Pure tone audiogram classification using deep learning techniques.

OBJECTIVE: Pure tone audiometry has played a critical role in audiology as the initial diagnostic tool, offering vital insights for subsequent analyses. This study aims to develop a robust deep learning framework capable of accurately classifying audiograms across various commonly encountered tasks. DESIGN, SETTING, AND PARTICIPANTS: This single-centre retrospective study was conducted in accordance with the STROBE guidelines. A total of 12 518 audiograms were collected from 6259 patients aged between 4 and 96 years, who underwent pure tone audiometry testing between February 2018 and April 2022 at Tongji Hospital, Tongji Medical College, Wuhan, China. Three experienced audiologists independently annotated the audiograms, labelling the hearing loss in degrees, types and configurations of each audiogram. MAIN OUTCOME MEASURES: A deep learning framework was developed and utilised to classify audiograms across three tasks: determining the degrees of hearing loss, identifying the types of hearing loss, and categorising the configurations of audiograms. The classification performance was evaluated using four commonly used metrics: accuracy, precision, recall and F1-score. RESULTS: The deep learning method consistently outperformed alternative methods, including K-Nearest Neighbors, ExtraTrees, Random Forest, XGBoost, LightGBM, CatBoost and FastAI Net, across all three tasks. It achieved the highest accuracy rates, ranging from 96.75% to 99.85%. Precision values fell within the range of 88.93% to 98.41%, while recall values spanned from 89.25% to 98.38%. The F1-score also exhibited strong performance, ranging from 88.99% to 98.39%. CONCLUSIONS: This study demonstrated that a deep learning approach could accurately classify audiograms into their respective categories and could contribute to assisting doctors, particularly those lacking audiology expertise or experience, in better interpreting pure tone audiograms, enhancing diagnostic accuracy in primary care settings, and reducing the misdiagnosis rate of hearing conditions. In scenarios involving large-scale audiological data, the automated classification system could be used as a research tool to efficiently provide a comprehensive overview and statistical analysis. In the era of mobile audiometry, our deep learning framework can also help patients quickly and reliably understand their self-tested audiograms, potentially encouraging timely consultations with audiologists for further evaluation and intervention.

Dyadic association between mindfulness, family avoidance of communication about cancer and fear of cancer recurrence among breast cancer couples: A cross-sectional study.

PURPOSE: The research focused on examining the dyadic relationship between mindfulness, fear of cancer recurrence (FCR), and family avoidance of communication about cancer (FACC) within breast cancer couples. METHODS: This study utilized a cross-sectional approach to gather data from 249 breast cancer couples. Participants completed self-report measures assessing mindfulness, FCR, and FACC. The Actor-Partner Interdependence Mediation Model was applied to analyze how each individual's and their partner's mindfulness affected their own and their partner's FCR, as well as the mediating role of FACC in this relationship. RESULTS: The study found that the average FCR score for breast cancer patients was (32.59 ± 10.05), while their spouses had a score of (34.39 ± 8.60). The bootstrap method showed that self-FACC as a mediator between mindfulness in breast cancer couples and their own FCR (patient: ß = -0.044, P = 0.019; spouse: ß = -0.046, P = 0.007). Patients' FACC influenced the connection between their mindfulness and spouses' FCR (ß = -0.031, P = 0.030). CONCLUSIONS: The findings highlight the potential for interventions that focus on mindfulness and communication enhancement to alleviate FCR and improve the overall well-being of breast cancer couples.

Identifying symptom clusters among pregnant women during early and late pregnancy.

OBJECTIVES: To investigate the status of multiple psychosomatic symptoms among women and identify symptom clusters at different gestational stages. METHODS: This was a cross-sectional study and a consecutive sample of 557 pregnant women were recruited. They were asked to complete the Memorial Symptom Assessment Scale, and to supply sociodemographic and clinical information. Spearman correlation analysis, partial correlation networks, and hierarchical cluster analysis were carried out to identify the optimal number of symptom clusters. RESULTS: The top five scores for symptoms in early pregnancy were nausea, lack of appetite, feeling drowsy, lack of energy, and vomiting. Weight gain, difficulty sleeping, sweating, lack of energy, and dry mouth scored high in late pregnancy. Four clusters were identified in early pregnancy, and three clusters were determined in late pregnancy. CONCLUSIONS: Women experience multiple psychosomatic symptoms during pregnancy, and the manifestation of symptoms varies at different stages. The present study has provided new insights into symptom clusters in pregnant women.

