RESUMEN
BACKGROUND: Schizophrenia is one of the leading causes of disability. Paliperidone palmitate once-monthly injection (PP1M) was developed to provide consistent drug delivery and improve medication adherence for maintenance treatment. It is well known that patients with schizophrenia have higher cardiovascular risks, however little is known about the cardiovascular risks of patients with schizophrenia treated with PP1M in Asia. OBJECTIVE: This study aimed to estimate the incidence of cardiovascular events after initiating PP1M treatment and evaluate the cardiovascular risk associations compared with oral second-generation antipsychotics (SGAs). METHODS: Data from Taiwan's National Health Insurance Research Database were used to identify a cohort of adult patients with schizophrenia who received any SGAs from 1 March 2012 to 31 December 2018. Patients who initiated PP1M treatment were enrolled for descriptive analysis of incidence rates. PP1M patients were propensity matched 1:1 to patients initiating a new oral SGA, for comparative analysis based on demographics, clinical characteristics and treatment history at baseline, in three-step matching procedures, following the prevalent new-user design to enhance comparability. Follow-up ended at the end of the treatment episode of index drug, death, last record available, or end of the study (31 December 2019). Study endpoints included serious cardiovascular events (including severe ventricular arrhythmia and sudden death), expanded serious cardiovascular events (which further included acute myocardial infarction and ischemic stroke), and cardiovascular hospitalizations. Risks of study endpoints between matched cohorts were compared using Cox regression. RESULTS: Overall, 11,023 patients initiating PP1M treatment were identified (49.5% were females; mean age of 43.2 [12.2] years). Overall incidences for serious cardiovascular events, expanded serious cardiovascular events, and cardiovascular hospitalizations were 3.92, 7.88 and 51.96 per 1000 person-years, respectively. In matched cohort analysis (N = 10,115), the hazard ratios (HRs) between initiating PP1M and a new oral SGA for serious cardiovascular events, expanded serious cardiovascular events, and cardiovascular hospitalizations were 0.86 (95% confidence interval [CI] 0.55-1.36), 0.88 (95% CI 0.63-1.21), and 0.78 (95% CI 0.69-0.89), respectively. CONCLUSION: This study reported the population-based incidence of cardiovascular events in schizophrenic patients initiating PP1M treatment. PP1M was not associated with increased risks of serious cardiovascular events but was potentially associated with lower risks of cardiovascular hospitalizations compared with oral SGAs.
Asunto(s)
Antipsicóticos , Enfermedades Cardiovasculares , Palmitato de Paliperidona , Esquizofrenia , Humanos , Esquizofrenia/tratamiento farmacológico , Esquizofrenia/epidemiología , Femenino , Masculino , Palmitato de Paliperidona/administración & dosificación , Palmitato de Paliperidona/efectos adversos , Taiwán/epidemiología , Estudios Retrospectivos , Adulto , Enfermedades Cardiovasculares/epidemiología , Enfermedades Cardiovasculares/inducido químicamente , Persona de Mediana Edad , Antipsicóticos/administración & dosificación , Antipsicóticos/efectos adversos , Incidencia , InyeccionesRESUMEN
BACKGROUND: In practice, the collected datasets for data analysis are usually incomplete as some data contain missing attribute values. Many related works focus on constructing specific models to produce estimations to replace the missing values, to make the original incomplete datasets become complete. Another type of solution is to directly handle the incomplete datasets without missing value imputation, with decision trees being the major technique for this purpose. OBJECTIVE: To introduce a novel approach, namely Deep Learning-based Decision Tree Ensembles (DLDTE), which borrows the bounding box and sliding window strategies used in deep learning techniques to divide an incomplete dataset into a number of subsets and learning from each subset by a decision tree, resulting in decision tree ensembles. METHOD: Two medical domain problem datasets contain several hundred feature dimensions with the missing rates of 10% to 50% are used for performance comparison. RESULTS: The proposed DLDTE provides the highest rate of classification accuracy when compared with the baseline decision tree method, as well as two missing value imputation methods (mean and k-nearest neighbor), and the case deletion method. CONCLUSION: The results demonstrate the effectiveness of DLDTE for handling incomplete medical datasets with different missing rates.
