RESUMEN

Introduction: blood centres are often faced with the problem of donor lapsing resulting in loss of donors from the already strained donor pool. In Zimbabwe, 70% of the donated blood comes from younger donors aged 40 years and below, who at the same time, have high attrition rates. This study seeks to apply the concept of survival analysis in analysing blood donor lapsing rates. Methods: in analysing the donor lapsing and retention rates, data on 450 first-time blood donors at the National Blood Service Zimbabwe, in Harare´s blood bank for the period 2014 to 2017 was extracted from the donors´ database. The Cox proportional hazards (Cox PH) and Kaplan-Meier methods were applied in the analysis. Donor demographic characteristics suspected of having effect on donor lapsing and retention were identified and analysed. Results: the study findings show that 56.9% of the donors had lapsed by the end of the four-year study period. Results from the multiple Cox PH model indicate that donor age had a significant effect on blood donor retention time (p = 0.000918 < 0.05). The hazard ratio (HR) = 0.615 with 95% CI: (0.461; 0.820) shows that the relatively older donors had a lower hazard (38.5% lower) of lapsing compared to the hazard for younger donors. The effect of gender, blood donor group and donation time interval on donor retention and attrition were not statistically significant. Male donors had HR = 1.03; 95% CI (0.537; 1.99) with (p = 0.922 > 0.05) and donors with a 4-month interval between donations had HR = 1.31; 95% CI (0.667; 2.59) with (p = 0.430 > 0.05). Conclusion: the study confirmed the problem of donor attrition faced by blood centres. The age of the donor had a significant effect on the retention time of blood donors before lapsing. The older the blood donor, the lower the risk of lapsing. The Zimbabwe National Blood Service (NBSZ) Blood Centre authorities should have a critical mass of individuals above 40 years as potential blood donors because of their reliability in blood donation according to the study findings.

Asunto(s)

Bancos de Sangre , Donantes de Sangre , Humanos , Zimbabwe , Donantes de Sangre/estadística & datos numéricos , Masculino , Femenino , Adulto , Adulto Joven , Persona de Mediana Edad , Bancos de Sangre/estadística & datos numéricos , Factores de Edad , Factores de Tiempo , Modelos de Riesgos Proporcionales , Análisis de Supervivencia , Estimación de Kaplan-Meier , Adolescente

RESUMEN

Prognostic studies can provide important information about disease biology and improve the use of biomarkers to optimize treatment decisions. METHODS: A total of 199 patients with advanced melanoma treated with BRAF + MEK inhibitors were included in our single-center retrospective study. We analyzed the risk of progression and death using multivariate Cox proportional hazard models. The predictive effect of prognostic factors on progression-free survival (PFS) was evaluated in ROC analysis. RESULTS: We found that primary tumor localization, Clark level, pT category, baseline M stage and baseline serum S100B are independent and significant prognostic factors for PFS. The discriminative power of the combination of these factors was excellent for predicting 18 month PFS (AUC 0.822 [95% CI 0.727; 0.916], p < 0.001). Primary tumor localization on the extremities, Clark level V, baseline M1c stage or M1d stage, and elevated baseline serum S100B and LDH levels were independently and significantly associated with unfavorable overall survival (OS). CONCLUSION: Baseline M stage and serum S100B appear to be independent prognostic factors for both PFS and OS in melanoma patients treated with BRAF + MEK inhibitors. We newly identified significant and independent prognostic effects of primary tumor localization and Clark level on survival that warrant further investigation.

RESUMEN

Background: Musculoskeletal injuries (MSKIs) are endemic in military populations. Thus, it is essential to identify and mitigate MSKI risks. Time-to-event machine learning models utilizing self-reported questionnaires or existing data (e.g., electronic health records) may aid in creating efficient risk screening tools. Methods: A total of 4,222 U.S. Army Service members completed a self-report MSKI risk screen as part of their unit's standard in-processing. Additionally, participants' MSKI and demographic data were abstracted from electronic health record data. Survival machine learning models (Cox proportional hazard regression (COX), COX with splines, conditional inference trees, and random forest) were deployed to develop a predictive model on the training data (75%; n = 2,963) for MSKI risk over varying time horizons (30, 90, 180, and 365 days) and were evaluated on the testing data (25%; n = 987). Probability of predicted risk (0.00-1.00) from the final model stratified Service members into quartiles based on MSKI risk. Results: The COX model demonstrated the best model performance over the time horizons. The time-dependent area under the curve ranged from 0.73 to 0.70 at 30 and 180 days. The index prediction accuracy (IPA) was 12% better at 180 days than the IPA of the null model (0 variables). Within the COX model, "other" race, more self-reported pain items during the movement screens, female gender, and prior MSKI demonstrated the largest hazard ratios. When predicted probability was binned into quartiles, at 180 days, the highest risk bin had an MSKI incidence rate of 2,130.82 ± 171.15 per 1,000 person-years and incidence rate ratio of 4.74 (95% confidence interval: 3.44, 6.54) compared to the lowest risk bin. Conclusion: Self-reported questionnaires and existing data can be used to create a machine learning algorithm to identify Service members' MSKI risk profiles. Further research should develop more granular Service member-specific MSKI screening tools and create MSKI risk mitigation strategies based on these screenings.

