Detection of Adverse Event Signals with Severity Grade Classification from Cancer Patient Narrative.

Adverse event (AE) management is crucial to improve anti-cancer treatment outcomes, but it is reported that some AE signals can be missed in clinical visits. Thus, monitoring AE signals seamlessly, including events outside hospitals, would be helpful for early intervention. Here we investigated how to detect AE signals from texts written by cancer patients themselves by developing deep-learning (DL) models to classify posts mentioning AEs according to severity grade, in order to focus on those that might need immediate treatment interventions. Using patient blogs written in Japanese by cancer patients as a data source, we built DL models based on three approaches, BERT, ELECTRA, and T5. Among these models, T5 showed the best F1 scores for both Grade ≥ 1 and ≥ 2 article classification tasks (0.85 and 0.53, respectively). This model might benefit patients by enabling earlier AE signal detection, thereby improving quality of life.

Adverse event signal extraction from cancer patients' narratives focusing on impact on their daily-life activities.

Adverse event (AE) management is important to improve anti-cancer treatment outcomes, but it is known that some AE signals can be missed during clinical visits. In particular, AEs that affect patients' activities of daily living (ADL) need careful monitoring as they may require immediate medical intervention. This study aimed to build deep-learning (DL) models for extracting signals of AEs limiting ADL from patients' narratives. The data source was blog posts written in Japanese by breast cancer patients. After pre-processing and annotation for AE signals, three DL models (BERT, ELECTRA, and T5) were trained and tested in three different approaches for AE signal identification. The performances of the trained models were evaluated in terms of precision, recall, and F1 scores. From 2,272 blog posts, 191 and 702 articles were identified as describing AEs limiting ADL or not limiting ADL, respectively. Among tested DL modes and approaches, T5 showed the best F1 scores to identify articles with AE limiting ADL or all AE: 0.557 and 0.811, respectively. The most frequent AE signals were "pain or numbness", "fatigue" and "nausea". Our results suggest that this AE monitoring scheme focusing on patients' ADL has potential to reinforce current AE management provided by medical staff.

Extracting Multiple Worries From Breast Cancer Patient Blogs Using Multilabel Classification With the Natural Language Processing Model Bidirectional Encoder Representations From Transformers: Infodemiology Study of Blogs.

BACKGROUND: Patients with breast cancer have a variety of worries and need multifaceted information support. Their accumulated posts on social media contain rich descriptions of their daily worries concerning issues such as treatment, family, and finances. It is important to identify these issues to help patients with breast cancer to resolve their worries and obtain reliable information. OBJECTIVE: This study aimed to extract and classify multiple worries from text generated by patients with breast cancer using Bidirectional Encoder Representations From Transformers (BERT), a context-aware natural language processing model. METHODS: A total of 2272 blog posts by patients with breast cancer in Japan were collected. Five worry labels, "treatment," "physical," "psychological," "work/financial," and "family/friends," were defined and assigned to each post. Multiple labels were allowed. To assess the label criteria, 50 blog posts were randomly selected and annotated by two researchers with medical knowledge. After the interannotator agreement had been assessed by means of Cohen kappa, one researcher annotated all the blogs. A multilabel classifier that simultaneously predicts five worries in a text was developed using BERT. This classifier was fine-tuned by using the posts as input and adding a classification layer to the pretrained BERT. The performance was evaluated for precision using the average of 5-fold cross-validation results. RESULTS: Among the blog posts, 477 included "treatment," 1138 included "physical," 673 included "psychological," 312 included "work/financial," and 283 included "family/friends." The interannotator agreement values were 0.67 for "treatment," 0.76 for "physical," 0.56 for "psychological," 0.73 for "work/financial," and 0.73 for "family/friends," indicating a high degree of agreement. Among all blog posts, 544 contained no label, 892 contained one label, and 836 contained multiple labels. It was found that the worries varied from user to user, and the worries posted by the same user changed over time. The model performed well, though prediction performance differed for each label. The values of precision were 0.59 for "treatment," 0.82 for "physical," 0.64 for "psychological," 0.67 for "work/financial," and 0.58 for "family/friends." The higher the interannotator agreement and the greater the number of posts, the higher the precision tended to be. CONCLUSIONS: This study showed that the BERT model can extract multiple worries from text generated from patients with breast cancer. This is the first application of a multilabel classifier using the BERT model to extract multiple worries from patient-generated text. The results will be helpful to identify breast cancer patients' worries and give them timely social support.

