM: To predict the pathological diagnosis of ovarian tumors using preoperative MRI images, using deep learning models. PATIENTS AND METHODS: A total of 185 patients were enrolled, including 40 with ovarian cancers, 25 with borderline malignant tumors, and 120 with benign tumors. Using sagittal and horizontal T2-weighted images (T2WI), we constructed the pre-trained convolutional neural networks to predict pathological diagnoses. The performance of the model was assessed by precision, recall, and F1-score on macro-average with 95% confidence interval (95%CI). The accuracy and area under the curve (AUC) were also assessed after binary transformation by the division into benign and non-benign groups. RESULTS: The macro-average accuracy in the three-class classification was 0.523 (95%CI=0.504-0.544) for sagittal images and 0.426 (95%CI=0.404-0.446) for horizontal images. The model achieved a precision of 0.63 (95%CI=0.61-0.66), recall of 0.75 (95%CI=0.72-0.78), and F1 score of 0.69 (95%CI=0.67-0.71) for benign tumor. Regarding the discrimination between benign and non-benign tumors, the accuracy in the binary-class classification was 0.628 (95%CI=0.592-0.662) for sagittal images and AUC was 0.529 (95%CI=0.500-0.557). CONCLUSION: Using deep learning, we could perform pathological diagnosis from preoperative MRI images.

The inflammatory macrophages repress the growth of bone metastatic human prostate cancer cells via TNF-α and IL-6 signaling: Involvement of cell signaling regulator regucalcin.

Macrophages in the cancer microenvironments may play a regulatory role in the progression and metastasis of prostate cancer cells. However, the crosstalk between macrophages and prostate cancer cells is poorly understood. This study elucidates whether inflammatory macrophages regulate the proliferation and death of human prostate cancer cells in vitro. The RAW264.7 mouse macrophages were cocultured with PC-3 or DU-145 wild-type cells by using a Transwell chamber in vitro. RAW264.7 cells were cocultured with PC-3 or DU-145 cells in the presence of lipopolysaccharide (LPS). This coculturing blocked the proliferation and accelerated the death of cancer cells. Interestingly, cancer cell proliferation was repressed and death was promoted by the addition of the conditioned medium obtained from RAW264.7 cells treated with LPS. Culturing with LPS mostly augmented the production of tumor necrosis factor-α (TNF-α) and interleukin-6 (IL-6) in the culture medium of RAW264.7 cells. The effects of the conditioned medium on the proliferation and death of PC-3 or DU-145 cells were blocked by NF-κB or STAT3 signaling inhibitors. Moreover, the effects of the conditioned medium on the proliferation and death of prostate cancer cells were not expressed in regucalcin-overexpressing cancer cells that diminish the levels of NF-κB p65 and STAT3. Culturing with extracellular TNF-α, IL-6, or regucalcin triggered inhibition of the proliferation of PC-3 wild-type cells. The levels of regucalcin in PC-3 cells were elevated by TNF-α or IL-6 stimulation. This study demonstrates that inflammatory macrophages triggered the loss of prostate cancer cells via the signaling process of NF-κB, STAT3, or regucalcin.

Relationship between the affective dimension of pain and site of the disorder: A cross-sectional study.

BACKGROUND: Pain is a complex experience with both sensory and affective dimensions, and the affective dimension can increase the risks of chronic pain development. It is thus critical to identify factors influencing the affective dimension of pain. OBJECTIVE: This study aimed to identify the relationship between the affective dimension of pain and disorder site (primary pain source). METHODS: Study participants were recruited from patients referred for physical therapy at an orthopedic outpatient clinic. Pain quality including the affective dimension, disorder site from descriptive medical diagnosis, pain intensity, duration from pain onset, and demographic data, was collected. A multivariable logistic regression model was constructed to analyze the relationship between the affective dimension of pain and the disorder site. RESULTS: A total of 282 participants were included. Cervical and lumbar spine disorders were significantly associated with an affective dimension of pain compared to limbs disorders when adjusted for age, sex, pain intensity, and duration from the onset in the regression model. CONCLUSIONS: Regardless of duration from the onset and other confounding factors, disorder site is correlated with the affective dimension of pain. Multidimensional pain assessment is crucial when clinicians evaluate patients with cervical and lumbar spine disorders, even in the acute phase.