RESUMEN

Accurate prediction of postoperative recurrence is important for optimizing the treatment strategies for non-small cell lung cancer (NSCLC). Previous studies identified the PD-L1 expression in NSCLC as a risk factor for postoperative recurrence. This study aimed to examine the contribution of PD-L1 expression to predicting postoperative recurrence using machine learning. The clinical data of 647 patients with NSCLC who underwent surgical resection were collected and stratified into training (80%), validation (10%), and testing (10%) datasets. Machine learning models were trained on the training data using clinical parameters including PD-L1 expression. The top-performing model was assessed on the test data using the SHAP analysis and partial dependence plots to quantify the contribution of the PD-L1 expression. Multivariate Cox proportional hazards model was used to validate the association between PD-L1 expression and postoperative recurrence. The random forest model demonstrated the highest predictive performance with the SHAP analysis, highlighting PD-L1 expression as an important feature, and the multivariate Cox analysis indicated a significant increase in the risk of postoperative recurrence with each increment in PD-L1 expression. These findings suggest that variations in PD-L1 expression may provide valuable information for clinical decision-making regarding lung cancer treatment strategies.

Asunto(s)

Antígeno B7-H1 , Carcinoma de Pulmón de Células no Pequeñas , Neoplasias Pulmonares , Recurrencia Local de Neoplasia , Humanos , Carcinoma de Pulmón de Células no Pequeñas/cirugía , Carcinoma de Pulmón de Células no Pequeñas/metabolismo , Carcinoma de Pulmón de Células no Pequeñas/patología , Antígeno B7-H1/metabolismo , Antígeno B7-H1/genética , Neoplasias Pulmonares/cirugía , Neoplasias Pulmonares/metabolismo , Neoplasias Pulmonares/patología , Masculino , Femenino , Persona de Mediana Edad , Anciano , Factores de Riesgo , Aprendizaje Automático , Biomarcadores de Tumor/metabolismo , Modelos de Riesgos Proporcionales , Periodo Posoperatorio , Pronóstico

RESUMEN

The prediction of the susceptibility of an individual to a certain disease is an important and timely research area. An established technique is to estimate the risk of an individual with the help of an integrated risk model, that is, a polygenic risk score with added epidemiological covariates. However, integrated risk models do not capture any time dependence, and may provide a point estimate of the relative risk with respect to a reference population. The aim of this work is twofold. First, we explore and advocate the idea of predicting the time-dependent hazard and survival (defined as disease-free time) of an individual for the onset of a disease. This provides a practitioner with a much more differentiated view of absolute survival as a function of time. Second, to compute the time-dependent risk of an individual, we use published methodology to fit a Cox's proportional hazard model to data from a genetic SNP study of time to Alzheimer's disease (AD) onset, using the lasso to incorporate further epidemiological variables such as sex, APOE (apolipoprotein E, a genetic risk factor for AD) status, 10 leading principal components, and selected genomic loci. We apply the lasso for Cox's proportional hazards to a data set of 6792 AD patients (composed of 4102 cases and 2690 controls) and 87 covariates. We demonstrate that fitting a lasso model for Cox's proportional hazards allows one to obtain more accurate survival curves than with state-of-the-art (likelihood-based) methods. Moreover, the methodology allows one to obtain personalized survival curves for a patient, thus giving a much more differentiated view of the expected progression of a disease than the view offered by integrated risk models. The runtime to compute personalized survival curves is under a minute for the entire data set of AD patients, thus enabling it to handle datasets with 60,000-100,000 subjects in less than 1 h.

