Isolated adrenocorticotropic hormone deficiency (IAD) is a rare pituitary disorder that can cause adrenal insufficiency. However, due to its nonspecific symptoms, its diagnosis is often difficult and may be delayed. Patients with IAD require lifelong glucocorticoid (GC) replacement therapy. Contrastingly, GC-induced secondary adrenal insufficiency is a reversible condition that arises when patients receiving GC therapy reduce their GC dosage or discontinue therapy. Differentiating between IAD and GC-induced secondary adrenal insufficiency is clinically crucial. We report a unique case that required differentiation between these two conditions. A 71-year-old Japanese woman presented with symptoms of adrenal insufficiency after discontinuation of GC therapy for eosinophilic esophagitis. We conducted detailed interviews and repeated the endocrinological examinations. We concluded that her symptoms were owing to IAD rather than GC-induced secondary adrenal insufficiency. She began a lifelong hydrocortisone replacement therapy. This case suggests that when caring for patients undergoing GC therapy, it is important to consider the possibility of coexisting IAD and arrange endocrinological examinations if signs of adrenal insufficiency arise during the gradual reduction of GC treatment.

Ocular manifestations often serve as critical indicators of underlying systemic diseases, providing valuable diagnostic and prognostic information. This comprehensive review aims to elucidate the complex interplay between ocular symptoms and systemic conditions, emphasising the importance of early recognition and interdisciplinary collaboration in patient management. The review encompasses various systemic diseases, including cardiovascular, autoimmune, infectious, neurological, endocrine, hematologic, genetic, dermatologic, gastrointestinal, hepatic, renal, and connective tissue disorders, highlighting their specific ocular manifestations. Diagnostic approaches, including ophthalmologic examination techniques, imaging modalities, and laboratory tests, are discussed to enhance diagnostic accuracy. Furthermore, the review outlines current management and treatment strategies, emphasising the need for a multidisciplinary approach to care. Emerging therapies and future research directions are also explored, underscoring the necessity of continued innovation in this field. This review aims to improve clinical practices, promote integrative healthcare, and ultimately enhance patient outcomes by providing a detailed overview of ocular manifestations in systemic diseases.

Recurrent or metastatic head and neck squamous cell carcinoma (R/M HNSCC) is a challenging disease, requiring personalized management by a multidisciplinary team. The aim of this retrospective multicentric study was to characterize real-world healthcare resource use and patient care for R/M HNSCC in Portugal during the first year after diagnosis. A total of 377 patients ineligible for curative treatment were included, mostly male (92.8%), aged 50-69 years (74.5%), with heavy alcohol (72.7%) or smoking habits (89.3%). Oropharynx (33.2%) and oral cavity (28.7%) were primary tumor locations, with lung metastases being the most common (61.4%). Eligible patients for systemic treatment with palliative intent (80.6%) received up to four treatment lines, with varied regimens. Platinum-based combination chemotherapy dominated first-line treatment (>70%), while single-agent chemotherapy and anti-PD1 immunotherapy were prevalent in later lines. Treatment approaches were uniform across disease stages and primary tumor locations but varied geographically. Treated patients received more multidisciplinary support than those who were ineligible. This study provides the first Portuguese real-world description of R/M HNSCC patient characteristics, treatment patterns, and supportive care during the year after diagnosis, highlighting population heterogeneity and aiming to improve patient management.

