RESUMEN
BACKGROUND: Prediction of mortality is very important for care planning in hospitalized patients with dementia and artificial intelligence has the potential to serve as a solution; however, this issue remains unclear. Thus, this study was conducted to elucidate this matter. METHODS: We identified 10,573 hospitalized patients aged ≥ 45 years with dementia from three hospitals between 2010 and 2020 for this study. Utilizing 44 feature variables extracted from electronic medical records, an artificial intelligence (AI) model was constructed to predict death during hospitalization. The data was randomly separated into 70 % training set and 30 % testing set. We compared predictive accuracy among six algorithms including logistic regression, random forest, extreme gradient boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), multilayer perceptron (MLP), and support vector machine (SVM). Additionally, another set of data collected in 2021 was used as the validation set to assess the performance of six algorithms. RESULTS: The average age was 79.8 years, with females constituting 54.5 % of the sample. The in-hospital mortality rate was 6.7 %. LightGBM exhibited the highest area under the curve (0.991) for predicting mortality compared to other algorithms (XGBoost: 0.987, random forest: 0.985, logistic regression: 0.918, MLP: 0.898, SVM: 0.897). The accuracy, sensitivity, positive predictive value, and negative predictive value of LightGBM were 0.943, 0.944, 0.943, 0.542, and 0.996, respectively. Among the features in LightGBM, the three most important variables were the Glasgow Coma Scale, respiratory rate, and blood urea nitrogen. In the validation set, the area under the curve of LightGBM reached 0.753. CONCLUSIONS: The AI prediction model demonstrates strong accuracy in predicting in-hospital mortality among patients with dementia, suggesting its potential implementation to enhance future care quality.
RESUMEN
BACKGROUND: Intradialytic hypotension (IDH) is one of the most common and critical complications of hemodialysis. Despite many proven factors associated with IDH, accurately predicting it before it occurs for individual patients during dialysis sessions remains a challenge. PURPOSE: To establish artificial intelligence (AI) predictive models for IDH, which consider risk factors from previous and ongoing dialysis to optimize model performance. We then implement a novel digital dashboard with the best model for continuous monitoring of patients' status undergoing hemodialysis. The AI dashboard can display the real-time probability of IDH for each patient in the hemodialysis center providing an objective reference for care members for monitoring IDH and treating it in advance. METHODS: Eight machine learning (ML) algorithms, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), K Nearest Neighbor (KNN), Light Gradient Boosting Machine (LightGBM), Multilayer Perception (MLP), eXtreme Gradient Boosting (XGBoost), and NaiveBayes, were used to establish the predictive model of IDH to determine if the patient will acquire IDH within 60 min. In addition to real-time features, we incorporated several features sourced from previous dialysis sessions to improve the model's performance. The electronic medical records of patients who had undergone hemodialysis at Chi Mei Medical Center between September 1, 2020 and December 31, 2020 were included in this research. Impact evaluation of AI assistance was conducted by IDH rate. RESULTS: The results showed that the XGBoost model had the best performance (accuracy: 0.858, sensitivity: 0.858, specificity: 0.858, area under the curve: 0.936) and was chosen for AI dashboard implementation. The care members were delighted with the dashboard providing real-time scientific probabilities for IDH risk and historic predictive records in a graphic style. Other valuable functions were appended in the dashboard as well. Impact evaluation indicated a significant decrease in IDH rate after the application of AI assistance. CONCLUSION: This AI dashboard provides high-quality results in IDH risk prediction during hemodialysis. High-risk patients for IDH will be recognized 60 min earlier, promoting individualized preventive interventions as part of the treatment plan. Our approachis believed to promise an excellent way for IDH management.