Potential application of a hydrotalcite-like compound for reduction of toxicity to aquatic organisms via rapid and efficient removal of hydrogen sulfide.

Hydrogen sulfide (H2S) is known to have wide ranging toxicities not only as a gas but also as dissolved forms in aquatic environments. The diversity of aquatic organisms can be severely affected by hydrogen sulfide at very low concentrations, indicating the urgent necessity to develop an efficient method for removal of hydrogen sulfide in water. In this study, the removal capacity for hydrogen sulfide of our originally developed hydrotalcite-like compound composed of magnesium and iron (MF-HT) was investigated and its potential application for reduction of toxicity to aquatic organisms was evaluated. The MF-HT experimentally showed a high adsorption capacity of 146.5 mg/g with a fast adsorption equilibrium time of 45 min, both of which are top-class compared with those of other adsorbents previously reported. In fact, removal of hydrogen sulfide (1.2-152.5 mg/L) at an average rate of >97.6% was achieved in groundwater samples (n = 16) by the MF-HT within 60 min. The toxicities of groundwater, indicated by inhibition rate for microalgae (primary producers) and immobilization rate for crustaceans (secondary consumers), were reduced by 96.1% and 82.5% in 2-fold and 4-fold diluted groundwater, respectively, after treatment with the MF-HT for 60 min. These results indicate that MF-HT has an excellent safety record for aquatic organisms. After clarifying the adsorption mechanism, excellent reusability of MF-HT was also confirmed after regeneration using 1 M Na2CO3 solution. Considering the efficacy, speed, safety and cost of MF-HT, it could be a novel promising material for solving the problem of hydrogen sulfide pollution in the hydrosphere.

The overexpressed transcription factor RGPR-p117 suppresses the proliferation of normal rat kidney proximal tubular epithelial NRK-52E cells: Involvement of diverse signaling pathways.

AIMS: RGPR-p117 was originally discovered as a novel transcription factor, which specifically binds to a nuclear factor I (NFI) consensus motif TTGGC(N)6CC in the promoter region of the regucalcin gene. RGPR-p117 is also called as Lztr2 and SEC16B. The role of RGPR-p117 in cell regulation is poorly understood. This study was undertaken to determine whether the overexpression of RGPR-p117 impacts the proliferation of normal rat kidney proximal tubular epithelial NRK-52E cells in vitro. MAIN METHODS: The NRK-52E wild-type cells and RGPR-p117-overexpressing NRK-52E cells were cultured in DMEM containing fetal bovine serum. KEY FINDINGS: The overexpression of RGPR-p117 repressed colony formation and proliferation of NRK-52E cells. Interestingly, RGPR-p117 overexpression blocked cell proliferation promoted by culturing with Bay K 8644, a calcium-entry agonist, and phorbol 12-myristate 13-acetate, an activator of protein kinase C. The depressive effects of RGPR-p117 overexpression on cell proliferation were not occurred by culturing with various inhibitors of cell cycle and intracellular signaling processes. RGPR-p117 overexpression increased the translocation of RGPR-p117 into the nucleus of NRK-52E cells. Mechanistically, RGPR-p117 overexpression diminished the levels of Ras, PI3 kinase, Akt, mitogen-activated protein kinase, and mTOR, while it raised the levels of p53, Rb, p21, and regucalcin. Furthermore, RGPR-p117 overexpression protected cell death caused by apoptosis-inducing factors, suggesting that the suppressive effects of RGPR-p117 on cell growth are independent of cell death. SIGNIFICANCE: The present study demonstrates that the overexpressed transcription factor RGPR-p117 suppresses cell proliferation via targeting diverse signaling processes, suggesting a role of RGPR-p117 in cell regulation.

Prediction of preterm birth using artificial intelligence: a systematic review.