Asunto(s)
Aprendizaje Profundo , Humanos , Análisis por Conglomerados , Árboles de DecisiónRESUMEN
Data discretization aims to transform a set of continuous features into discrete features, thus simplifying the representation of information and making it easier to understand, use, and explain. In practice, users can take advantage of the discretization process to improve knowledge discovery and data analysis on medical domain problem datasets containing continuous features. However, certain feature values were frequently missing. Many data-mining algorithms cannot handle incomplete datasets. In this study, we considered the use of both discretization and missing-value imputation to process incomplete medical datasets, examining how the order of discretization and missing-value imputation combined influenced performance. The experimental results were obtained using seven different medical domain problem datasets: two discretizers, including the minimum description length principle (MDLP) and ChiMerge; three imputation methods, including the mean/mode, classification and regression tree (CART), and k-nearest neighbor (KNN) methods; and two classifiers, including support vector machines (SVM) and the C4.5 decision tree. The results show that a better performance can be obtained by first performing discretization followed by imputation, rather than vice versa. Furthermore, the highest classification accuracy rate was achieved by combining ChiMerge and KNN with SVM.
Asunto(s)
Algoritmos , Máquina de Vectores de Soporte , Minería de Datos , Análisis por ConglomeradosRESUMEN
BACKGROUND: Anorexia nervosa (AN) is a serious and potentially life-threatening eating disorder characterized by starvation and malnutrition, a high prevalence of coexisting psychiatric conditions, marked treatment resistance, frequent medical complications, and a substantial risk of death. Body mass index (BMI) is a key measure of treatment outcome of AN and it is necessary to evaluate the long-term prognosis of AN. This study aimed to better assess the BMI course trend between different medications and timepoints in order to improve AN treatment in clinical practice. METHODS: During the period 2010-2021, we retrospectively reviewed historical data of all patients diagnosed with AN. There were two groups in this study, which were based on the duration of follow-up. Group A was a 6-month follow-up group, comprising 93 patients (mean age 19.6 ± 6.8 years), with BMI assessed at three consecutive time points: first outpatient visit (T0), three months follow-up (T3), and six months follow-up (T6). Group B was a 12-month follow-up group comprising 36 patients (mean age 17.0 ± 5.2 years) with BMI assessed at five consecutive time points: first outpatient visit (T0), three months follow-up (T3), six months follow-up (T6), nine months follow-up (T9), and twelve months follow-up (T12). In our study, we retrospectively compared BMI courses based on patients' usage of medication using the following variables: single medication, switching medications, combined medications, and without medications. The primary outcome measurement was BMI recorded at the 6-month follow-up and the 12-month follow-up respectively. In our study, which was conducted at Taichung Veterans General Hospital, we reviewed outpatient medical records of all patients with AN who were seen at the hospital during the period 2010-2021. RESULTS: In Group A (6-month follow-up), patients treated with antidepressants showed a mean BMI increase of 1.3 (p < 0.001); patients treated with antipsychotics showed a mean BMI increase of 1.1 (p = 0.01); patients treated with switching medications showed a mean BMI increase of 0.1 (p = 0.397); patients treated with combined medications showed a mean BMI increase of 0.5 (p = 0.208); and patients treated without medications showed a mean BMI increase of 0.1 (p = 0.821). The results indicated that patients with AN had a significant BMI increase after treatment with antidepressants and antipsychotics in the 6-month follow-up group. In Group B (12-month follow-up), patients treated with antidepressants showed a mean BMI increase of 2.7 (p < 0.001); patients treated with antipsychotics showed a mean BMI increase of 2.8 (p = 0.168); patients treated with switching medications showed a mean BMI decrease of 0.8 (p = 0.595); patients treated with combined medications showed a mean BMI increase of 1.6 (p = 0.368); and patients treated without medications showed a mean BMI increase of 1.0 (p = 0.262). The results indicated that patients with AN had a significant BMI increase after treatment with antidepressants at the 12-month follow-up. CONCLUSIONS: AN is a complex disease caused by multiple factors. Evaluating its long-term prognosis is crucial. Our study provides insights and highlights three key findings: 1) medication adherence is crucial in treating AN, 2) frequent switching of medications may not promote weight gain and may also require a re-establishment of rapport with patients with AN, and 3) pharmacotherapy, especially antidepressants, is more effective than no treatment. Further research is needed to confirm these findings.