RESUMEN
BACKGROUND: Exposure to light at night (LAN) has been associated with multiple adverse health outcomes. However, evidence is limited regarding the impacts of LAN exposure on human inflammation. OBJECTIVES: To examine the association between real-ambient bedroom LAN exposure with systemic inflammation and circadian rhythm of inflammatory markers. METHODS: Using data from a prospective cohort study of Chinese young adults. At baseline, bedroom LAN exposure was measured with a portable illuminance meter; fasting blood sample for high-sensitivity C-reactive protein (hs-CRP) assay was collected. At 3-year follow-up, 20 healthy young adults (10 LANavg < 5â¯lx, 10 LANavg ≥ 5â¯lx) were recruited from the same cohort; time-series venous blood samples were sampled every 4â¯h over a 24â¯h-cycle for the detection of 8 inflammatory markers. Circadian rhythm of inflammatory markers was assessed using cosinor analysis. RESULTS: At baseline, the average age of the 276 participants was 18.7 years, and 33.3â¯% were male. Higher levels of bedroom LAN exposure were significantly associated with increased hs-CRP levels. The association between bedroom LAN exposure and systemic inflammation was only significant in the inactive group (MVPA < 2â¯h/d) but not in the physically active group (MVPA ≥ 2â¯h/d). In addition, exposure to higher levels of nighttime light (LANavg ≥ 5â¯lx) disrupted circadian rhythms (including rhythmic expression, circadian amplitude and circadian phase) of some inflammatory cytokines and inflammatory balance indicators. CONCLUSION: Exposure to bedroom nighttime light increases systemic inflammation and disrupts circadian rhythm of inflammatory markers. Keep bedroom darkness at night may represent important strategies for the prevention of chronic inflammation. Additionally, for people living a community with higher nighttime light pollution, regular physical activity may be a viable option to counteract the negative impacts of LAN exposure on chronic inflammation.
Asunto(s)
Biomarcadores , Proteína C-Reactiva , Ritmo Circadiano , Inflamación , Luz , Humanos , Masculino , Inflamación/sangre , Femenino , Biomarcadores/sangre , Adulto Joven , Estudios Prospectivos , Adolescente , Luz/efectos adversos , Proteína C-Reactiva/análisis , Iluminación/efectos adversos , China , AdultoRESUMEN
In this research, we aimed to harness machine learning to predict the imminent risk of acute exacerbation in chronic obstructive pulmonary disease (AECOPD) patients. Utilizing retrospective data from electronic medical records of two Taiwanese hospitals, we identified 26 critical features. To predict 3- and 6-month AECOPD occurrences, we deployed five distinct machine learning algorithms alongside ensemble learning. The 3-month risk prediction was best realized by the XGBoost model, achieving an AUC of 0.795, whereas the XGBoost was superior for the 6-month prediction with an AUC of 0.813. We conducted an explainability analysis and found that the episode of AECOPD, mMRC score, CAT score, respiratory rate, and the use of inhaled corticosteroids were the most impactful features. Notably, our approach surpassed predictions that relied solely on CAT or mMRC scores. Accordingly, we designed an interactive prediction system that provides physicians with a practical tool to predict near-term AECOPD risk in outpatients.
RESUMEN
BACKGROUND: Light at night (LAN) have attracted increased research attention on account of its widespread health hazards. However, the underlying mechanism remains unknown. The objective of this study was to investigate the effects of real-ambient bedroom LAN exposure on circadian rhythm among young adults and potential sex differences. METHODS: Bedroom LAN exposure was measured at 60-s intervals for 2 consecutive days using a portable illuminance meter. Circadian phase was determined by the dim light melatonin onset (DLMO) time in 7 time-series saliva samples. RESULTS: The mean age of the 142 participants was 20.7 ± 0.8 years, and 59.9% were women. The average DLMO time was 21:00 ± 1:11 h, with men (21:19 ± 1:12 h) later than women (20:48 ± 1:07 h). Higher level of LAN intensity (LANavg ≥ 3lx vs. LANavg < 3lx) was associated with an 81.0-min later in DLMO time (95% CI: 0.99, 1.72), and longer duration of nighttime light intensity ≥ 5lx (LAN5; LAN5 ≥ 45 min vs. LAN5 < 45 min) was associated with a 51.6-min later in DLMO time (95% CI: 0.46, 1.26). In addition, the delayed effect of LAN exposure on circadian phase was more pronounced in men than in women (all P-values <0.05). CONCLUSIONS: Overall, bedroom LAN exposure was significantly associated with delayed circadian rhythm. Additionally, the delayed effect is more significant in men. Keeping bedroom dark at night may be a practicable option to prevent circadian disruption and associated health implications. Future studies with more advanced light measurement instrument and consensus methodology for DLMO assessment are warranted.