RESUMEN

BACKGROUND: Globally, infant mortality is one of the major public health threats, especially in low-income countries. The infant mortality rate of Somalia stands at 73 deaths per 1000 live births, which is one of the highest infant death rates in the region as well as in the world. Therefore, the aim of this study was to ascertain the risk factors of infant mortality in Somalia using national representative data. METHOD: In this study, data from the Somali Health and Demographic Survey (SHDS), conducted for the first time in Somalia in 2018/2019 and released in 2020, were utilized. The analysis of the data involved employing the Chi-square test as a bivariate analysis. Furthermore, a multivariate Cox proportional hazard model was applied to accommodate potential confounders that act as risk factors for infant death. RESULTS: The study found that infant mortality was highest among male babies, multiple births, and those babies who live in rural areas, respectively, as compared to their counterparts. Those mothers who delivered babies with small birth size and belonged to a poor wealth index experienced higher infant mortality than those mothers who delivered babies with average size and belonged to a middle or rich wealth index. Survival analysis indicated that mothers who did use ANC services (HR = 0.740; 95% CI = 0.618-0.832), sex of the baby (HR = 0.661; 95% CI = 0.484-0.965), duration of pregnancy (HR = 0.770; 95% CI = 0.469-0.944), multiple births (HR = 1.369; 1.142-1.910) and place of residence (HR = 1.650; 95% CI = 1.451-2.150) were found to be statistically significantly related to infant death. CONCLUSION: The study investigated the risk factors associated with infant mortality by analyzing data from the first Somali Health and Demographic Survey (SHDS), which included a representative sample of the country's population. Place of residence, gestational duration, infant's gender, antenatal care visits, and multiple births were identified as determinants of infant mortality. Given that infant mortality poses a significant public health concern, particularly in crisis-affected countries like Somalia, intervention programs should prioritize the provision of antenatal care services, particularly for first-time mothers. Moreover, these programs should place greater emphasis on educating women about the importance of receiving antenatal care and family planning services, in order to enhance their awareness of these vital health services and their positive impact on infant survival rates.

Asunto(s)

Mortalidad Infantil , Humanos , Somalia/etnología , Mortalidad Infantil/etnología , Factores de Riesgo , Lactante , Femenino , Masculino , Recién Nacido , Adulto , Encuestas Epidemiológicas , Atención Prenatal/estadística & datos numéricos , Adulto Joven , Modelos de Riesgos Proporcionales , Factores Socioeconómicos , Embarazo

RESUMEN

PURPOSE: Signet ring cell carcinoma (SRCC) is a rare type of lung cancer. The conventional survival nomogram used to predict lung cancer performs poorly for SRCC. Therefore, a novel nomogram specifically for studying SRCC is highly required. METHODS: Baseline characteristics of lung signet ring cell carcinoma were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate Cox regression and random forest analysis were performed on the training group data, respectively. Subsequently, we compared results from these two types of analyses. A nomogram model was developed to predict 1-year, 3-year, and 5-year overall survival (OS) for patients, and receiver operating characteristic (ROC) curves and calibration curves were used to assess the prediction accuracy. Decision curve analysis (DCA) was used to assess the clinical applicability of the proposed model. For treatment modalities, Kaplan-Meier curves were adopted to analyze condition-specific effects. RESULTS: We obtained 731 patients diagnosed with lung signet ring cell carcinoma (LSRCC) in the SEER database and randomized the patients into a training group (551) and a validation group (220) with a ratio of 7:3. Eight factors including age, primary site, T, N, and M.Stage, surgery, chemotherapy, and radiation were included in the nomogram analysis. Results suggested that treatment methods (like surgery, chemotherapy, and radiation) and T-Stage factors had significant prognostic effects. The results of ROC curves, calibration curves, and DCA in the training and validation groups demonstrated that the nomogram we constructed could precisely predict survival and prognosis in LSRCC patients. Through deep verification, we found the constructed model had a high C-index, indicating that the model had a strong predictive power. Further, we found that all surgical interventions had good effects on OS and cancer-specific survival (CSS). The survival curves showed a relatively favorable prognosis for T0 patients overall, regardless of the treatment modality. CONCLUSIONS: Our nomogram is demonstrated to be clinically beneficial for the prognosis of LSRCC patients. The surgical intervention was successful regardless of the tumor stage, and the Cox proportional hazard (CPH) model had better performance than the machine learning model in terms of effectiveness.

Asunto(s)

Carcinoma de Células en Anillo de Sello , Neoplasias Pulmonares , Aprendizaje Automático , Nomogramas , Modelos de Riesgos Proporcionales , Programa de VERF , Humanos , Neoplasias Pulmonares/mortalidad , Neoplasias Pulmonares/patología , Neoplasias Pulmonares/terapia , Masculino , Femenino , Carcinoma de Células en Anillo de Sello/patología , Carcinoma de Células en Anillo de Sello/mortalidad , Carcinoma de Células en Anillo de Sello/terapia , Persona de Mediana Edad , Pronóstico , Anciano , Adulto , Curva ROC

RESUMEN

Background: According to the Centers for Disease Control (CDC), breast cancer is the second most common cancer among women in the United States. Affected people are financially challenged due to the high out-of-pocket cost of breast cancer treatment, as it is the most expensive treatment. Using a 16-year cohort study of breast cancer survival data in Texas, we investigate the factors that might explain why some breast cancer patients live longer than others. Methods: Performing a survival analysis consisting of the log-rank test, a survival time regression, and Cox proportional hazards regression, we explore the breast cancer survivors' specific attributes to identify the main determinants of survival time. Results: Analyses show that the factors: stage, grade, primary site of the cancer, number of cancers each patient has, histology of the cancer, age, race, and income are among the main variables that enlighten why some breast cancer survivors live much longer than others. For instance, compared to White non-Hispanics, Black non-Hispanics have a shorter length of survival with a hazard ratio of (1.282). The best prognostic for White non-Hispanics, Hispanics (all races), and Black non-Hispanics is a woman aged between 40 to 49 years old, diagnosed with localized stage and grade one with Axillary tail of breast as a primary site with only one cancer and with a household income of 75,000.00 and over. Conclusion: Policymakers should promote early diagnosis and screening and better assist the older and the poor to improve the survival time for breast cancer patients.