Identification of hand-foot syndrome from cancer patients' blog posts: BERT-based deep-learning approach to detect potential adverse drug reaction symptoms.

Early detection and management of adverse drug reactions (ADRs) is crucial for improving patients' quality of life. Hand-foot syndrome (HFS) is one of the most problematic ADRs for cancer patients. Recently, an increasing number of patients post their daily experiences to internet community, for example in blogs, where potential ADR signals not captured through routine clinic visits can be described. Therefore, this study aimed to identify patients with potential ADRs, focusing on HFS, from internet blogs by using natural language processing (NLP) deep-learning methods. From 10,646 blog posts, written in Japanese by cancer patients, 149 HFS-positive sentences were extracted after pre-processing, annotation and scrutiny by a certified oncology pharmacist. The HFS-positive sentences described not only HFS typical expressions like "pain" or "spoon nail", but also patient-derived unique expressions like onomatopoeic ones. The dataset was divided at a 4 to 1 ratio and used to train and evaluate three NLP deep-learning models: long short-term memory (LSTM), bidirectional LSTM and bidirectional encoder representations from transformers (BERT). The BERT model gave the best performance with precision 0.63, recall 0.82 and f1 score 0.71 in the HFS user identification task. Our results demonstrate that this NLP deep-learning model can successfully identify patients with potential HFS from blog posts, where patients' real wordings on symptoms or impacts on their daily lives are described. Thus, it should be feasible to utilize patient-generated text data to improve ADR management for individual patients.

Preliminary Screening Method for Low Bone Mineral Density Using a Self-Reported Questionnaire among Peri- and Postmenopausal Women.

STUDY DESIGN: Retrospective cohort study. PURPOSE: We propose a method for screening for low bone mineral density (BMD) among perimenopausal and postmenopausal women using a self-reported questionnaire. OVERVIEW OF LITERATURE: Osteoporosis is a major health problem worldwide. However, it is not cost-effective to evaluate BMD in all patients. Although several tools for predicting osteoporosis have been established, they do not focus much on low BMD prior to the development of osteoporosis. METHODS: We retrospectively reviewed the medical records of 198 women aged 40-70 years who underwent mass screening for osteoporosis at our hospital between 2016 and 2019. The BMD values and the following data were collected: age, body mass index, fracture history, lower back pain, height loss, kyphosis, history of fragility fracture, family history of vertebral or hip fracture, and menopause. The reliability of each data point for the young adult mean <80% was calculated using discriminant analysis. Variables with large weight coefficients were selected and scored. This scoring tool was examined, and a cutoff score for predicting the young adult mean <80% was determined. RESULTS: Sixty-four participants (32.3%) had a young adult mean <80%. According to the weight coefficients, the following five variables were scored as follows: age ≥60 years 3 points, body mass index <22 kg/m2 3 points, lower back pain 1 point, height loss (cm) 1 point, and menopause 1 point. The area under the receiver operating characteristic curve was 0.738 (95% confidence interval, 0.669-0.807). At cutoff scores of ≥5 and <5, the sensitivity was 82.8%, with specificity of 52.0%. CONCLUSIONS: The scoring tool performed well for predicting young adult mean <80% among perimenopausal and postmenopausal women in Japan. This tool may be useful to screen for low BMD.

Advances in forecasting harmful algal blooms using machine learning models: A case study with Planktothrix rubescens in Lake Geneva.