Asunto(s)
Ritmo Circadiano , Luz , Melatonina , Humanos , Masculino , Femenino , Adulto Joven , Estudios Transversales , China , Iluminación , Saliva/química , Saliva/efectos de la radiación , Adulto , Pueblos del Este de AsiaRESUMEN
At present, there is a lack of sufficiently specific laboratory diagnostic indicators for schizophrenia. Serum homocysteine (Hcy) levels have been found to be related to schizophrenia. Cysteine (Cys) is a demethylation product in the metabolism of Hcy, and they always coexist with highly similar structures in vivo. There are few reports on the use of Cys as a diagnostic biomarker for schizophrenia in collaboration with Hcy, mainly because the rapid, economical, accurate, and high-throughput simultaneous detection of Cys and Hcy in serum is highly challenging. Herein, a click reaction-based surface-enhanced Raman spectroscopy (SERS) sensor was developed for simultaneous and selective detection of Cys and Hcy. Through the efficient and specific CBT-Cys click reaction between the probe containing cyan benzothiazole and Cys/Hcy, the tiny methylene difference between the molecular structures of Cys and Hcy was converted into the difference between the ring skeletons of the corresponding products that could be identified by plasmonic silver nanoparticle enhanced molecular fingerprint spectroscopy to realize discriminative detection. Furthermore, the SERS sensor was successfully applied to the detection in related patient serum samples, and it was found that the combined analysis of Cys and Hcy can improve the diagnostic accuracy of schizophrenia compared to a single indicator.
Asunto(s)
Nanopartículas del Metal , Esquizofrenia , Humanos , Cisteína/química , Células HeLa , Esquizofrenia/diagnóstico , Colorantes Fluorescentes/química , Plata , Espectrometría de Fluorescencia/métodos , Homocisteína , Glutatión/análisisRESUMEN
PURPOSE: To develop a multi-parameter intrahepatic cholangiocarcinoma (ICC) scoring system and compare its diagnostic performance with contrast-enhanced ultrasound (CEUS) liver imaging reporting and data system M (LR-M) criteria for differentiating ICC from hepatocellular carcinoma (HCC). METHODS: This retrospective study enrolled 62 high-risk patients with ICCs and 62 high-risk patients with matched HCCs between January 2022 and December 2022 from two institutions. The CEUS LR-M criteria was modified by adjusting the early wash-out onset (within 45 s) and the marked wash-out (within 3 min). Then, a multi-parameter ICC scoring system was established based on clinical features, B-mode ultrasound features, and modified LR-M criteria. RESULT: We found that elevated CA 19-9 (OR=12.647), lesion boundary (OR=11.601), peripheral rim-like arterial phase hyperenhancement (OR=23.654), early wash-out onset (OR=7.211), and marked wash-out (OR=19.605) were positive predictors of ICC, whereas elevated alpha-fetoprotein (OR=0.078) was a negative predictor. Based on these findings, an ICC scoring system was established. Compared with the modified LR-M and LR-M criteria, the ICC scoring system showed the highest area under the curve (0.911 vs. 0.831 and 0.750, both p<0.05) and specificity (0.935 vs. 0.774 and 0.565, both p<0.05). Moreover, the numbers of HCCs categorized as LR-M decreased from 27 (43.5%) to 14 (22.6%) and 4 (6.5%) using the modified LR-M criteria and ICC scoring system, respectively. CONCLUSION: The modified LR-M criteria-based multi-parameter ICC scoring system had the highest specificity for diagnosing ICC and reduced the number of HCC cases diagnosed as LR-M category.