Preterm birth is the leading cause of neonatal death. It is challenging to predict preterm birth. We elucidated the state of artificial intelligence research on the prediction of preterm birth, clarifying the predictive values and accuracy. We performed a systematic review using three databases (PubMed, Web of Science, and Scopus) in August 2020, with keywords as 'artificial intelligence,' 'deep learning,' 'machine learning,' and 'neural network' combined with 'preterm birth'. We included 22 publications between 2010 and 2020. Regarding the predictive values, electrohysterogram images were mostly used, followed by the biological profiles, the metabolic panel in amniotic fluid or maternal blood, and the cervical images on the ultrasound examination. The size of dataset in most studies was hundred cases and too small for learning, although only three studies used the medical database over a hundred thousand cases. The accuracy was better in the studies using the metabolic panel and electrohysterogram images. Impact statementWhat is already known on this subject? Preterm birth is the leading cause of newborn morbidity and mortality. Presently, the prediction of preterm birth in individual cases is still challenging.What the results of this study add? Using artificial intelligence such as deep learning and machine learning models, clinical data could lead to accurate prediction of preterm birth.What the implications are of these findings for clinical practice and/or further research? The size of the datasets was too small for the models using artificial intelligence in the previous studies. Big data should be prepared for the future studies.

Redistribution of potentially toxic elements in the hydrosphere after the relocation of a group of tanneries.

Simultaneous relocation of a group of pollutant sources in a heavily polluted area is a rare event. Such a relocation has been implemented in Hazaribagh, a tannery built-up area with heavy pollution, in Bangladesh. This provides a valuable opportunity to compare the changes in environmental conditions associated with the relocation of multiple putative sources. Our environmental monitoring for a period of 6 years at the stationary areas centered on Hazaribagh geographically revealed trivalent [Cr(III)], hexavalent [Cr(VI)] chromium, lead, iron, and manganese as tannery-related elements after the legal deadline for tannery relocation. The median Cr(III) level in canal water, into which wastewater from tanneries was directly discharged, after the relocation was 97% lower of that before the relocation, indicating a beneficial effect of the relocation. In contrast, the median Cr(VI) level in water samples just after the relocation and 2 years after the relocation were approximately 5-fold and 30-fold higher, respectively, than those before the relocation. These results indicate not only a harmful effect of the relocation but also the possibility of conversion from Cr(III) to Cr(VI) in nature. Although the health hazard indexes considering all of the tannery-related elements in all of the canal water samples before the relocation exceeded the safety thresholds, the percentages of samples in which the indexes exceeded their safety thresholds after the relocation decreased by 32.5%-45.0%. Treatment with our patented hydrotalcite-like compound consisting of magnesium and iron (MF-HT) resulted in decreases in the health hazard indexes in all of the water samples in which the indexes exceeded their safety thresholds to levels lower than their thresholds. Thus, this study shows the double-edged effects associated with the relocation and a potential solution.

Chemical inducer of regucalcin attenuates lipopolysaccharide-induced inflammatory responses in pancreatic MIN6 ß-cells and RAW264.7 macrophages.

We previously isolated derrisfolin A, a novel rotenoid derivative, from the stems of Derris trifoliata Lour. (Leguminosae). Here, we report that derrisfolin A induces the expression of endogenous regucalcin (RGN) protein in both pancreatic MIN6 ß-cells and RAW264.7 macrophages. Induction of RGN expression by derrisfolin A or retrovirus-mediated gene transfer in MIN6 cells and RAW264.7 macrophages significantly decreased lipopolysaccharide (LPS)-induced mRNA expression of Nos2, Il1b, and Tnf via nuclear factor-κB activation; reduced LPS-induced apoptosis in MIN6 cells, accompanied by decreased production of nitric oxide, interleukin-1ß, and tumor necrosis factor-α; and attenuated generation of LPS-induced reactive oxygen species, malondialdehyde, and 3-nitrotyrosine in MIN6 cells. Additionally, in co-cultures of MIN6 cells with RAW264.7 macrophages in the presence of LPS, induction of RGN expression by derrisfolin A or retrovirus-mediated gene transfer in RAW264.7 macrophages attenuated apoptosis and oxidative/nitrosative stress in MIN6 cells. These results suggest that the induction of RGN expression in MIN6 cells was effective in suppressing LPS-induced inflammatory cytotoxicity and that in co-culture conditions, the induction of RGN expression in RAW264.7 macrophages blocked LPS-induced paracrine effects of RAW264.7 macrophages on inflammatory cytotoxicity in MIN6 cells. Our findings suggest that derrisfolin A, a chemical inducer of RGN, might be useful for developing a new drug against macrophage-associated ß-cell inflammation in type 2 diabetes.