The development of anthropic activities during the 20th century increased the nutrient fluxes in freshwater ecosystems, leading to the eutrophication phenomenon that most often promotes harmful algal blooms (HABs). Recent years have witnessed the regular and massive development of some filamentous algae or cyanobacteria in Lake Geneva. Consequently, important blooms could result in detrimental impacts on economic issues and human health. In this study, we tried to lay the foundation of an HAB forecast model to help scientists and local stakeholders with the present and future management of this peri-alpine lake. Our forecast strategy was based on pairing two machine learning models with a long-term database built over the past 34 years. We created HAB groups via a K-means model. Then, we introduced different lag times in the input of a random forest (RF) model, using a sliding window. Finally, we used a high-frequency dataset to compare the natural mechanisms with numerical interaction using individual conditional expectation plots. We demonstrate that some HAB events can be forecasted over a year scale. The information contained in the concentration data of the cyanobacteria was synthesized in the form of four intensity groups that directly depend on the P. rubescens concentration. The categorical transformation of these data allowed us to obtain a forecast with correlation coefficients that stayed above a threshold of 0.5 until one year for the counting cells and two years for the biovolume data. Moreover, we found that the RF model predicted the best P. rubescens abundance for water temperatures around 14°C. This result is consistent with the biological processes of the toxic cyanobacterium. In this study, we found that the coupling between K-means and RF models could help in forecasting the development of the bloom-forming P. rubescens in Lake Geneva. This methodology could create a numerical decision support tool, which should be a significant advantage for lake managers.

Septic arthritis of the wrist caused by Mycobacterium intracellulare: a case report.

Septic arthritis of the wrist is rare entity, especially; atypical mycobacterial infection of the wrist is extremely rare. We report a case of septic arthritis of the wrist caused by Mycobacterium intracellulare, which was successfully treated by radical debridement followed by wrist arthrodesis using vascularised fibular grafting.

Six1 is required for mouse dental follicle cell and human periodontal ligament-derived cell proliferation.

The periodontal ligament (PDL) is a connective tissue that attaches the tooth cementum to the alveolar bone and is derived from dental follicle cells (DFCs). The DFCs form fibroblasts, osteoblasts, cementoblasts, and PDL stem cells (PDLSCs). We previously reported homeobox transcription factor Six1 expression in mouse DFCs. However, the role of Six1 in periodontal tissue development is largely unknown. In this study, we analyzed SIX1 expression in mouse periodontal tissue cells during postnatal development and adulthood. We also addressed the role of SIX1 in mouse periodontium development and in human cultured PDL-derived cells (PDLCs). In mouse development, SIX1 production was abundant in DFCs and PDL cells by 2 weeks, but it was greatly diminished in the PDL at 4 weeks and in adults. Although the SIX1-positive cell distribution was sparse in the adult PDL, SIX1-positive cells were observed with low expression levels. We used 5-ethynyl-2'-deoxyuridine (EdU) for cell labeling to reveal numerous EdU/SIX1-double positive cells at 2 weeks; however, a few EdU-positive cells remained at 4 weeks. The proportion of DFCs that incorporated EdU was significantly lower in Six1-deficient mice compared with wild-type mice at E18.5. In human PDLCs, SIX1 was intensely expressed, and SIX1-knockdown using siRNA reduced proliferating PDLCs. Our results suggest that SIX1 is a key proliferation regulator in mouse DFCs and human PDLCs, which provides novel insight into Six family gene function in mammals.

Low Six4 and Six5 gene dosage improves dystrophic phenotype and prolongs life span of mdx mice.