BACKGROUND: An increasing number of clinical trials for new therapeutic strategies are underway or being considered for dystrophinopathy. Having detailed data on the natural progression of this condition is crucial for assessing the effectiveness of new drugs. However, there\'s a lack of data regarding the long-term data on the natural course and how it\'s managed in China. In this study, we offer a comprehensive overview of clinical and molecular findings, as well as treatment outcomes in the Chinese population.
METHODS: Institutional data on all patients with dystrophinopathy from August 2011 to August 2021 were retrospectively reviewed. The data included geographic distribution, age at diagnosis, molecular findings, and treatment options, such as corticosteroids, cardiac interventions, and clinical outcomes.
RESULTS: In total, 2097 patients with dystrophinopathy, including 1703 cases of Duchenne muscular dystrophy (DMD), 311 cases of Becker muscular dystrophy (BMD), 46 cases of intermediate muscular dystrophy (IMD), and 37 cases categorized as \"pending\" (individuals with an undetermined phenotype), were registered in the Children\'s Hospital of Fudan University database for dystrophinopathy from August 2011 to August 2021. The spectrum of identified variants included exonic deletions (66.6%), exonic duplications (10.7%), nonsense variants (10.3%), splice-site variants (4.5%), small deletions (3.5%), small insertions/duplications (1.8%), and missense variants (0.9%). Four deep intronic variants and two inversion variants were identified. Regarding treatment, glucocorticoids were administered to 54.4% of DMD patients and 39.1% of IMD patients. The median age at loss of ambulation was 2.5 years later in DMD patients who received glucocorticoid treatment. Overall, one cardiac medicine at least was prescribed to 7.4% of DMD patients, 8.3% of IMD patients, and 2.6% of BMD patients. Additionally, ventilator support was required by four DMD patients. Eligibility for exon skipping therapy was found in 55.3% of DMD patients, with 12.9%, 10%, and 9.6% of these patients being eligible for skipping exons 51, 53, and 45, respectively.
CONCLUSIONS: This is one of the largest studies to have evaluated the natural history of dystrophinopathy in China, which is particularly conducive to the recruitment of eligible patients for clinical trials and the provision of real-world data to support drug development.

Left ventricular assist devices (LVADs) are increasingly implanted in patients with advanced heart failure. Currently, LVAD care is predominantly concentrated at specialized tertiary care hospitals. However, the increasing workload and logistical burden for implanting centres pose significant challenges to accessing care for individual patients in remote areas. An emerging approach to LVAD patient management is the use of a shared care model (SCM), which facilitates collaboration between implanting centres and local non-implanting hospitals. This scoping review explores and synthesizes the current scientific evidence on the use of SCMs in LVAD care management. Eligible studies were identified in EMBASE, PubMed MEDLINE, Web of Science, Cochrane and Google Scholar. Findings were synthesized in accordance with PRISMA-ScR guidelines. Of the 950 records screened, five articles met the inclusion criteria. Four review articles focused on the proposed benefits and challenges of using SCMs. Main benefits included improved patient satisfaction and continuity of care. Important challenges were initial education of non-implanting centre staff and maintaining competency. One prospective study showed that absence of LVAD-specific care was associated with impaired survival and higher rates of pump thrombosis and LVAD-related infections. The use of SCMs is a promising approach in the long-term management of LVAD patients. However, sufficient evidence about the impact of SCMs on patients and the healthcare system is not currently available. Standardized protocols based on prospective studies are needed to develop safe and effective shared care for LVAD patients.