RESUMEN

BACKGROUND: Dogs with retroperitoneal hemangiosarcoma (HSA) exhibit variable postoperative median survival times (MST). OBJECTIVE: To retrospectively evaluate the prognostic value of selected tumour-related factors, such as tumour size, rupture, invasion into adjacent tissue, involvement of lymph node and distant metastasis, they were analysed in dogs with retroperitoneal HSA. METHODS: Ten dogs with retroperitoneal HSA managed solely with surgical excision were reviewed and compared with spleen (71) and liver (9) HSA. The Kaplan-Meier method and log-rank analysis were used compare MSTs between factors. Multivariable Cox proportional-hazard analysis was used to compare differences between arising sites. RESULTS: Retroperitoneal HSA showed comparatively longer postoperative MST compared with that of spleen and liver HSA and demonstrated significantly longer MST (p = 0.003) for tumours ≥5 cm (195 days) than <5 cm (70 days). Spleen HSA revealed significantly shorter MSTs in involvement of distant lymph nodes (23 days) and distant metastasis (39 days) than those in negative (83 days, p = 0.002 and 110 days, p < 0.001, respectively). Liver HSA also revealed significantly shorter MST (16.5 days compared with 98 days, p = 0.003) for distant metastasis. Additionally, hazard ratios (HRs) and their forest plot for overall HSA revealed as poor prognostic factors, arising sites (spleen; HR 2.78, p = 0.016 and liver; HR 3.62, p = 0.019), involvement of distant lymph nodes (HR 2.43, p = 0.014), and distant metastasis (HR 2.86, p < 0.001), and as better prognostic factor of tumour size ≥5 cm (HR 0.53, p = 0.037). CONCLUSION: In combination with overall HSA, retroperitoneal HSA shows comparatively longer postoperative MST compared to spleen and liver HSA, associated with tumour size ≥5 cm suggesting better prognostic factor.

Asunto(s)

Enfermedades de los Perros , Hemangiosarcoma , Neoplasias Retroperitoneales , Animales , Perros , Hemangiosarcoma/veterinaria , Hemangiosarcoma/patología , Hemangiosarcoma/cirugía , Hemangiosarcoma/mortalidad , Estudios Retrospectivos , Enfermedades de los Perros/patología , Enfermedades de los Perros/cirugía , Enfermedades de los Perros/mortalidad , Masculino , Femenino , Neoplasias Retroperitoneales/veterinaria , Neoplasias Retroperitoneales/patología , Neoplasias Retroperitoneales/cirugía , Neoplasias Retroperitoneales/mortalidad , Pronóstico , Neoplasias del Bazo/veterinaria , Neoplasias del Bazo/cirugía , Neoplasias del Bazo/patología , Neoplasias del Bazo/mortalidad , Neoplasias Hepáticas/veterinaria , Neoplasias Hepáticas/mortalidad , Neoplasias Hepáticas/cirugía , Neoplasias Hepáticas/patología

RESUMEN

In this retrospective cohort study, we investigated: (1) The impact of comorbid chronic kidney disease (CKD) on postoperative mortality in patients with a hip fracture; (2) mortality variations by dialysis type, potentially indicating CKD stage; (3) the efficacy of different hip fracture surgical methods in reducing mortality for patients with CKD. This study included 25,760 patients from the Korean National Health Insurance Service-Senior cohort (2002-2019) who underwent hip fracture surgery. Participants were categorized as CKD and Non-CKD. Mortality rate was determined using a generalized linear model with a Poisson distribution. The effect size was presented as a hazard ratio (HR) through a Cox proportional-hazard model. During follow-up, we ascertained that 978 patients (3.8%) had CKD preoperatively. Compared to the Non-CKD group, the mortality risk (HR) in the CKD group was 2.17 times higher (95% confidence interval [CI], 1.99-2.37). In sensitivity analysis, the mortality risk of in patients who received peritoneal dialysis and hemodialysis was 6.21 (95% CI, 3.90-9.87) and 3.62 times (95% CI, 3.11-4.20) higher than that of patients who received conservative care. Mortality risk varied by surgical method: hip hemiarthroplasty (HR, 2.11; 95% CI, 1.86-2.40), open reduction and internal fixation (HR, 2.21; 95% CI, 1.94-2.51), total hip replacement (HR, 2.27; 95% CI, 1.60-3.24), and closed reduction and percutaneous fixation (HR, 3.08; 95% CI, 1.88-5.06). Older patients with CKD undergoing hip fracture surgery had elevated mortality risk, necessitating comprehensive pre- and postoperative assessments and management.