Muscle regeneration is an important process for skeletal muscle growth and recovery. Repair of muscle damage is exquisitely programmed by cellular mechanisms inherent in myogenic stem cells, also known as muscle satellite cells. We demonstrated previously the involvement of homeobox transcription factors, SIX1, SIX4 and SIX5, in the coordinated proliferation and differentiation of isolated satellite cells in vitro. However, their roles in adult muscle regeneration in vivo remain elusive. To investigate SIX4 and SIX5 functions during muscle regeneration, we introduced knockout alleles of Six4 and Six5 into an animal model of Duchenne Muscular Dystrophy (DMD), mdx (Dmd(mdx) /Y) mice, characterized by frequent degeneration-regeneration cycles in muscles. A lower number of small myofibers, higher number of thick ones and lower serum creatine kinase and lactate dehydrogenase activities were noted in 50-week-old Six4(+/-) 5(+/-) Dmd(mdx) /Y mice than Dmd(mdx) /Y mice, indicating improvement of dystrophic phenotypes of Dmd(mdx) /Y mice. Higher proportions of cells positive for MYOD1 and MYOG (markers of regenerating myonuclei) and SIX1 (a marker of regenerating myoblasts and newly regenerated myofibers) in 12-week-old Six4(+/-) 5(+/-) Dmd(mdx) /Y mice suggested enhanced regeneration, compared with Dmd(mdx) /Y mice. Although grip strength was comparable in Six4(+/-) 5(+/-) Dmd(mdx) /Y and Dmd(mdx) /Y mice, treadmill exercise did not induce muscle weakness in Six4(+/-) 5(+/-) Dmd(mdx) /Y mice, suggesting higher regeneration capacity. In addition, Six4(+/-) 5(+/-) Dmd(mdx) /Y mice showed 33.8% extension of life span. The results indicated that low Six4 and Six5 gene dosage improved dystrophic phenotypes of Dmd(mdx) /Y mice by enhancing muscle regeneration, and suggested that SIX4 and SIX5 are potentially useful de novo targets in therapeutic applications against muscle disorders, including DMD.

Activation of Six1 Expression in Vertebrate Sensory Neurons.

SIX1 homeodomain protein is one of the essential key regulators of sensory organ development. Six1-deficient mice lack the olfactory epithelium, vomeronasal organs, cochlea, vestibule and vestibuloacoustic ganglion, and also show poor neural differentiation in the distal part of the cranial ganglia. Simultaneous loss of both Six1 and Six4 leads to additional abnormalities such as small trigeminal ganglion and abnormal dorsal root ganglia (DRG). The aim of this study was to understand the molecular mechanism that controls Six1 expression in sensory organs, particularly in the trigeminal ganglion and DRG. To this end, we focused on the sensory ganglia-specific Six1 enhancer (Six1-8) conserved between chick and mouse. In vivo reporter assays using both animals identified an important core region comprising binding consensus sequences for several transcription factors including nuclear hormone receptors, TCF/LEF, SMAD, POU homeodomain and basic-helix-loop-helix proteins. The results provided information on upstream factors and signals potentially relevant to Six1 regulation in sensory neurons. We also report the establishment of a new transgenic mouse line (mSix1-8-NLSCre) that expresses Cre recombinase under the control of mouse Six1-8. Cre-mediated recombination was detected specifically in ISL1/2-positive sensory neurons of Six1-positive cranial sensory ganglia and DRG. The unique features of the mSix1-8-NLSCre line are the absence of Cre-mediated recombination in SOX10-positive glial cells and central nervous system and ability to induce recombination in a subset of neurons derived from the olfactory placode/epithelium. This mouse model can be potentially used to advance research on sensory development.

Additional gastrectomy after endoscopic mucosal resection for early gastric cancer.

The aim of this study was to examine the clinicopathological characteristics of cases undergoing additional gastrectomy after endoscopic mucosal resection (EMR) for early gastric cancer (EGC) and the appropriate strategy for treating those after incomplete EMR. We studied 16 patients who underwent additional gastrectomy after EMR for EGC. The reasons for additional gastrectomy were positive horizontal margin (8 cases), indeterminate horizontal margin (2 cases), positive vertical margin (4 cases), submucosal invasion (7 cases), lymphatic invasion (4 cases), venous invasion (1 case), and local recurrence (2 cases, including overlapped cases). Residual cancer was found in 6 of the 13 cases (46%), while no lymph node metastasis was found in any case; there were cases in which local resection was possible depending on tumor location and cases in which additional gastrectomy was performed due to suspected residual cancer but the specimens were free of cancer; follow-up without intervention appears to be feasible in some of these cases. When performing additional gastrectomy after EMR, the most appropriate method should be chosen so as not to worsen the quality of life of the patient while taking radical cure into consideration.