BACKGROUND: Machine learning (ML) risk prediction models, although much more accurate than traditional statistical methods, are inconvenient to use in clinical practice due to their nontransparency and requirement of a large number of input variables.
OBJECTIVE: We aimed to develop a precise, explainable, and flexible ML model to predict the risk of in-hospital mortality in patients with ST-segment elevation myocardial infarction (STEMI).
METHODS: This study recruited 18,744 patients enrolled in the 2013 China Acute Myocardial Infarction (CAMI) registry and 12,018 patients from the China Patient-Centered Evaluative Assessment of Cardiac Events (PEACE)-Retrospective Acute Myocardial Infarction Study. The Extreme Gradient Boosting (XGBoost) model was derived from 9616 patients in the CAMI registry (2014, 89 variables) with 5-fold cross-validation and validated on both the 9125 patients in the CAMI registry (89 variables) and the independent China PEACE cohort (10 variables). The Shapley Additive Explanations (SHAP) approach was employed to interpret the complex relationships embedded in the proposed model.
RESULTS: In the XGBoost model for predicting all-cause in-hospital mortality, the variables with the top 8 most important scores were age, left ventricular ejection fraction, Killip class, heart rate, creatinine, blood glucose, white blood cell count, and use of angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin II receptor blockers (ARBs). The area under the curve (AUC) on the CAMI validation set was 0.896 (95% CI 0.884-0.909), significantly higher than the previous models. The AUC for the Global Registry of Acute Coronary Events (GRACE) model was 0.809 (95% CI 0.790-0.828), and for the TIMI model, it was 0.782 (95% CI 0.763-0.800). Despite the China PEACE validation set only having 10 available variables, the AUC reached 0.840 (0.829-0.852), showing a substantial improvement to the GRACE (0.762, 95% CI 0.748-0.776) and TIMI (0.789, 95% CI 0.776-0.803) scores. Several novel and nonlinear relationships were discovered between patients\' characteristics and in-hospital mortality, including a U-shape pattern of high-density lipoprotein cholesterol (HDL-C).
CONCLUSIONS: The proposed ML risk prediction model was highly accurate in predicting in-hospital mortality. Its flexible and explainable characteristics make the model convenient to use in clinical practice and could help guide patient management.
BACKGROUND: ClinicalTrials.gov NCT01874691; https://clinicaltrials.gov/study/NCT01874691.

BACKGROUND: Poor anticoagulation management of warfarin may lead to patient admission, prolonged hospital stays, and even death due to anticoagulation-related adverse events. Traditional non-web-based outpatient clinics struggle to provide ideal anticoagulation management services for patients, and there is a need to explore a safer, more effective, and more convenient mode of warfarin management.
OBJECTIVE: This study aimed to compare differences in the quality of anticoagulation management and clinical adverse events between a web-based management model (via a smartphone app) and the conventional non-web-based outpatient management model.
METHODS: This study is a prospective cohort research that includes multiple national centers. Patients meeting the nadir criteria were split into a web-based management group using the Alfalfa app or a non-web-based management group with traditional outpatient management, and they were then monitored for a 6-month follow-up period to collect coagulation test results and clinical events. The effectiveness and safety of the 2 management models were assessed by the following indicators: time in therapeutic range (TTR), bleeding events, thromboembolic events, all-cause mortality events, cumulative event rates, and the distribution of the international normalized ratio (INR).
RESULTS: This national multicenter cohort study enrolled 522 patients between June 2019 and May 2021, with 519 (99%) patients reaching the follow-up end point, including 260 (50%) in the non-web-based management group and 259 (50%) in the web-based management group. There were no observable differences in baseline characteristics between the 2 patient groups. The web-based management group had a significantly higher TTR than the non-web-based management group (82.4% vs 71.6%, P<.001), and a higher proportion of patients received effective anticoagulation management (81.2% vs 63.5%, P<.001). The incidence of minor bleeding events in the non-web-based management group was significantly higher than that in the web-based management group (12.1% vs 6.6%, P=.048). Between the 2 groups, there was no statistically significant difference in the incidence of severe bleeding and thromboembolic and all-cause death events. In addition, compared with the non-web-based management group, the web-based management group had a lower proportion of INR in the extreme subtreatment range (17.6% vs 21.3%) and severe supertreatment range (0% vs 0.8%) and a higher proportion in the treatment range (50.4% vs 43.1%), with statistical significance.
CONCLUSIONS: Compared with traditional non-web-based outpatient management, web-based management via the Alfalfa app may be more beneficial because it can enhance patient anticoagulation management quality, lower the frequency of small bleeding events, and improve INR distribution.