Machine learning approach for the prediction of postpartum hemorrhage in vaginal birth.

Postpartum hemorrhage is the leading cause of maternal morbidity. Clinical prediction of postpartum hemorrhage remains challenging, particularly in the case of a vaginal birth. We studied machine learning models to predict postpartum hemorrhage. Women who underwent vaginal birth at the Tokyo Women Medical University East Center between 1995 and 2020 were included. We used 11 clinical variables to predict a postpartum hemorrhage defined as a blood loss of > 1000 mL. We constructed five machine learning models and a deep learning model consisting of neural networks with two layers after applying the ensemble learning of five machine learning classifiers, namely, logistic regression, a support vector machine, random forest, boosting trees, and decision tree. For an evaluation of the performance, we applied the area under the curve of the receiver operating characteristic (AUC), the accuracy, false positive rate (FPR) and false negative rate (FNR). The importance of each variable was evaluated through a comparison of the feature importance calculated using a Boosted tree. A total of 9,894 patients who underwent vaginal birth were enrolled in the study, including 188 cases (1.9%) with blood loss of > 1000 mL. The best learning model predicted postpartum hemorrhage with an AUC of 0.708, an accuracy of 0.686, FPR of 0.312, and FNR of 0.398. The analysis of the importance of the variables showed that pregnant gestation of labor, the maternal weight upon admission of labor, and the maternal weight before pregnancy were considered to be weighted factors. Machine learning model can predict postpartum hemorrhage during vaginal delivery. Further research should be conducted to analyze appropriate variables and prepare big data, such as hundreds of thousands of cases.

Artificial intelligence in gynecologic cancers: Current status and future challenges - A systematic review.

OBJECTIVE: Over the past years, the application of artificial intelligence (AI) in medicine has increased rapidly, especially in diagnostics, and in the near future, the role of AI in medicine will become progressively more important. In this study, we elucidated the state of AI research on gynecologic cancers. METHODS: A search was conducted in three databases-PubMed, Web of Science, and Scopus-for research papers dated between January 2010 and December 2020. As keywords, we used "artificial intelligence," "deep learning," "machine learning," and "neural network," combined with "cervical cancer," "endometrial cancer," "uterine cancer," and "ovarian cancer." We excluded genomic and molecular research, as well as automated pap-smear diagnoses and digital colposcopy. RESULTS: Of 1632 articles, 71 were eligible, including 34 on cervical cancer, 13 on endometrial cancer, three on uterine sarcoma, and 21 on ovarian cancer. A total of 35 studies (49%) used imaging data and 36 studies (51%) used value-based data as the input data. Magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, cytology, and hysteroscopy data were used as imaging data, and the patients' backgrounds, blood examinations, tumor markers, and indices in pathological examination were used as value-based data. The targets of prediction were definitive diagnosis and prognostic outcome, including overall survival and lymph node metastasis. The size of the dataset was relatively small because 64 studies (90%) included less than 1000 cases, and the median size was 214 cases. The models were evaluated by accuracy scores, area under the receiver operating curve (AUC), and sensitivity/specificity. Owing to the heterogeneity, a quantitative synthesis was not appropriate in this review. CONCLUSIONS: In gynecologic oncology, more studies have been conducted on cervical cancer than on ovarian and endometrial cancers. Prognoses were mainly used in the study of cervical cancer, whereas diagnoses were primarily used for studying ovarian cancer. The proficiency of the study design for endometrial cancer and uterine sarcoma was unclear because of the small number of studies conducted. The small size of the dataset and the lack of a dataset for external validation were indicated as the challenges of the studies.