Asunto(s)
Neoplasias de los Conductos Biliares , Carcinoma Hepatocelular , Colangiocarcinoma , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/diagnóstico por imagen , Carcinoma Hepatocelular/patología , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/patología , Estudios Retrospectivos , Medios de Contraste , Diagnóstico Diferencial , Colangiocarcinoma/diagnóstico por imagen , Colangiocarcinoma/patología , Conductos Biliares Intrahepáticos/patología , Neoplasias de los Conductos Biliares/diagnóstico por imagen , Neoplasias de los Conductos Biliares/patología , Imagen por Resonancia Magnética/métodos , Sensibilidad y EspecificidadRESUMEN
OBJECTIVE: Artificial intelligence (AI) prediction is increasingly used for decision making in health care, but its application for adverse outcomes in emergency department (ED) patients with acute pancreatitis (AP) is not well understood. This study aimed to clarify this aspect. METHODS: Data from 8274 ED patients with AP in three hospitals from 2009 to 2018 were analyzed. Demographic data, comorbidities, laboratory results, and adverse outcomes were included. Six algorithms were evaluated, and the one with the highest area under the curve (AUC) was implemented into the hospital information system (HIS) for real-time prediction. Predictive accuracy was compared between the AI model and Bedside Index for Severity in Acute Pancreatitis (BISAP). RESULTS: The mean ± SD age was 56.1 ± 16.7 years, with 67.7% being male. The AI model was successfully implemented in the HIS, with Light Gradient Boosting Machine (LightGBM) showing the highest AUC for sepsis (AUC 0.961) and intensive care unit (ICU) admission (AUC 0.973), and eXtreme Gradient Boosting (XGBoost) showing the highest AUC for mortality (AUC 0.975). Compared to BISAP, the AI model had superior AUC for sepsis (BISAP 0.785), ICU admission (BISAP 0.778), and mortality (BISAP 0.817). CONCLUSIONS: The first real-time AI prediction model implemented in the HIS for predicting adverse outcomes in ED patients with AP shows favorable initial results. However, further external validation is needed to ensure its reliability and accuracy.
Asunto(s)
Pancreatitis , Sepsis , Humanos , Masculino , Adulto , Persona de Mediana Edad , Anciano , Femenino , Pancreatitis/complicaciones , Pancreatitis/diagnóstico , Pancreatitis/terapia , Índice de Severidad de la Enfermedad , Inteligencia Artificial , Enfermedad Aguda , Reglas de Decisión Clínica , Reproducibilidad de los Resultados , Pronóstico , Estudios Retrospectivos , Valor Predictivo de las PruebasRESUMEN
PURPOSE: This study aimed to develop preprocedural real-time artificial intelligence (AI)-based systems for predicting individualized risks of contrast-associated acute kidney injury (CA-AKI) and dialysis requirement within 30 days following contrast-enhanced computed tomography (CECT). METHOD: This single-center, retrospective study analyzed adult patients from emergency or in-patient departments who underwent CECT; 18,895 patients were included after excluding those who were already on dialysis, had stage V chronic kidney disease, or had missing data regarding serum creatinine levels within 7 days before and after CECT. Clinical parameters, laboratory data, medication exposure, and comorbid diseases were selected as predictive features. The patients were randomly divided into model training and testing groups at a 7:3 ratio. Logistic regression (LR) and random forest (RF) were employed to create prediction models, which were evaluated using receiver operating characteristic curves. RESULTS: The incidence rates of CA-AKI and dialysis within 30 days post-CECT were 6.69% and 0.98%, respectively. For CA-AKI prediction, LR and RF exhibited similar performance, with areas under curve (AUCs) of 0.769 and 0.757, respectively. For 30-day dialysis prediction, LR (AUC, 0.863) and RF (AUC, 0.872) also exhibited similar performance. Relative to eGFR-alone, the LR and RF models produced significantly higher AUCs for CA-AKI prediction (LR vs. eGFR alone, 0.769 vs. 0.626, p < 0.001) and 30-day dialysis prediction (RF vs. eGFR alone, 0.872 vs. 0.738, p < 0.001). CONCLUSIONS: The proposed AI prediction models significantly outperformed eGFR-alone for predicting the CA-AKI and 30-day dialysis risks of emergency department and hospitalized patients who underwent CECT.