BACKGROUND: Primary malignant melanoma of the cervix (PMMC) is an extremely rare disease that originates from primary cervical malignant melanoma and frequently represents a challenge in disease diagnosis due to unclarified clinical and histological presentations, particularly those without melanin.
METHODS: Here, we report a case of amelanotic PMMC, with a history of breast cancer and thyroid carcinoma. The patient was finally diagnosed by immunohistochemical staining and staged as IB2 based on the International Federation of Gynecology and Obstetrics with reference to National Comprehensive Cancer Network guidelines and was treated with radical hysterectomy, bilateral salpingo-oophorectomy and pelvic lymphadenectomy. She then received combination therapy consisting of immunotherapy with tislelizumab and radiofrequency hyperthermia. She has remained free of disease for more than 1 year.
CONCLUSIONS: The differential diagnosis process reenforced the notion that immunohistochemical staining is the most reliable approach for amelanotic PMMC diagnosis. Due to the lack of established therapeutic guidelines, empirical information from limited available studies does not provide the rationale for treatment-decision making. By integrating \'omics\' technologies and patient-derived xenografts or mini-patient-derived xenograft models this will help to identify selective therapeutic window(s) and screen the appropriate therapeutics for targeted therapies, immune checkpoint blockade or combination therapy strategies effectively and precisely that will ultimately improve patient survival.

BACKGROUND: Acute coronary syndrome (ACS) is a severe cardiovascular disease with globally rising incidence and mortality rates. Traditional risk assessment tools are widely used but are limited due to the complexity of the data.
METHODS: This study introduces a gated Transformer model utilizing machine learning to analyze electronic health records (EHRs) for an enhanced prediction of major adverse cardiovascular events (MACEs) in ACS patients. The model\'s efficacy was evaluated using metrics such as area under the curve (AUC), precision-recall (PR), and F1-scores. Additionally, a patient management platform was developed to facilitate personalized treatment strategies.
RESULTS: Incorporating a gating mechanism substantially improved the Transformer model\'s performance, especially in identifying true-positive cases. The TabTransformer+Gate model demonstrated an AUC of 0.836, a 14% increase in average precision (AP), and a 6.2% enhancement in accuracy, significantly outperforming other deep learning approaches. The patient management platform enabled healthcare professionals to effectively assess patient risks and tailor treatments, improving patient outcomes and quality of life.
CONCLUSIONS: The integration of a gating mechanism within the Transformer model markedly increases the accuracy of MACE risk predictions in ACS patients, optimizes personalized treatment, and presents a novel approach for advancing clinical practice and research.

Background Breast cancer patients often experience complications related to the disease or its treatment. With the rising average life expectancy, age is becoming less of a factor in treatment decisions for this condition. This study aims to evaluate differences in breast cancer complications among various age groups in patients referred to a hospital\'s physical medicine and rehabilitation (PMR) department. Methodology A retrospective study was conducted among all breast cancer patients evaluated in a PMR department between November 2019 and March 2021. Data were collected from patients\' clinical files. SPSS® version 24 (IBM Corp., Armonk, NY, USA) was used for data analysis. Results We assessed 85 patients with a mean age of 56 years, finding that shoulder pain was the primary referral reason, reported by 85.9% of patients, followed by lymphedema in 32% of cases. Patients aged 56-65 years exhibited greater deficits in shoulder mobility compared to those between 66 and 75 years old, as well as greater functional limitations compared to other age groups. Most patients reported symptoms post-surgery, with an average delay of 24 months in PMR consultation. Despite this, nearly all patients (89.3%) reported clinical improvement following interventions. Conclusions We found that individuals in the 56-65-year age group were more prone to develop functional and shoulder mobility limitations. Despite delayed consultation, the majority of patients experienced clinical improvement, highlighting the intervention effectiveness of PMR interventions. These findings suggest that age alone may not be a determining factor in the reported breast cancer sequelae, implying the influence of other contributing factors in patient management. Further research is needed to elucidate the underlying mechanisms contributing to the diverse burden of disease sequelae observed across different age groups and to devise tailored interventions.