Evaluation of postgastrectomy symptoms after distal gastrectomy with Billroth-I reconstruction using the Postgastrectomy Syndrome Assessment Scale-45 (PGSAS-45).

BACKGROUND: Distal gastrectomy with Billroth-I reconstruction (DGBI) is the most commonly used treatment approach for gastric cancer patients in Japan. The aim of this study was to assess and elucidate the effect of different surgical DGBI techniques on postgastrectomy syndrome (PGS) using the Postgastrectomy Syndrome Assessment Scale-45 (PGSAS-45). METHODS: The newly created PGSAS-45 composed of 45 questions was used in this study. The scale was distributed to 2,922 patients who underwent gastrectomy >1 year prior. Completed forms were returned by 2,520 patients (86 %), of which 909 underwent DGBI. The effects of performing the Kocher maneuver, differences in the size of the gastric remnant and differences the anastomosis technique had on the main outcome measures of PGSAS-45 were analyzed. RESULTS: Patients for whom the Kocher maneuver was performed experienced significantly worse meal-related distress and poorer quality of ingestion. Additionally, a less satisfactory physical and mental component summary from the SF-8 was reported. Patients with larger gastric remnants showed significantly better scores on the diarrhea subscale, a slightly better trend for the need for additional meals and dissatisfaction with eating. Regarding the anastomosis technique, there was no difference between the hand-sewn, circular stapler (CS) and linear stapler end-to-end anastomosis, and there was also no difference between the end-to-end and side-to-end anastomosis with the CS. CONCLUSIONS: The Kocher maneuver may increase meal-related distress, reduce the quality of ingestion and impart a negative effect on quality of life (QOL). The larger gastric remnants may cause reduction in diarrhea and an improvement in meal-related scores.

Post-traumatic osteonecrosis of the lunate after fracture of the distal radius.

We present a case of post-traumatic osteonecrosis of the lunate after fracture of the distal radius. Post-traumatic osteonecrosis of the carpal lunate after a fracture of the distal radius has, to our knowledge, not been reported previously. We treated the patient with vascularised bone graft from the distal radius, with a satisfactory result.

Six1 is a key regulator of the developmental and evolutionary architecture of sensory neurons in craniates.

BACKGROUND: Various senses and sensory nerve architectures of animals have evolved during adaptation to exploit diverse environments. In craniates, the trunk sensory system has evolved from simple mechanosensory neurons inside the spinal cord (intramedullary), called Rohon-Beard (RB) cells, to multimodal sensory neurons of dorsal root ganglia (DRG) outside the spinal cord (extramedullary). The fish and amphibian trunk sensory systems switch from RB cells to DRG during development, while amniotes rely exclusively on the DRG system. The mechanisms underlying the ontogenic switching and its link to phylogenetic transition remain unknown. RESULTS: In Xenopus, Six1 overexpression promoted precocious apoptosis of RB cells and emergence of extramedullary sensory neurons, whereas Six1 knockdown delayed the reduction in RB cell number. Genetic ablation of Six1 and Six4 in mice led to the appearance of intramedullary sensory neuron-like cells as a result of medial migration of neural crest cells into the spinal cord and production of immature DRG neurons and fused DRG. Restoration of SIX1 expression in the neural crest-linage partially rescued the phenotype, indicating the cell autonomous requirements of SIX1 for normal extramedullary sensory neurogenesis. Mouse Six1 enhancer that mediates the expression in DRG neurons activated transcription in Xenopus RB cells earlier than endogenous six1 expression, suggesting earlier onset of mouse SIX1 expression than Xenopus during sensory development. CONCLUSIONS: The results indicated the critical role of Six1 in transition of RB cells to DRG neurons during Xenopus development and establishment of exclusive DRG system of mice. The study provided evidence that early appearance of SIX1 expression, which correlated with mouse Six1 enhancer, is essential for the formation of DRG-dominant system in mice, suggesting that heterochronic changes in Six1 enhancer sequence play an important role in alteration of trunk sensory architecture and contribute to the evolution of the trunk sensory system.

Clinicopathological features of CA19-9-producing gastric cancer.