Effects of Resilience-Promoting Interventions on Cancer Patients' Positive Adaptation and Quality of Life: A Meta-analysis.

BACKGROUND: Resilience-promoting interventions (RPIs) are increasingly used for cancer patients. However, there are few comprehensive reports on the efficacy of RPIs in cancer patients. OBJECTIVE: A meta-analysis of randomized controlled trials (RCTs) was conducted to systematically evaluate the effects of RPIs on resilience, posttraumatic growth (PTG), and quality of life in cancer patients. METHODS: Two authors conducted independent literature searches in electronic databases (PubMed, Scopus, Web of Science, MEDLINE, EBSCO [ASC], Cochrane library, China National Knowledge Infrastructure, Wan Fang Data, and Chinese Scientific and Technological Journal Database) from the first available date to February 2021. Then, eligible studies were selected, data for meta-analysis were extracted, and the risk of bias was evaluated. RESULTS: Sixteen independent randomized controlled trials with 1620 participants were included. Meta-analysis showed that RPIs significantly improved the level of resilience and PTG among cancer patients. Further analysis indicated that both group and individual interventions could enhance resilience and PTG levels. However, RPIs did not significantly enhance the quality of life in cancer patients. CONCLUSIONS: Clinical evidence from current randomized controlled trials shows that RPIs can improve the positive adaptation in cancer patients through either group intervention or individual intervention methods. In the future, the impact of RPIs on the quality of life needs further validation. IMPLICATIONS FOR PRACTICE: Interventions to enhance the positive adaptation for patients with cancer are needed. Considering that both group and individual forms of RPIs can improve resilience and PTG, future clinical intervention methods can be considered in combination with the specific situation of research implementation.

The structure of menopausal syndrome: Using network analysis to understand unique symptomatic relationships.

OBJECTIVE: To explore the network structure underlying the symptoms of menopausal syndrome and to identify the central and bridge symptoms of menopause among middle-aged women. METHODS: This is a cross-sectional survey study conducted in the Chinese community with a total of 1829 women aged 40-65 years. The Menopause Rating Scale (MRS) was used to assess the menopausal syndrome, including somato-vegetative, psychological, and urogenital subdomains. The network analysis was performed to determine the central and bridge symptoms of menopause. RESULTS: In the network of menopausal symptoms, anxiety, vaginal dryness, depressive mood, and irritability were the most central symptoms. Depressive mood, anxiety, and vaginal dryness were also detected as the bridge symptoms. The estimated network between the symptoms had good stability (CS-strength = 0.75 and CS-edge = 0.75). CONCLUSION: The present network analysis provided unique insights into the inner structure of menopausal symptoms. Psychological symptoms should be considered as the core symptoms in developing relevant interventions to improve the health and well-being of middle-aged women.

Psychosocial resources moderate the association between stress and insomnia among patients with digestive system cancers.

This study explored the profiles of psychosocial resources combined with resilience and family care, and analyzed their moderating effects on the relationship between stress and insomnia in patients with digestive system cancers. A total of 366 patients were recruited to participate in this study from two tertiary hospitals in China. They were assessed using the Perceived Stress Scale - 4 items, Insomnia Severity Index, Family Concern Index Questionnaire, and 10-item Connor-Davidson Resilience Scale. Latent profile analysis and the BCH (Bolck, Croon & Hagenaars) method were used to identify the subtypes and estimate the moderating role of psychosocial coping resources. About 62.3% of participants had insomnia symptoms. Insomnia was positively correlated to the stress (r = 0.25, P < 0.001). The latent classes were the low resources class (32.8%), the medium resources class (46.1%), and high resources class (21.1%). Among these, in low (estimate value = 0.563, P = 0.003) and medium (estimate value = 0.301, P = 0.029) resources class, stress had an effect on insomnia. There was no association between stress and insomnia in high resources class (estimate value = 0.165, P = 0.637). Stress might be associated with to insomnia problems, whereas patients with high psychosocial resources are more not vulnerable. Interventions to improve family function and resilience could contribute to easing the insomnia of patients with digestive system cancers.