Asunto(s)
Anorexia Nerviosa , Antipsicóticos , Humanos , Niño , Adolescente , Adulto Joven , Adulto , Estudios Retrospectivos , Anorexia Nerviosa/tratamiento farmacológico , Estudios de Seguimiento , Pacientes Ambulatorios , Antipsicóticos/uso terapéutico , Hospitales GeneralesRESUMEN
Objective: Endometrial cancer is the most common malignancy of the female genital tract worldwide, and the associated relationship between endometrial cancer formation and various antipsychotics need to be confirmed. Methods: We conducted a case-control study by using data from Taiwan National Health Insurance Research Database to compare individual antipsychotic exposure between females with and without endometrial cancer. Among 14,079,089 females in the 12-year population-based national dataset, 9,502 females with endometrial cancer were identified. Their medical records of exposure to antipsychotics, including quetiapine, haloperidol, risperidone, olanzapine, amisulpride, clozapine, and aripiprazole, for up to 3 years before endometrial cancer diagnosis were reviewed. Daily dosage and cumulative exposure days were analyzed in the risky antipsychotic users. Additionally, the subsequent 5-year mortality rate of endometrial cancer among users of the risky antipsychotic were also analyzed. Results: Among endometrial cancer patients, the proportion of those who have used haloperidol before being diagnosed with endometrial cancer is significantly higher than other antipsychotic users. The significant odds ratio (OR) and a 95% confidence interval of 1.75 (1.31-2.34) were noted. Furthermore, haloperidol users were associated with a significantly higher 5-year mortality rate after getting endometrial cancer than non-users. Conclusion: There is a high correlation between the use of haloperidol and endometrial cancer formation. However, the underlying pathological biomechanisms require additional investigations.
RESUMEN
BACKGROUND: Long-acting injectable (LAI) antipsychotics improve medication adherence in patients with schizophrenia and extend the duration of therapeutic drug levels but with administration of an increased dose. Real-world mortality data in patients prescribed LAIs are lacking. We conducted a population-based cohort study to estimate and compare the incidence rates of all-cause death and completed suicide in patients with schizophrenia/schizoaffective disorder exposed to LAIs and oral antipsychotics. METHODS: Patients with a diagnosis of schizophrenia/schizoaffective disorder between January 1, 2015 and November 30, 2019 were enrolled from the Taiwan National Health Insurance Research Database and linked to Death Registry records. Eligible patients were new antipsychotic users. Relative risks of death for each antipsychotic compared with oral paliperidone were evaluated using a Cox proportional hazard model adjusted for age, sex, Charlson Comorbidity Index, index year, bipolar or major depressive or other mood disorders, mental disorders due to drug use, and baseline hospitalization frequency. RESULTS: There were 228,791.08 person-years of follow-up (mean 2.48 years). The incidence rates of all-cause death in users of LAI paliperidone administered monthly (PP1M) and every 3 months (PP3M) were 7.40/1,000 person-years (95% confidence interval 5.94-9.11) and 9.93 (5.88-15.79), respectively. The incidences of completed suicide were 2.03/1,000 person-years (1.32-2.99) and 3.10 (1.14-6.88), respectively. No significant associations were observed between PP1M and PP3M compared to oral paliperidone in incidences of all-cause death or for completed suicide. DISCUSSION: No increased risk of all-cause death or completed suicide was observed in users of antipsychotic LAIs, including PP1M and PP3M.
Asunto(s)
Antipsicóticos , Trastorno Depresivo Mayor , Trastornos Psicóticos , Esquizofrenia , Suicidio Completo , Antipsicóticos/efectos adversos , Estudios de Cohortes , Preparaciones de Acción Retardada/uso terapéutico , Trastorno Depresivo Mayor/tratamiento farmacológico , Humanos , Trastornos Psicóticos/tratamiento farmacológico , Trastornos Psicóticos/epidemiología , Estudios Retrospectivos , Esquizofrenia/tratamiento farmacológico , Taiwán/epidemiologíaRESUMEN
As the proportion of elderly people continues to grow, so does the concern about age-related cognitive decline. Serious games have been developed for cognitive training or treatment, but measuring the activity of the autonomic nervous system (ANS) has not been taken to account. However, cognitive functioning has been known to be heavily influenced by the autonomic nervous system (ANS), and ANS activity can be quantified using heart rate variability (HRV). This paper aims to analyze the physiological response in normal elderly people as they play two types of serious games using HRV features from electrocardiography (ECG). A wearable device designed in-house was used to measure ECG, and the data from this device was pre-processed using digital signal processing techniques. Ten HRV features were extracted, including time-domain, nonlinear, and frequency-domain features. The experiment proceeds as follows: rest for three minutes, play a cognitive aptitude game, rest for another three minutes, followed by two reaction time games. Data from thirty older adults (age: 65.9 ± 7.34; male: 15, female: 15) were analyzed. The statistical results show that there was a significant difference in the HRV between the two types of games. From this, it can be concluded that the type of game has a significant effect on the ANS response. This can be further used in designing games for the elderly, either for training or mood management.