Asunto(s)

Fracturas de Cadera , Insuficiencia Renal Crónica , Humanos , Fracturas de Cadera/cirugía , Fracturas de Cadera/mortalidad , Masculino , Estudios Retrospectivos , Femenino , Anciano , Insuficiencia Renal Crónica/mortalidad , Insuficiencia Renal Crónica/complicaciones , Anciano de 80 o más Años , Factores de Riesgo , Persona de Mediana Edad , República de Corea/epidemiología , Estudios de Cohortes , Diálisis Renal

RESUMEN

Background: Atrial fibrillation (AF) is a prevalent issue among critically ill patients, and the availability of effective treatment strategies for AF is limited. Aim: The objective of this study was to evaluate the mortality rate associated with AF in critically ill patients who were either aspirin or non-aspirin users. Methods: This cohort study incorporated critically ill patients with AF from the Medical Information Mart for Intensive Care database. The study compared incidences of 28-day mortality, 90-day mortality, and 1-year mortality between patients with and without aspirin prescriptions. To assess the association between aspirin and the endpoints, Kaplan-Meier analysis and Cox proportional hazards regression analyses were conducted. Results: In this study, a total of 13,330 critically ill patients with atrial fibrillation (AF) were included, of which 4,421 and 8,909 patients were categorized as aspirin and non-aspirin users, respectively. The 28-day, 90-day, and 1-year mortality rates were found to be 17.5% (2,330/13,330), 23.9% (3,180/13,330), and 32.9% (4,379/13,330), respectively. The results of a fully-adjusted Cox proportional hazard model indicated that aspirin use was negatively associated with the risk of death after adjusting for confounding factors (28-day mortality, HR 0.64, 95% CI 0.55-0.74; 90-day mortality, HR 0.65, 95% CI 0.58-0.74; 1-year mortality, HR 0.67, 95%CI 0.6∼0.74). The results of the subgroup analysis indicate a more robust correlation, specifically among patients under the age of 65 and those without a history of congestive heart failure or myocardial infarction. Conclusions: The utilization of aspirin may exhibit a correlation with a reduction in risk-adjusted mortality from all causes in critically ill patients diagnosed with atrial fibrillation. However, additional randomized controlled trials are necessary to elucidate and confirm this potential association.

RESUMEN

In precision medicine, both predicting the disease susceptibility of an individual and forecasting its disease-free survival are areas of key research. Besides the classical epidemiological predictor variables, data from multiple (omic) platforms are increasingly available. To integrate this wealth of information, we propose new methodology to combine both cooperative learning, a recent approach to leverage the predictive power of several datasets, and polygenic hazard score models. Polygenic hazard score models provide a practitioner with a more differentiated view of the predicted disease-free survival than the one given by merely a point estimate, for instance computed with a polygenic risk score. Our aim is to leverage the advantages of cooperative learning for the computation of polygenic hazard score models via Cox's proportional hazard model, thereby improving the prediction of the disease-free survival. In our experimental study, we apply our methodology to forecast the disease-free survival for Alzheimer's disease (AD) using three layers of data. One layer contains epidemiological variables such as sex, APOE (apolipoprotein E, a genetic risk factor for AD) status and 10 leading principal components. Another layer contains selected genomic loci, and the last layer contains methylation data for selected CpG sites. We demonstrate that the survival curves computed via cooperative learning yield an AUC of around $0.7$, above the state-of-the-art performance of its competitors. Importantly, the proposed methodology returns (1) a linear score that can be easily interpreted (in contrast to machine learning approaches), and (2) a weighting of the predictive power of the involved data layers, allowing for an assessment of the importance of each omic (or other) platform. Similarly to polygenic hazard score models, our methodology also allows one to compute individual survival curves for each patient.