BACKGROUND/AIMS: The aims of this study were to define CA19-9-producing gastric cancer and investigate its clinicopathological features. METHODOLOGY: Twenty-three patients showing high preoperative serum CA19-9 levels (> or = 38 U/mL) were enrolled in this retrospective cohort study. The CA19-9 cut-off level was determined on the basis of receiver operating characteristic analysis of CA19-9 levels obtained from patients having survived for 3 years after surgery. Patients in whom the CA19-9 level was the cut-off level or higher were defined as having CA19-9-producing gastric cancer (Group A), and their clinicopathological features were compared with those of patients showing CA19-9 levels less than the cut-off level (Group B). RESULTS: The preoperative serum CA19-9 cut-off level was set at 77 U/mL. In Group A, lymph node metastasis was seen in all 11 patients, with the incidence being higher than that in Group B (p <0.001). The number of patients with stage III or greater disease was 10 in Group A, compared with only 3 in Group B (p < 0.001). The independent prognostic factors were preoperative serum CA19-9 levels, venous invasion and tumor stage. CONCLUSIONS: CA19-9-producing gastric cancer is a type of gastric cancer with poor prognosis and characterized by preoperative serum CA19-9 > or = 77 U/mL.

Functional reconstruction of bilateral injuries to the dorsum of hand using radial forearm tendocutaneous flaps.

We treated a patient with skin and tendon defects of both hands as a result of injury by a heat press. There have been no reports of bilateral hand injuries being treated using simultaneous bilateral tendocutaneous flaps. In this case, we reconstructed the injured tissue using simultaneous bilateral radial forearm tendocutaneous flaps, with satisfactory results.

Reasons and risk factors for intraoperative conversion from laparoscopic to open cholecystectomy.

PURPOSE: The aim of this study was to analyze the reasons and risk factors for intraoperative conversion from laparoscopic cholecystectomy to open cholecystectomy. METHODS: The study involved 407 patients in whom laparoscopic cholecystectomy was planned between January 1998 and July 2006. The patients were divided into two groups (the LC completed group and the conversion group), and the two groups were compared. RESULTS: Laparoscopic surgery was intraoperatively converted to open surgery in 47 cases (11.6 %). The reasons for the conversion consisted of adhesions (15 cases), inflammation (8 cases), adhesion plus inflammation (9 cases), bleeding (8 cases), common bile duct injury (4 cases), suspected common bile duct injury (1 case), injury of the duodenal bulb (1 case) and respiratory disorder (1 case). The group of patients who required conversion to open surgery had a significantly higher percentage of males (P = 0.042) and prevalence of acute cholecystitis (P < 0.001) than the group of patients for whom laparoscopic surgery could be completed. A multivariate logistic regression analysis of these significant predictors showed that male sex [odds ratio (OR) 1.95] and acute cholecystitis (OR 8.45) were significant. CONCLUSION: Particular attention is needed when laparoscopic surgery is considered for male patients with acute cholecystitis.

Conservative treatment of the isolated dislocation of the pisiform bone.

We report isolated dislocation of the right pisiform bone dislocated distal and medial to the triquetrum bone in a young adult after a fall. Manipulation and closed reduction under intravenous regional anaesthesia resulted in full functional recovery and a good radiological outcome.

Ewing sarcoma of the proximal phalanx: case report.

We report a case of primary Ewing sarcoma of the proximal phalanx of the right middle finger in an 18-year-old boy. He was treated with neoadjuvant chemotherapy, followed by ray amputation. To restore maximum function, the index ray was transferred to the base of the third metacarpal bone and fixed with a plate. The function of his right hand after the operation was excellent and the cosmetic appearance acceptable. There was no evidence of local recurrence or metastasis after 20 months follow up.

Bilateral pediatric Kienböck's disease: a case report.

Bilateral Kienböck's disease in pediatrics is extremely rare. We report a case of a 14-year-old boy with bilateral pediatric Kienböck's disease who was treated by temporary scaphotrapeziotrapezoidal joint fixation, with a good clinical result and radiographic results.