Asunto(s)
Sistema Nervioso Autónomo , Dispositivos Electrónicos Vestibles , Anciano , Electrocardiografía , Femenino , Frecuencia Cardíaca , Humanos , Masculino , Persona de Mediana Edad , DescansoRESUMEN
For decades, scientists have been trying to solve the problem of dementia, with no cure currently available. Semantic-lexical impairment is well established as the early critical sign of dementia, although there are still gaps in knowledge that must be investigated. In this study, we used fMRI to observe the neural activity of 31 subjects, including 16 HC (Healthy Control) and 15 AD (Alzheimer's Disease), who participated in the naming task. The neuropsychology profile of HC (Healthy Control) and AD (Alzheimer's Disease) are discussed in this study. The involvement of FG (Fusiform Gyrus) and IFG (Inferior Frontal Gyrus) shows dominant activation in both of the groups. We observed a decrease in neural activity in the AD group, resulting in semantic deficit problems in this preliminary study. Furthermore, ROI analysis was performed and revealed both hyperactivation and hypoactivation in the AD group. The compensatory mechanism demonstrated during the task, due to the effort required to identify an animal's name, represents the character profile of AD.
RESUMEN
OBJECTIVE: Major depressive disorder (MDD) is a complex mental disorder. The lack of well-established biomarkers hinders its diagnosis, treatment, and new-drug development. N-methyl-D-aspartate receptor (NMDAR) dysfunction has been implicated in the pathogenesis of MDD. This study examined whether expressions of the NMDAR-related genes are characteristic of MDD. METHODS: Expressions of NMDAR-related genes including SRR, SHMT2, PSAT1, GCAT, GAD1, SLC1A4, NRG1 and COMT in peripheral WBCs of 110 patients with MDD (25 drug-naïve, 21 drug-free, and 64 medicated patients) and 125 healthy individuals were measured using quantitative PCR. RESULTS: The mRNA expression levels of SRR, PSAT1, GCAT, GAD1, NRG1 and COMT were significantly different among the four groups (all pâ¯<â¯0.05). For drug-naïve patients, the ΔΔCT values of SRR, PSAT1, GCAT, GAD1, and NRG1 mRNA expressions were significantly different from those in healthy individuals (all pâ¯<â¯0.05). The ROC analysis of the ΔΔCT values of the target genes for differentiating drug-naïve patients from healthy controls showed an excellent sensitivity (0.960) and modest specificity (0.640) (AUCâ¯=â¯0.889). Drug-free and medicated patients obtained less favorable AUC values while compared to healthy controls. The results for the age- and sex-matched cohort were similar to those of the unmatched cohort. CONCLUSIONS: This is the first study demonstrating that the peripheral mRNA expression levels of NMDAR-related genes may be altered in patients with MDD, especially drug-naïve individuals. The finding supports the NMDAR hypothesis of depression. Whether mRNA expresssion of NMDAR-related genes could serve as a potential biomarker of MDD deserves further investigations.
Asunto(s)
Trastorno Depresivo Mayor/genética , Leucocitos/metabolismo , ARN Mensajero/metabolismo , Receptores de N-Metil-D-Aspartato/metabolismo , Aciltransferasas/genética , Aciltransferasas/metabolismo , Adulto , Sistema de Transporte de Aminoácidos ASC/genética , Sistema de Transporte de Aminoácidos ASC/metabolismo , Antidepresivos/uso terapéutico , Pueblo Asiatico/genética , Biomarcadores/metabolismo , Estudios de Casos y Controles , Catecol O-Metiltransferasa/genética , Catecol O-Metiltransferasa/metabolismo , Estudios de Cohortes , Trastorno Depresivo Mayor/tratamiento farmacológico , Trastorno Depresivo Mayor/metabolismo , Femenino , Glutamato Descarboxilasa/genética , Glutamato Descarboxilasa/metabolismo , Glicina Hidroximetiltransferasa/genética , Glicina Hidroximetiltransferasa/metabolismo , Humanos , Lipasa/genética , Lipasa/metabolismo , Masculino , Persona de Mediana Edad , Neurregulina-1/genética , Neurregulina-1/metabolismo , Curva ROC , Racemasas y Epimerasas/genética , Racemasas y Epimerasas/metabolismo , Transaminasas/genética , Transaminasas/metabolismoRESUMEN
BACKGROUND: In past magnetic resonance imaging studies, normal participants and schizophrenia patients have usually been compared using imaging processing modes with only one parameter. A more extensive evaluation of significant differences between gray and white matter in Schizophrenic patents was necessary. METHODS: Voxel based morphometry was used to separate brain images into gray matter and white matter. Then, the images were mapped to Montreal Neurological Institute space, and DARTEL analytic template was applied for image calibration with statistical parametric mapping. Finally, joint independent component analysis was employed to analyze the gray and white matter of brain images from Schizophrenic patients and normal controls. In this study, joint independent component analysis was used to discriminate clinical differences in magnetic resonance imaging signals between Schizophrenic patients and normal controls. RESULTS: Region of interest analyses has repeatedly shown gray matter reduction in the superior temporal gyrus of Schizophrenic patients. CONCLUSION: These results strongly support previous studies regarding brain volume in schizophrenic patients. The connection networks in frontal and temporal lobes evidently did not differ between normal participants and schizophrenia patients.