Asunto(s)

Enfermedad de Alzheimer , Medicina de Precisión , Humanos , Medicina de Precisión/métodos , Enfermedad de Alzheimer/genética , Enfermedad de Alzheimer/mortalidad , Supervivencia sin Enfermedad , Aprendizaje Automático , Modelos de Riesgos Proporcionales , Herencia Multifactorial , Masculino , Femenino , Multiómica

RESUMEN

BACKGROUND: Dysregulation of the immune system and N6-methyladenosine (m6A) contribute to immune therapy resistance and cancer progression in urothelial carcinoma (UC). This study aims to identify immune-related molecules, that are m6A-modified, and that are associated with tumor progression, poor prognosis, and immunotherapy response. METHODS: We identified prognostic immune genes (PIGs) using Cox analysis and random survival forest variable hunting algorithm (RSF-VH) on immune genes retrieved from the Immunology Database and Analysis Portal database (ImmPort). The RM2Target database and MeRIP-seq analysis, combined with a hypergeometric test, assessed m6A methylation in these PIGs. We analyzed the correlation between the immune pattern and prognosis, as well as their association with clinical factors in multiple datasets. Moreover, we explored the interplay between immune patterns, tumor immune cell infiltration, and m6A regulators. RESULTS: 28 PIGs were identified, of which the 10 most significant were termed methylated prognostic immune genes (MPIGs). These MPIGs were used to create an immune pattern score. Kaplan-Meier and Cox analyses indicated this pattern as an independent risk factor for UC. We observed significant associations between the immune pattern, tumor progression, and immune cell infiltration. Differential expression analysis showed correlations with m6A regulators expression. This immune pattern proved effective in predicting immunotherapy response in UC in real-world settings. CONCLUSION: The study identified a m6A-modified immune pattern in UC, offering prognostic and therapeutic response predictions. This emphasizes that immune genes may influence tumor immune status and progression through m6A modifications.

Asunto(s)

Adenosina , Inmunoterapia , Humanos , Adenosina/análogos & derivados , Pronóstico , Neoplasias de la Vejiga Urinaria/inmunología , Neoplasias de la Vejiga Urinaria/genética , Neoplasias de la Vejiga Urinaria/tratamiento farmacológico , Neoplasias de la Vejiga Urinaria/mortalidad , Neoplasias de la Vejiga Urinaria/patología , Neoplasias de la Vejiga Urinaria/terapia , Regulación Neoplásica de la Expresión Génica , Biomarcadores de Tumor/genética , Carcinoma de Células Transicionales/inmunología , Carcinoma de Células Transicionales/genética , Carcinoma de Células Transicionales/tratamiento farmacológico , Carcinoma de Células Transicionales/mortalidad , Carcinoma de Células Transicionales/patología , Carcinoma de Células Transicionales/terapia

RESUMEN

BACKGROUND AND AIM: In this study, a deep learning algorithm was used to predict the survival rate of colon cancer (CC) patients, and compared its performance with traditional Cox regression. METHODS: In this population-based cohort study, we used the characteristics of patients diagnosed with CC between 2010 and 2015 from the Surveillance, Epidemiology and End Results (SEER) database. The population was randomized into a training set (n = 10 596, 70%) and a test set (n = 4536, 30%). Brier scores, area under the (AUC) receiver operating characteristic curve and calibration curves were used to compare the performance of the three most popular deep learning models, namely, artificial neural networks (ANN), deep neural networks (DNN), and long-short term memory (LSTM) neural networks with Cox proportional hazard (CPH) model. RESULTS: In the independent test set, the Brier values of ANN, DNN, LSTM and CPH were 0.155, 0.149, 0.148, and 0.170, respectively. The AUC values were 0.906 (95% confidence interval [CI] 0.897-0.916), 0.908 (95% CI 0.899-0.918), 0.910 (95% CI 0.901-0.919), and 0.793 (95% CI 0.769-0.816), respectively. Deep learning showed superior promising results than CPH in predicting CC specific survival. CONCLUSIONS: Deep learning showed potential advantages over traditional CPH models in terms of prognostic assessment and treatment recommendations. LSTM exhibited optimal predictive accuracy and has the ability to provide reliable information on individual survival and treatment recommendations for CC patients.

RESUMEN

BACKGROUND: Metastatic triple-negative breast cancer (TNBC) is aggressive with poor median overall survival (OS) ranging from 8 to 13 months. There exists considerable heterogeneity in survival at the individual patient level. To better understand the survival heterogeneity and improve risk stratification, our study aims to identify the factors influencing survival, utilizing a large patient sample from the National Cancer Database (NCDB). METHODS: Women diagnosed with metastatic TNBC from 2010 to 2020 in the NCDB were included. Demographic, clinicopathological, and treatment data and overall survival (OS) outcomes were collected. Kaplan-Meier curves were used to estimate OS. The log-rank test was used to identify OS differences between groups for each variable in the univariate analysis. For the multivariate analysis, the Cox proportional hazard model with backward elimination was used to identify factors affecting OS. Adjusted hazard ratios and 95% confidence intervals are presented. RESULTS: In this sample, 2273 women had a median overall survival of 13.6 months. Factors associated with statistically significantly worse OS included older age, higher comorbidity scores, specific histologies, higher number of metastatic sites, presence of liver or other site metastases in those with only one metastatic site (excluding brain metastases), presence of cranial and extra-cranial metastases, lack of chemotherapy, lack of immunotherapy, lack of surgery to distant sites, lack of radiation to distant sites, and receipt of palliative treatment to alleviate symptoms. In the multivariate analysis, comorbidity score, histology, number of metastatic sites, immunotherapy, and chemotherapy had a statistically significant effect on OS. CONCLUSIONS: Through NCDB analysis, we have identified prognostic factors for metastatic TNBC. These findings will help individualize prognostication at diagnosis, optimize treatment strategies, and facilitate patient stratification in future clinical trials.