Asunto(s)
Lesión Renal Aguda , Diálisis Renal , Humanos , Medición de Riesgo , Estudios Retrospectivos , Inteligencia Artificial , Lesión Renal Aguda/inducido químicamente , Lesión Renal Aguda/epidemiología , Tomografía Computarizada por Rayos X/métodosRESUMEN
Combined hepatocellular-cholangiocarcinoma (cHCC-CC) is a rare type of primary liver cancer. It is a complex "biphenotypic" tumor type consisting of bipotential hepatic progenitor cells that can differentiate into cholangiocytes subtype and hepatocytes subtype. The prognosis of patients with cHCC-CC is quite poor with its specific and more aggressive nature. Furthermore, there are no definite demographic or clinical features of cHCC-CC, thus a clear preoperative identification and accurate non-invasive imaging diagnostic analysis of cHCC-CC are of great value. In this review, we first summarized the epidemiological features, pathological findings, molecular biological information and serological indicators of cHCC-CC disease. Then we reviewed the important applications of non-invasive imaging modalities-particularly ultrasound (US)-in cHCC-CC, covering both diagnostic and prognostic assessment of patients with cHCC-CC. Finally, we presented the shortcomings and potential outlooks for imaging studies in cHCC-CC.
Asunto(s)
Neoplasias de los Conductos Biliares , Carcinoma Hepatocelular , Colangiocarcinoma , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/diagnóstico por imagen , Carcinoma Hepatocelular/patología , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/patología , Neoplasias de los Conductos Biliares/patología , Colangiocarcinoma/diagnóstico por imagen , Colangiocarcinoma/patología , Conductos Biliares Intrahepáticos/patología , Estudios RetrospectivosRESUMEN
PURPOSE: To investigate the association between different treatments of tubal ectopic pregnancy (EP) -expectant management, methotrexate (MTX), selected or recommended laparoscopic surgery-and the subsequent reproductive outcomes. METHODS: We conducted a retrospective cohort study including 228 EPs. The patients were divided into four treatment groups: 28 (12.3%) with expectant management successfully, 60 (26.3%) with MTX successfully, 140 patients with laparoscopic salpingectomy, of which 47 (20.6%) were assigned to selected surgery group because they opted for surgical treatment versus MTX, 93 (40.8%) were assigned to recommended surgery group as recommended by the attending physician. RESULTS: The recommended surgery group had the lowest rate of intrauterine pregnancy (IUP) (77.42%) and live birth (LB) (72.04%), while the incidence of recurrent EP (REP) (20.43%) was the highest, but the statistical differences were not significant. We did not observe significant differences of the EP-IUP time interval, rates of LB and miscarriage (MIS) between the four groups. Compared to the MTX group, recommended surgery was negatively associated with IUP (adjusted OR, 95%CI: 0.34, 0.11-1.03) and LB (0.35, 0.14-0.92), while it had higher risk for REP (3.48, 1.03-11.74) in the subsequent pregnancy. Further, compared to selective surgery group, recommended surgery was negatively associated with IUP (0.15, 0.03-0.68) and LB (0.23, 0.07-0.74), while it had higher risk for REP (6.83, 1.43-32.67) in the subsequent pregnancy. Expectant treatment was negatively associated with assisted reproductive technology (ART) (0.08, 0.02-0.40) compared with MTX. Of the185 patients who had LBs, all adverse outcomes were not statistically different between the four groups. CONCLUSION: Patients with recommended laparoscopic salpingectomy had worse reproductive outcomes than the other treatment groups. The disease status of EP may play an important role in the association rather than the surgery alone.