Asunto(s)
Sustancia Gris/diagnóstico por imagen , Imagen por Resonancia Magnética , Neuroimagen/métodos , Esquizofrenia/diagnóstico por imagen , Sustancia Blanca/diagnóstico por imagen , Adulto , Femenino , Humanos , Masculino , Análisis de Componente PrincipalRESUMEN
Bioelectrical impedance analysis technology was used tomeasure whole body parameters and electrical resistance and reactance of specific body regions in schizophrenia patients after long-term medication use. Patient data was compared to that of a control group of subjects to analyze metabolic differences. Our experimental group was composed of 60 schizophrenia patients, and the control group was composed of 30 normal subjects. T-test and ANOVA analyses were conducted to compared differences between groups, with confidencev intervals set at 95%. T-test results showed significant differences in body fat levels between groups (F=4.753, p=0.031<0.05). Additionally, we also found significant differences in upper body resistance and reactance (F=78.433, p=0.000<0.05, F=67.488, p=0.000<0.05), which could be related to accumulation of body fat. These results show correlation between schizophrenia and development of metabolic syndrome.
Asunto(s)
Esquizofrenia , Tejido Adiposo , Composición Corporal , Impedancia Eléctrica , Humanos , Síndrome MetabólicoRESUMEN
Depressive disorder is a severe mental disorder associated with functional and cognitive impairment. Numerous papers in the literature investigated associations between sexually transmitted infections (STIs) and psychiatric illnesses. However, the results of these studies are controversial.We explored the relationship between depressive disorder and the subsequent development of STIs including human immunodeficiency virus (HIV) infection, primary, secondary, and latent syphilis, genital warts, gonorrhea, chlamydial infection, and trichomoniasis.We identified patients who were diagnosed with the depressive disorder in the Taiwan National Health Insurance Research Database. A comparison cohort was constructed of patients without the depressive disorder who were matched according to age and sex. The occurrence of subsequent new-onset STIs was evaluated in both cohorts.The depression cohort consisted of 5959 patients, and the comparison cohort consisted of 23,836 matched control patients without depressive disorder. The incidence of subsequent STIs (hazard ratio [HR] 1.54, 95% confidence interval [CI] 1.34-1.76) was higher among the depressed patients than among the patients in the comparison cohort. Furthermore, female gender compared to male (HR 1.58, 95% CI 1.24-2.01) and young age <40-year-old (HR 1.79, 95% CI 1.38-2.32) are both risk factors for acquisition of STIs in depression patient. For individual STI, the results indicated that the patients with depressive disorder exhibited a markedly higher risk for subsequent STIs including HIV infection, syphilis, genital warts, gonorrhea, chlamydial infection, and trichomoniasis.Depressive disorder might increase the risk of subsequent newly diagnosed STIs including HIV infection, syphilis, genital warts, gonorrhea, chlamydial infection, and trichomoniasis in Taiwan population. Clinicians should pay particular attention to STIs in depression patients. Depression patients, especially those with the history of high-risk sexual behaviors, should be routinely screened for STIs.