Learning Curve of Robotic-assisted Hysterectomy With Pelvic Lymphadenectomy for Early Stage Endometrial Cancer: Analysis of 81 Cases.

BACKGROUND/AIM: The purpose of this study was to evaluate the learning curve of robotic hysterectomy and pelvic lymphadenectomy for early-stage endometrial carcinoma. PATIENTS AND METHODS: A retrospective chart review was performed on the first 81 surgeries performed by a single surgeon. The 81 cases were divided into three groups; 4 subgroups of 20 cases each, 3 subgroups of 27 cases each, and 2 subgroups of 40 cases each. The surgical outcomes in each group were analyzed, using operative time, estimated blood loss, and the number of lymph nodes resected. RESULTS: The median operating time, estimated blood loss, and number of pelvic lymph nodes were 147 min, 50 g and 23, respectively. The estimated blood loss improved over time significantly, when dividing by every 27 and 40 cases. No statistical significance was shown regarding operative time and the number of lymph nodes. CONCLUSION: Approximately, 30 cases were needed to gain proficiency in the surgical technique.

Development of an efficient remediation system with a low cost after identification of water pollutants including phenolic compounds in a tannery built-up area in Bangladesh.

Water pollution caused by tannery wastewater is an important issue in developing countries. Most studies have focused on inorganic chemicals represented by chromium as a tannery-related main pollutant. This is the first study in which pollution of water by tannery-related organic chemicals was assessed by a combination of qualitative and quantitative analyses. Our quantitative analysis showed that the maximum concentration of total phenolic compounds (phenols), consisting of phenol, bisphenol F, p-cresol and chlorocresol, in canal water in a tannery built-up area in Bangladesh was >67-fold higher than the Environmental, Health and Safety (EHS) guideline value. Mapping of our results indicated tanneries as the sources of phenols pollution. Our original depurative, a hydrotalcite-like compound consisting of magnesium and iron (MF-HT), could adsorb all kinds of phenols and exhibited the highest phenol adsorption ability (115.8 mg/g) among reported hydrotalcite-like compounds. The levels of phenols in canal water samples were reduced to levels below the guideline value by using MF-HT with assistance of a photocatalytic reaction. Moreover, the mean level of chromium (112.2 mg/L) in canal water samples was decreased by 99.7% by using the depurative. Thus, the depurative has the potential for solving the problem of tannery-related water pollution by phenols and chromium.

Intranasal levels of lead as an exacerbation factor for allergic rhinitis in humans and mice.

BACKGROUND: Air pollutants are suspected to affect pathological conditions of allergic rhinitis (AR). OBJECTIVES: After detecting Pb (375 µg/kg) in Japanese cedar pollen, the effects of intranasal exposure to Pb on symptoms of AR were investigated. METHODS: Pollen counts, subjective symptoms, and Pb levels in nasal epithelial lining fluid (ELF) were investigated in 44 patients with Japanese cedar pollinosis and 57 controls from preseason to season. Effects of intranasal exposure to Pb on symptoms were confirmed by using a mouse model of AR. RESULTS: Pb levels in ELF from patients were >40% higher than those in ELF from control subjects during the pollen season but not before the pollen season. Pb level in ELF was positively associated with pollen counts for the latest 4 days before visiting a hospital as well as scores of subjective symptoms. Intranasal exposure to Pb exacerbated symptoms in allergic mice, suggesting Pb as an exacerbation factor. Pb levels in ELF and nasal mucosa in Pb-exposed allergic mice were higher than those in Pb-exposed nonallergic mice, despite intranasally challenging the same amount of Pb. Because the increased Pb level in the nasal mucosa of Pb-exposed allergic mice was decreased after washing the nasal cavity, Pb on the surface of but not inside the nasal mucosa may have been a source of increased Pb level in ELF of allergic mice. CONCLUSIONS: Increased nasal Pb level partially derived from pollen could exacerbate subjective symptoms of AR, indicating Pb as a novel hazardous air pollutant for AR.