Asunto(s)
Embarazo Tubario , Embarazo , Femenino , Humanos , Estudios Retrospectivos , Embarazo Tubario/epidemiología , Embarazo Tubario/cirugía , Salpingectomía , Metotrexato/uso terapéutico , Técnicas Reproductivas AsistidasRESUMEN
Background: The purpose of this study is to investigate the clinical and radiological results of a sliding oblique metatarsal osteotomy (SOMO) to correct bunionette deformity. Methods: We retrospectively reviewed 44 patients (51 feet, left/right: 29/22) from December 2010 to December 2018 who underwent SOMO and compared radiographic measurements and clinical outcome scores preoperatively and postoperatively. Radiographic measurements included 4th and 5th intermetatarsal angle (IMA), metatarsophalangeal angle (MTPA), and lateral deviation angle (LDA). Clinical outcome measurements included The American Orthopedic Foot and Ankle Society (AOFAS) score for lesser metatarsophalangeal procedures and visual analog scale (VAS) pain score. The mean follow-up period was 26.6 months (minimum 18 months). Based on Coughlin and Fallat classification, all cases were separated into four subtypes: 6 type I, 10 type II, 12 type III, 23 type IV cases included.) Results: All radiographic parameters significantly improved after SOMO procedure (IMA/MTPA/LDA, p value < 0.001). Clinical scores also showed a significant improvement in AOFAS and VAS scores (p value < 0.001). In terms of subgroup based on each type, both radiographic measurements and clinical scores revealed significant improvements in each subgroup (p value < 0.05), except LDA of type I subgroup (p value = 0.09). Three cases reported pin-tract infection but recovered with good healing after removal of the K-wire and a prescription of oral antibiotic. Conclusion: The SOMO procedure may be considered as a reliable and simple treatment for most types of bunionette deformity with satisfactory outcomes and no severe complications. Level of Evidence: Level IV, case series.
RESUMEN
OBJECTIVE: Iatrogenic vocal fold paralysis is an important issue in laryngology, yet there are few population-based studies regarding the epidemiology. This study used a nationwide population-based claims database (the National Health Insurance Research Database) to investigate the epidemiology of iatrogenic unilateral and bilateral vocal fold paralysis (UVFP/BVFP) among the general adult population in Taiwan. METHOD: This study analyzed patients (20-90 years old) who underwent thyroid, parathyroid, thoracic, cardiac, or anterior cervical spine operations with vocal fold paralysis among adults in Taiwan from January 1, 2007 to December 31, 2013. The codes for vocal fold paralysis were defined by International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM). Claims data in the Taiwan National Health Insurance Research Database were used. RESULTS: The most commonly performed operations which were related to vocal fold paralysis in Taiwan were, in descending order of frequency, thyroid, cervical spine, cardiac, thoracic (esophagectomy), and parathyroid operations. The operations that put laryngeal nerves at risk (ONRs) most commonly associated with a diagnosis of UVFP were, in descending order of frequency, thoracic, thyroid, parathyroid, cardiac, and cervical spine. For both UVFP and BVFP, the most commonly associated age group was 51 to 60. For both UVFP and BVFP, the more commonly associated sex was women. Increased length of stay was associated with a higher incidence of UVFP and BVFP. Charlson medical co-morbidity index (CCI) was not associated with UVFP but BVFP was associated with higher Charlson medical co-morbidity scores. CONCLUSIONS: Thyroid operations, age 51 to 60, longer hospital stays are associated with vocal fold paralysis. Overall women are more surgically affected than men. This is the first population-based study of iatrogenic vocal fold paralysis.