Asunto(s)
Trastorno Depresivo/etiología , Vigilancia de la Población , Conducta Sexual , Enfermedades Bacterianas de Transmisión Sexual/complicaciones , Adulto , Trastorno Depresivo/epidemiología , Femenino , Estudios de Seguimiento , Humanos , Incidencia , Masculino , Persona de Mediana Edad , Estudios Retrospectivos , Factores de Riesgo , Enfermedades Bacterianas de Transmisión Sexual/epidemiología , Taiwán/epidemiología , Factores de TiempoRESUMEN
Rationale: Although molecular investigations of regulator of G-protein signaling 4 (RGS4) alterations in schizophrenia patients yielded partially inconsistent findings, the previous studies suggested that RGS4 is both a positional and functional candidate gene for schizophrenia and is significantly decreased in the prefrontal cortex. However, the exact role of RGS4 in the pathophysiology of schizophrenia is unclear. Moreover, a whole genome transcription profile study showed the possibility of RGS4-regulated expression of SLC7A11(xCT), a component of cysteine/glutamate transporter or system xc-. We hypothesized that system xc- is a therapeutic target of RGS4 deficit-mediated schizophrenia. Methods: Pharmacological and genetic manipulation of RGS4 in organotypic brain slice cultures were used as an ex vivo model to investigate its role in system xc- and glutamatergic function. Lentiviral-based mouse models with RGS4 deficit in the prefrontal cortex and treatment with system xc- activator, N-acetyl cysteine (NAC), were utilized to observe their impacts on glutamatergic function and schizophrenic behaviors. Results: Genetic and pharmacological inhibition of RGS4 resulted in a significant decrease in SLC7A11 (xCT) expression and hypofunction of system xc- and reduced glutamatergic function in organotypic brain slice cultures. However, NAC restored the dysregulation of RGS4-mediated functional deficits of glutamate. Moreover, knockdown of RGS4 specifically in the prefrontal cortex caused mice to exhibit behaviors related to schizophrenia such as increased stereotypy, impaired prepulse inhibition, deficits in social interactions, working memory, and nesting behavior, while enhancing sensitivity to the locomotor stimulatory effect of MK-801. These mice displayed glutamatergic dysfunction in the prefrontal cortex, which may have contributed to the behavioral deficits. RGS4 knockdown mice that received NAC treatment had improved glutamatergic dysfunction and schizophrenia behaviors. Conclusion: Our results suggest that RGS4 deficit induces dysregulation and dysfunction of system xc-, which further results in functional deficits of the glutamatergic system and subsequently to schizophrenia-related behavioral phenotypes. Activation of system xc- offers a promising strategy to treat RGS4 deficit-mediated schizophrenia.
Asunto(s)
Sistema de Transporte de Aminoácidos y+/biosíntesis , Regulación de la Expresión Génica , Corteza Prefrontal/fisiopatología , Proteínas RGS/metabolismo , Esquizofrenia/fisiopatología , Acetilcisteína/administración & dosificación , Animales , Conducta Animal/efectos de los fármacos , Modelos Animales de Enfermedad , Técnicas de Silenciamiento del Gen , Ratones , Técnicas de Cultivo de Órganos , Proteínas RGS/genéticaRESUMEN
Digoxin is a high-alert medication because of its narrow therapeutic range and high drug-to-drug interactions (DDIs). Approximately 50% of digoxin toxicity cases are preventable, which motivated us to improve the treatment outcomes of digoxin. The objective of this study is to apply machine learning techniques to predict the appropriateness of initial digoxin dosage. A total of 307 inpatients who had their conditions treated with digoxin between 2004 and 2013 at a medical center in Taiwan were collected in the study. Ten independent variables, including demographic information, laboratory data, and whether the patients had CHF were also noted. A patient with serum digoxin concentration being controlled at 0.5-0.9 ng/mL after his/her initial digoxin dosage was defined as having an appropriate use of digoxin; otherwise, a patient was defined as having an inappropriate use of digoxin. Weka 3.7.3, an open source machine learning software, was adopted to develop prediction models. Six machine learning techniques were considered, including decision tree (C4.5), k-nearest neighbors (kNN), classification and regression tree (CART), randomForest (RF), multilayer perceptron (MLP), and logistic regression (LGR). In the non-DDI group, the area under ROC curve (AUC) of RF (0.912) was excellent, followed by that of MLP (0.813), CART (0.791), and C4.5 (0.784); the remaining classifiers performed poorly. For the DDI group, the AUC of RF (0.892) was the best, followed by CART (0.795), MLP (0.777), and C4.5 (0.774); the other classifiers' performances were less than ideal. The decision tree-based approaches and MLP exhibited markedly superior accuracy performance, regardless of DDI status. Although digoxin is a high-alert medication, its initial dose can be accurately determined by using data mining techniques such as decision tree-based and MLP approaches. Developing a dosage decision support system may serve as a supplementary tool for clinicians and also increase drug safety in clinical practice.