RESUMEN

Background: Cardiovascular diseases (CVD) represent a leading cause of global mortality, necessitating proactive identification of risk factors for preventive strategies. This study aimed to uncover prognostic factors influencing cardiovascular patient survival. Methods: This study, which used a sample size of 410, showed how to analyze data using simple random sampling. It was conducted at the Tikur Anbessa Specialist Hospital in Addis Ababa, Ethiopia, between September 2012 and April 2016. The Cox PH and stratified Cox regression models were used for the analysis. Results: Findings disclosed a patient cohort where 200 patients (48.8%) persisted through subsequent evaluation, while 210 patients (51.2%) succumbed. Blood pressure (BP), specific CVD, and education levels (EL) exhibited nonproportionalities in scaled Schoenfeld residuals (P < 0.001), prompting necessary stratification. Inadequacies in the Cox proportional hazards model led to favoring the stratified Cox model. Notably, EL, BP, cholesterol level (CL), alcohol use (AU), smoking use (SU), and pulse rate (PR) exhibited statistical significance (P < 0.001). Acceptability of the absence of interaction in the model, with disease types as strata, was established. Different cardiovascular conditions served as distinct groups, where EL, AU, BP, PR, CL, and SU emerged as variables with statistically substantiated significance associated with the mortality of patients with CVD. Conclusion: Implications stress the imperative of widespread awareness among policymakers and the public concerning cardiovascular disease incidence. Such awareness is pivotal in mitigating identified risk factors, guiding more effective healthcare interventions tailored to the multifaceted challenges posed by cardiovascular health.

RESUMEN

Introduction: Intrauterine adhesions (IUAs) caused by endometrial injury, commonly occurring in developing countries, can lead to subfertility. This study aimed to develop and evaluate a DeepSurv architecture-based artificial intelligence (AI) system for predicting fertility outcomes after hysteroscopic adhesiolysis. Methods: This diagnostic study included 555 intrauterine adhesions (IUAs) treated with hysteroscopic adhesiolysis with 4,922 second-look hysteroscopic images from a prospective clinical database (IUADB, NCT05381376) with a minimum of 2 years of follow-up. These patients were randomly divided into training, validation, and test groups for model development, tuning, and external validation. Four transfer learning models were built using the DeepSurv architecture and a code-free AI application for pregnancy prediction was also developed. The primary outcome was the model's ability to predict pregnancy within a year after adhesiolysis. Secondary outcomes were model performance which evaluated using time-dependent area under the curves (AUCs) and C-index, and ART benefits evaluated by hazard ratio (HR) among different risk groups. Results: External validation revealed that using the DeepSurv architecture, InceptionV3+ DeepSurv, InceptionResNetV2+ DeepSurv, and ResNet50+ DeepSurv achieved AUCs of 0.94, 0.95, and 0.93, respectively, for one-year pregnancy prediction, outperforming other models and clinical score systems. A code-free AI application was developed to identify candidates for ART. Patients with lower natural conception probability indicated by the application had a higher ART benefit hazard ratio (HR) of 3.13 (95% CI: 1.22-8.02, p = 0.017). Conclusion: InceptionV3+ DeepSurv, InceptionResNetV2+ DeepSurv, and ResNet50+ DeepSurv show potential in predicting the fertility outcomes of IUAs after hysteroscopic adhesiolysis. The code-free AI application based on the DeepSurv architecture facilitates personalized therapy following hysteroscopic adhesiolysis.