Asunto(s)
Parálisis de los Pliegues Vocales , Pliegues Vocales , Adulto , Anciano , Anciano de 80 o más Años , Estudios de Cohortes , Femenino , Humanos , Enfermedad Iatrogénica/epidemiología , Masculino , Persona de Mediana Edad , Estudios Retrospectivos , Taiwán/epidemiología , Parálisis de los Pliegues Vocales/epidemiología , Parálisis de los Pliegues Vocales/etiología , Parálisis de los Pliegues Vocales/cirugía , Adulto JovenRESUMEN
Chronic obstructive pulmonary disease (COPD) is one of the leading causes of mortality and contributes to high morbidity worldwide. Patients with COPD have a higher risk for acute respiratory failure, ventilator dependence, and mortality after hospitalization compared with the general population. Accurate and early risk detection will provide more information for early management and better decision making. This study aimed to build prediction models using patients' characteristics, laboratory data, and comorbidities for early detection of acute respiratory failure, ventilator dependence, and mortality in patients with COPD after hospitalization. We retrospectively collected the electronic medical records of 5061 patients with COPD in three hospitals of the Chi Mei Medical Group, Taiwan. After data cleaning, we built three prediction models for acute respiratory failure, ventilator dependence, and mortality using seven machine learning algorithms. Based on the AUC value, the best model for mortality was built by the XGBoost algorithm (AUC = 0.817), the best model for acute respiratory failure was built by random forest algorithm (AUC = 0.804), while the best model for ventilator dependence was built by LightGBM algorithm (AUC = 0.809). A web service application was implemented with the best models and integrated into the existing hospital information system for physician's trials and evaluations. Our machine learning models exhibit excellent predictive quality and can therefore provide physicians with a useful decision-making reference for the adverse prognosis of COPD patients.
RESUMEN
INTRODUCTION: Estrogen receptors (ESRs) and progesterone receptors (PGRs) are associated with the development and progression of various tumors. The feasibility of ESRs and PGRs as prognostic markers and therapeutic targets for multiple cancers was evaluated via pan-cancer analysis. METHODS: The pan-cancer mRNA expression levels, genetic variations, and prognostic values of ESR1, ESR2, and PGR were analyzed using the Gene Expression Profiling Interactive Analysis 2 (GEPIA2) and cBioPortal. The expression levels of ERa, ERb, and PGR proteins were detected by immunohistochemical staining using paraffin-embedded tissue specimens of ovarian serous cystadenocarcinoma (OV) and uterine endometrioid adenocarcinoma (UTEA). Correlation between immunomodulators and immune cells was determined based on the Tumor and Immune System Interaction Database (TISIDB). RESULTS: ESR1, ESR2, and PGR mRNAs were found to be differentially expressed in different cancer types, and were associated with tumor progression and clinical prognosis. ERa, ERb, and PGR proteins were further determined to be significantly differentially expressed in OV and UTEA via immunohistochemical staining. The expression of ERa protein was positively correlated with a high tumor stage, whereas the expression of PGR protein was conversely associated with a high tumor stage in patients with OV. In patients with UTEA, the expression levels of both ERa and PGR proteins were conversely associated with tumor grade and stage. In addition, the expression levels of ESR1, ESR2, and PGR mRNAs were significantly associated with the expression of immunomodulators and immune cells. CONCLUSION: ESR1, ESR2, and PGR are potential prognostic markers and therapeutic targets, as well as important factors for the prediction, evaluation, and individualized treatment in several cancer types.
RESUMEN
BACKGROUND: Artificial intelligence of things (AIoT) may be a solution for predicting adverse outcomes in emergency department (ED) patients with pneumonia; however, this issue remains unclear. Therefore, we conducted this study to clarify it. METHODS: We identified 52,626 adult ED patients with pneumonia from three hospitals between 2010 and 2019 for this study. Thirty-three feature variables from electronic medical records were used to construct an artificial intelligence (AI) model to predict sepsis or septic shock, respiratory failure, and mortality. After comparisons of the predictive accuracies among logistic regression, random forest, support-vector machine (SVM), light gradient boosting machine (LightGBM), multilayer perceptron (MLP), and eXtreme Gradient Boosting (XGBoost), we selected the best one to build the model. We further combined the AI model with the Internet of things as AIoT, added an interactive mode, and implemented it in the hospital information system to assist clinicians with decision making in real time. We also compared the AIoT-based model with the confusion-urea-respiratory rate-blood pressure-65 (CURB-65) and pneumonia severity index (PSI) for predicting mortality. RESULTS: The best AI algorithms were random forest for sepsis or septic shock (area under the curve [AUC] = 0.781), LightGBM for respiratory failure (AUC = 0.847), and mortality (AUC = 0.835). The AIoT-based model represented better performance than CURB-65 and PSI indicators for predicting mortality (0.835 vs. 0.681 and 0.835 vs. 0.728). CONCLUSIONS: A real-time interactive AIoT-based model might be a better tool for predicting adverse outcomes in ED patients with pneumonia. Further validation in other populations is warranted.