The application of machine learning for predicting recurrence in patients with early-stage endometrial cancer: a pilot study.

OBJECTIVE: Most women with early stage endometrial cancer have a favorable prognosis. However, there is a subset of patients who develop recurrence. In addition to the pathological stage, clinical and therapeutic factors affect the probability of recurrence. Machine learning is a subtype of artificial intelligence that is considered effective for predictive tasks. We tried to predict recurrence in early stage endometrial cancer using machine learning methods based on clinical data. METHODS: We enrolled 75 patients with early stage endometrial cancer (International Federation of Gynecology and Obstetrics stage I or II) who had received surgical treatment at our institute. A total of 5 machine learning classifiers were used, including support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and boosted tree, to predict the recurrence based on 16 parameters (age, body mass index, gravity/parity, hypertension/diabetic, stage, histological type, grade, surgical content and adjuvant chemotherapy). We analyzed the classification accuracy and the area under the curve (AUC). RESULTS: The highest accuracy was 0.82 for SVM, followed by 0.77 for RF, 0.74 for LR, 0.66 for DT, and 0.66 for boosted trees. The highest AUC was 0.53 for LR, followed by 0.52 for boosted trees, 0.48 for DT, and 0.47 for RF. Therefore, the best predictive model for this analysis was LR. CONCLUSION: The performance of the machine learning classifiers was not optimal owing to the small size of the dataset. The use of a machine learning model made it possible to predict recurrence in early stage endometrial cancer.

Lithium promotes malignant transformation of nontumorigenic cells in vitro.

Because of the deficiency of water caused by the regional disparities of rainfall due to global warming, attention has been given to the use of well water as drinking water in developing countries. Our fieldwork study in Afghanistan showed that there was a maximum value of 3371 µg/L and an average value of 233 µg/L of lithium in well drinking water. Since the level of lithium in well water is higher than the levels in other countries, we investigated the health risk of lithium. After confirming no influence of ≤1000 µM lithium on cell viability, we found that lithium at concentrations of 100 and 500 µM promoted anchorage-independent growth of human immortalized keratinocytes (HaCaT) and lung epithelial cells (BEAS-2B) but not that of human keratinocytic carcinoma cells (HSC-5) or lung epithelial carcinoma cells (A549). The same concentrations of lithium also promoted phosphorylation of c-SRC and MEK/ERK but not that of AKT in the keratinocytes. Inhibitors of c-SRC (PP2) and MEK (PD98059) suppressed the lithium-induced increase in anchorage-independent growth of the keratinocytes. Our results suggested that lithium promoted transformation of nontumorigenic cells rather than progression of tumorigenic cells with preferential activation of the c-SRC/MEK/ERK pathway. Since previous pharmacokinetics studies indicated that it is possible for the serum level of lithium to reach 100 µM by drinking 2.5 L of water containing 3371 µg/L of lithium per day, the high level of lithium contamination in well drinking water in Kabul might be a potential oncogenic risk in humans.

Artificial Intelligence in Ovarian Cancer Diagnosis.

BACKGROUND/AIM: This study aimed to use artificial intelligence (AI) to predict the pathological diagnosis of ovarian tumors using patient information and data from preoperative examinations. PATIENTS AND METHODS: A total of 202 patients with ovarian tumors were enrolled, including 53 with ovarian cancer, 23 with borderline malignant tumors, and 126 with benign ovarian tumors. Using 5 machine learning classifiers, including support vector machine, random forest, naive Bayes, logistic regression, and XGBoost, we derived diagnostic results from 16 features, commonly available from blood tests, patient background, and imaging tests. We also analyzed the importance of 16 features on the prediction of disease. RESULTS: The highest accuracy was 0.80 in the machine learning algorithm of XGBoost. The evaluation of importance of the features showed different results among the correlation coefficient of the features, the regression coefficient, and the features importance of random forest. CONCLUSION: AI could play a role in the prediction of pathological diagnosis of ovarian cancer from preoperative examinations.