RESUMEN

BACKGROUND & AIM: Cardiovascular disease (CVD) is the most important cause of death in the world and has a potential impact on health care costs, this study aimed to evaluate the performance of machine learning survival models and determine the optimum model for predicting CVD-related mortality. METHOD: In this study, the research population was all participants in Tehran Lipid and Glucose Study (TLGS) aged over 30 years. We used the Gradient Boosting model (GBM), Support Vector Machine (SVM), Super Learner (SL), and Cox proportional hazard (Cox-PH) models to predict the CVD-related mortality using 26 features. The dataset was randomly divided into training (80%) and testing (20%). To evaluate the performance of the methods, we used the Brier Score (BS), Prediction Error (PE), Concordance Index (C-index), and time-dependent Area Under the Curve (TD-AUC) criteria. Four different clinical models were also performed to improve the performance of the methods. RESULTS: Out of 9258 participants with a mean age of (SD; range) 43.74 (15.51; 20-91), 56.60% were female. The CVD death proportion was 2.5% (228 participants). The death proportion was significantly higher in men (67.98% M, 32.02% F). Based on predefined selection criteria, the SL method has the best performance in predicting CVD-related mortality (TD-AUC > 93.50%). Among the machine learning (ML) methods, The SVM has the worst performance (TD-AUC = 90.13%). According to the relative effect, age, fasting blood sugar, systolic blood pressure, smoking, taking aspirin, diastolic blood pressure, Type 2 diabetes mellitus, hip circumference, body mss index (BMI), and triglyceride were identified as the most influential variables in predicting CVD-related mortality. CONCLUSION: According to the results of our study, compared to the Cox-PH model, Machine Learning models showed promising and sometimes better performance in predicting CVD-related mortality. This finding is based on the analysis of a large and diverse urban population from Tehran, Iran.

Asunto(s)

Enfermedades Cardiovasculares , Diabetes Mellitus Tipo 2 , Masculino , Humanos , Femenino , Adulto , Enfermedades Cardiovasculares/epidemiología , Glucosa , Irán/epidemiología , Lípidos

RESUMEN

BACKGROUND: This study aimed to determine whether the waist-to-thigh ratio (WTTR) is associated with the incidence of metabolic-associated fatty liver disease (MAFLD) in health care workers. METHODS: There were 4517 health care workers with baseline data and results from 2 follow-up examinations. We divided the subjects into 3 groups according to baseline WTTR and used the Cox hazard regression model to estimate MAFLD risk. RESULTS: The WTTRs were categorized by tertiles at baseline using the values 1.58 and 1.66. Patients with higher WTTR tended to have significantly greater values for the following factors, body mass index (BMI), fasting blood glucose (FPG), systolic blood pressure, diastolic blood pressure, total cholesterol (TC), triglycerides (TG), low-density lipoprotein-cholesterol (LDL-C) and neck circumference. The incidence of MAFLD significantly increased with increasing WTTR tertiles (5.74%, 12.75% and 22.25% for the first, second and third tertiles, respectively, P < 0.05 for trend). Kaplan-Meier(K-M) survival analysis revealed a significant tendency towards increased MAFLD risk with increasing WTTR tertile. In the fully adjusted model, the hazard ratios (95% CIs) for MAFLD in the second, third WTTR tertiles compared with the first quartile were 2.17(1.58,2.98), 3.63(2.70,4.89), respectively, third neck circumference tertiles compared with the first quartile were 2.84(1.89,4.25), 8.95(6.00,13.35), respectively. Compared with those of individuals with a BMI > 23 kg/m2, the associations between WTTR and MAFLD incidence were more pronounced in subjects with a BMI < 23 kg/m2. Similarly, the difference in neck circumference was more pronounced in these patients with a BMI < 23 kg/m2. CONCLUSIONS: Our results revealed that the WTTR is an independent risk factor for MAFLD, and there was a dose‒response relationship between the WTTR and MAFLD risk. The neck circumference was significantly different in subjects with a BMI < 23 kg/m2. This approach provides a new way to predict the incidence rate of MAFLD.

Asunto(s)

Muslo , Circunferencia de la Cintura , Humanos , Masculino , Femenino , Persona de Mediana Edad , Estudios de Seguimiento , Incidencia , Adulto , Factores de Riesgo , Índice de Masa Corporal , Modelos de Riesgos Proporcionales , Personal de Salud , Enfermedad del Hígado Graso no Alcohólico/sangre , Enfermedad del Hígado Graso no Alcohólico/epidemiología , Glucemia/análisis , Glucemia/metabolismo

RESUMEN

In this study, we jointly modeled longitudinal CD4 count data and survival outcome (time-to-first occurrence of composite outcome of death, cardiac tamponade or constriction) in other to investigate the effects of Mycobacterium indicus pranii immunotherapy and the CD4 count measurements on the hazard of the composite outcome among patients with HIV and tuberculous (TB) pericarditis. In this joint modeling framework, the models for longitudinal and the survival data are linked by an association structure. The association structure represents the hazard of the event for 1-unit increase in the longitudinal measurement. Models fitting and parameter estimation were carried out using R version 4.2.3. The association structure that represents the strength of the association between the hazard for an event at time point j and the area under the longitudinal trajectory up to the same time j provides the best fit. We found that 1-unit increase in CD4 count results in 2 % significant reduction in the hazard of the composite outcome. Among HIV and TB pericarditis individuals, the hazard of the composite outcome does not differ between of M.indicus pranii versus placebo. Application of joint models to investigate the effect of M.indicus pranii on the hazard of the composite outcome is limited. Hence, this study provides information on the effect of M.indicus pranii on the hazard of the composite outcome among HIV and TB pericarditis patients.