Identifying the different subtypes in menopausal symptoms among middle-aged women in China: a latent class analysis.

OBJECTIVE: Many studies have focused on the severity and prevalence of menopausal symptoms among middle-aged women, which are limited by heterogeneity and diversity of subtypes. Subtyping facilitates the adaptation to prevention and clinical intervention strategies that target women. To determine the existence of significant subgroups of women with similar menopausal symptoms, a person-centered approach was used to identify potential profiles of women during the menopausal transition. In addition, we aimed to examine the association between latent subtypes and individual factors. METHODS: This cross-sectional study included 797 middle-aged women, aged 40 to 60 years, who were recruited from Shandong Province, China, between December 2017 and August 2018. We identified the subtypes in menopausal symptoms by performing a latent class analysis according to the self-reported Menopause Rating Scale and evaluated the robustness of our identified subtypes using a sensitivity analysis. Multinomial logistic regression was performed to explore the association between emergent latent subtypes and sociodemographic, clinical, and psychosocial characteristics. RESULTS: The mean age of participants was 49.83 ± 5.05 years. (1) Four potential classes were identified in middle-aged women: "severe symptoms" (14.9%), "dominant sleep-emotion symptoms" (31.4%), "physical/mental exhaustion symptoms" (32.5%), and "no symptoms" (21.2%). The four classes were also verified using a sensitivity analysis according to age and menopause status subgroups, which revealed the robust subtypes of menopausal symptoms. (2) The odds ratio of neuroticism, chronic diseases, and gynecological diseases were significantly higher for the "severe symptoms," "dominant sleep-emotion symptoms," and "physical/mental exhaustion symptoms" classes, compared to the "no symptoms" class, while the odds ratio of mindfulness and social support were lower. CONCLUSIONS: A person-centered approach for middle-aged women could address the unmet need to understand the heterogeneity of menopausal symptoms. Subtyping facilitates the identification of the potential causes of menopausal symptoms and the development of personalized interventions.

Video Summary:http://links.lww.com/MENO/A830 .

Individual and additive-effect relationships of sleep problems and severe menopausal symptoms among women in menopausal transition.

OBJECTIVE: Sleep problems and menopausal symptoms are both common complaints among midlife women. However, the associations of the quality and quantity of sleep problems with the severity of menopausal symptoms have not been well studied. Thus, this study aims to examine the relationships between individual sleep problems and the additive number of sleep problems with severe menopausal symptoms among women during the menopausal transition. METHODS: Using the convenience sampling, a total of 848 middle-aged women in China were investigated from December 2017 to August 2018. All participants completed a questionnaire on sleep problems, Menopause Rating Scale, and the general information questionnaire. Based on the cutoff of the Menopause Rating Scale, participants were divided into the nonsevere menopausal symptom group and severe menopausal symptoms group. Propensity score matching was used to balance covariates between the two groups. Stepwise binary logistic regression and restricted cubic spline were applied to analyze the associations of individual and additive sleep problems with severe menopausal symptoms. RESULTS: After propensity score matching, no significant difference was observed between the nonsevere menopausal symptoms group and severe menopausal symptoms group (Ps > 0.05). Logistic regression analysis showed that five sleep problems ("feeling too hot," "having pain," "restless legs syndrome," "taking medicine to help sleep," and "having trouble staying awake") were closely associated with severe menopausal symptoms. The restricted cubic spline curve showed an upward trend in odds ratios between the number of these five sleep problems and severe menopausal symptoms, and women were more than twice as likely to suffer severe menopausal symptoms when they experienced more than three of these individual sleep problems. CONCLUSION: Both the individual and additive number of sleep problems exerted significant effects on severe menopausal symptoms. It might be useful for healthcare providers to set guidelines to support a healthy menopausal transition for midlife women.