Asunto(s)
Inteligencia Artificial , Neumonía , Adulto , Servicio de Urgencia en Hospital , Humanos , Modelos Logísticos , Neumonía/diagnóstico , Estudios RetrospectivosRESUMEN
In the year 2020, the coronavirus disease 2019 (COVID-19) crisis intersected with the development and maturation of several digital technologies including the internet of things (IoT) with next-generation 5G networks, artificial intelligence (AI) that uses deep learning, big data analytics, and blockchain and robotic technology, which has resulted in an unprecedented opportunity for the progress of telemedicine. Digital technology-based telemedicine platform has currently been established in many countries, incorporated into clinical workflow with four modes, including "many to one" mode, "one to many" mode, "consultation" mode, and "practical operation" mode, and has shown to be feasible, effective, and efficient in sharing epidemiological data, enabling direct interactions among healthcare providers or patients across distance, minimizing the risk of disease infection, improving the quality of patient care, and preserving healthcare resources. In this state-of-the-art review, we gain insight into the potential benefits of demonstrating telemedicine in the context of a huge health crisis by summarizing the literature related to the use of digital technologies in telemedicine applications. We also outline several new strategies for supporting the use of telemedicine at scale.
RESUMEN
Ultrasound (US), a ï¬exible green imaging modality, is expanding globally as a ï¬rst-line imaging technique in various clinical fields following with the continual emergence of advanced ultrasonic technologies and the well-established US-based digital health system. Actually, in US practice, qualified physicians should manually collect and visually evaluate images for the detection, identification and monitoring of diseases. The diagnostic performance is inevitably reduced due to the intrinsic property of high operator-dependence from US. In contrast, artificial intelligence (AI) excels at automatically recognizing complex patterns and providing quantitative assessment for imaging data, showing high potential to assist physicians in acquiring more accurate and reproducible results. In this article, we will provide a general understanding of AI, machine learning (ML) and deep learning (DL) technologies; We then review the rapidly growing applications of AI-especially DL technology in the field of US-based on the following anatomical regions: thyroid, breast, abdomen and pelvis, obstetrics heart and blood vessels, musculoskeletal system and other organs by covering image quality control, anatomy localization, object detection, lesion segmentation, and computer-aided diagnosis and prognosis evaluation; Finally, we offer our perspective on the challenges and opportunities for the clinical practice of biomedical AI systems in US.
Asunto(s)
Inteligencia Artificial , Aprendizaje Automático , Diagnóstico por Computador , Diagnóstico por Imagen , Humanos , UltrasonografíaRESUMEN
With a large agricultural sector, China is greatly affected by natural disasters caused by extreme weather events. Because the occurrence of natural disasters is closely related to the sharp increased consumption of energy and the massive emissions of carbon dioxide, this research examines relevant data from 2013 to 2017 in four major regions of China that cover 30 provincial administrative regions. Using the two-stage dynamic DEA model, we evaluate total efficiency value, two-stage efficiency value, and the efficiencies of energy consumption, CO2 emissions, and crop disaster areas, setting CO2 as the link between the production stage (first stage) and the crop damage stage (second stage). The research findings show that overall efficiency in China is generally low, whereby the total efficiencies of eastern and northeastern China are higher than those of central and western China. The efficiency value of the first stage (production stage) is greater than that of the second stage (crop damage stage), and the efficiency of most administrative regions' second stage is below 0.3, which is the main reason for the country's low overall efficiency. There is little difference between China's CO2 and energy consumption efficiency scores, but the efficiency values of crop disaster areas fluctuate greatly. The efficiency scores of various indicators in the eastern region are generally higher and more balanced, and the total efficiency scores exhibit a decreasing trend from east to west. Therefore, it is necessary to implement the environmental policy of controlling energy consumption and early warning of natural disasters in the central and western regions, and promote the R&D industry and technological innovation of carbon dioxide emission reduction and disaster control in the economically developed eastern regions.