Asunto(s)
Antiarrítmicos/administración & dosificación , Sistemas de Apoyo a Decisiones Clínicas , Digoxina/administración & dosificación , Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos/prevención & control , Aprendizaje Automático , Adulto , Anciano , Anciano de 80 o más Años , Antiarrítmicos/efectos adversos , Digoxina/efectos adversos , Femenino , Humanos , Masculino , Persona de Mediana Edad , Adulto JovenRESUMEN
BACKGROUND: Bipolar disorder is a severe mental disorder associated with functional and cognitive impairment. Numerous studies have investigated associations between sexually transmitted infections (STIs) and psychiatric illnesses. However, the results of these studies are controversial. OBJECTIVE: We explored the association between bipolar disorder and the subsequent development of STIs, including human immunodeficiency virus infection; primary, secondary, and latent syphilis; genital warts; gonorrhea; chlamydial infection; and trichomoniasis. RESULTS: The bipolar cohort consisted of 1293 patients, and the comparison cohort consisted of 5172 matched control subjects without bipolar disorder. The incidence of subsequent STIs (hazard ratio (HR) = 2.23, 95% confidence interval (CI) 1.68-2.96) was higher among the patients with bipolar disorder than in the comparison cohort. Furthermore, female gender is a risk factor for acquisition of STIs (HR = 2.36, 95% CI 1.73-4.89) among patients with bipolar disorder. For individual STIs, the results indicated that the patients with bipolar disorder exhibited a markedly higher risk for subsequently contracting syphilis, genital warts, and trichomoniasis. CONCLUSIONS: Bipolar disorder might increase the risk of subsequent newly diagnosed STIs, including syphilis, genital warts, and trichomoniasis. Clinicians should pay particular attention to STIs in patients with bipolar disorder. Patients with bipolar disorder, especially those with a history of high-risk sexual behaviors, should be routinely screened for STIs. METHODS: We identified patients who were diagnosed with bipolar disorder in the Taiwan National Health Insurance Research Database. A comparison cohort was constructed of patients without bipolar disorder who were matched with the bipolar cohort according to age and gender. The occurrence of subsequent new-onset STIs was evaluated in both cohorts.
RESUMEN
Many real-world medical datasets contain some proportion of missing (attribute) values. In general, missing value imputation can be performed to solve this problem, which is to provide estimations for the missing values by a reasoning process based on the (complete) observed data. However, if the observed data contain some noisy information or outliers, the estimations of the missing values may not be reliable or may even be quite different from the real values. The aim of this paper is to examine whether a combination of instance selection from the observed data and missing value imputation offers better performance than performing missing value imputation alone. In particular, three instance selection algorithms, DROP3, GA, and IB3, and three imputation algorithms, KNNI, MLP, and SVM, are used in order to find out the best combination. The experimental results show that that performing instance selection can have a positive impact on missing value imputation over the numerical data type of medical datasets, and specific combinations of instance selection and imputation methods can improve the imputation results over the mixed data type of medical datasets. However, instance selection does not have a definitely positive impact on the imputation result for categorical medical datasets.
Asunto(s)
Algoritmos , Bases de Datos Factuales , Aprendizaje Automático , Reconocimiento de Normas Patrones Automatizadas/métodos , Investigación Biomédica , Humanos , Registros MédicosRESUMEN
BACKGROUND: Although erectile dysfunction (ED) is a common problem in men with mental disorders, there are few reports in the literature on the relation between bipolar disorder (BD) and ED. AIMS: To establish the incidence rate of ED in men with BD and assess the risk of ED in patients with BD according to type of treatment offered or no active treatment with medication during the 1st year of onset. METHODS: We identified 5,150 men with newly diagnosed BD using Taiwan's National Health Insurance Research Database. 2 matched controls per case were selected using the propensity score and a greedy matching method to obtain a balanced control group. Multivariate Cox regression analysis was used to examine the independent risk factors for ED, including obesity and comorbidities. Hazard ratios (HRs) for ED risk were calculated for the different psychotropic therapy groups, including antidepressants, antipsychotics, and mood stabilizers. OUTCOME: HRs for ED risk were calculated for the different psychotropic therapy groups, including antidepressants, antipsychotics, and mood stabilizers. Patients with BD had a significantly higher HR for an ED diagnosis than controls. RESULTS: Patients with BD had a higher HR for an ED diagnosis than controls. Although some psychotropic medications can increase the risk of ED, patients with BD not actively treated with medication still showed a higher risk of ED than controls. CLINICAL IMPLICATIONS: Because ED might be more prevalent in patients with BD than in the general population, clinicians should assess erectile function when selecting appropriate treatment for patients with BD to minimize the risk of ED as an annoying side effect and improve treatment compliance. STRENGTHS AND LIMITATIONS: This is the first large-scale population-based study to explore the association between BD and ED. A particular strength of this study is its nationwide, population-based study design, which afforded substantial statistical power for detecting subtle differences between the 2 cohorts, thereby minimizing selection bias. There are some limitations to the present study. (i) Data on other potential risk factors is lacking. (ii) Patient compliance and dose effect between psychotropic medication and ED could not be established. (iii) We could not assess the relation between ED and the severity and phases of BD. CONCLUSION: This cohort study found a temporal association between BD and subsequent ED in a large national sample of men. Clinicians should consider the risk of ED when choosing treatment for patients with BD. Hou P-H, Mao FC, Chang G-R, et al. Newly Diagnosed Bipolar Disorder and the Subsequent Risk of Erectile Dysfunction: A Nationwide Cohort Study. J Sex Med 2018;15:183-191.
Asunto(s)
Trastorno Bipolar/complicaciones , Disfunción Eréctil/etiología , Adolescente , Adulto , Antidepresivos/uso terapéutico , Antipsicóticos/uso terapéutico , Estudios de Cohortes , Comorbilidad , Bases de Datos Factuales , Disfunción Eréctil/epidemiología , Humanos , Masculino , Persona de Mediana Edad , Análisis Multivariante , Prevalencia , Modelos de Riesgos Proporcionales , Factores de Riesgo , Taiwán/epidemiología , Adulto JovenRESUMEN
BACKGROUND: In this study, the international affective picture system was used to evoke emotion, and then the corresponding signals were collected. The features from different points of brainwaves, frequency, and entropy were used to identify normal, moderately, and markedly ill schizophrenic patients. METHODS: The signals were collected and preprocessed. Then, the signals were separated according to three types of emotions and five frequency bands. Finally, the features were calculated using three different methods of entropy. For classification, the features were divided into different sections and classification using support vector machine (principal components analysis on 95%). Finally, simple regression and correlation analysis between the total scores of positive and negative syndrome scale and features were used. RESULTS: At first, we observed that to classify normal and markedly ill schizophrenic patients, the identification result was as high as 81.5%, and therefore, we further explored moderately and markedly ill schizophrenic patients. Second, the identification rate in both moderately and markedly ill schizophrenic patient was as high as 79.5%, which at the Fz point signal in high valence low arousal fragments was calculated using the ApEn methods. Finally, the total scores of positive and negative syndrome scale were used to analyze the correlation with the features that were the five frequency bands at the Fz point signal. The results show that the p value was less than .001 at the beta wave in the 15-18 Hz frequency range.
RESUMEN
BACKGROUND: Schizophrenia is a neurological disease characterized by alterations to patients' cognitive functions and emotional expressions. Relevant studies often use magnetic resonance imaging (MRI) of the brain to explore structural differences and responsiveness within brain regions. However, as this technique is expensive and commonly induces claustrophobia, it is frequently refused by patients. Thus, this study used non-contact infrared thermal facial images (ITFIs) to analyze facial temperature changes evoked by different emotions in moderately and markedly ill schizophrenia patients. METHODS: Schizophrenia is an emotion-related disorder, and images eliciting different types of emotions were selected from the international affective picture system (IAPS) and presented to subjects during ITFI collection. ITFIs were aligned using affine registration, and the changes induced by small irregular head movements were corrected. The average temperatures from the forehead, nose, mouth, left cheek, and right cheek were calculated, and continuous temperature changes were used as features. After performing dimensionality reduction and noise removal using the component analysis method, multivariate analysis of variance and the Support Vector Machine (SVM) classification algorithm were used to identify moderately and markedly ill schizophrenia patients. RESULTS: Analysis of five facial areas indicated significant temperature changes in the forehead and nose upon exposure to various emotional stimuli and in the right cheek upon evocation of high valence low arousal (HVLA) stimuli. The most significant P-value (lower than 0.001) was obtained in the forehead area upon evocation of disgust. Finally, when the features of forehead temperature changes in response to low valence high arousal (LVHA) were reduced to 9 using dimensionality reduction and noise removal, the identification rate was as high as 94.3%. CONCLUSIONS: Our results show that features obtained in the forehead, nose, and right cheek significantly differed between moderately and markedly ill schizophrenia patients. We then chose the features that most effectively distinguish between moderately and markedly ill schizophrenia patients using the SVM. These results demonstrate that the ITFI analysis protocol proposed in this study can effectively provide reference information regarding the phase of the disease in patients with schizophrenia.