ABSTRACT
BACKGROUND AND OBJECTIVES: Epilepsy surgery is often delayed. We previously developed machine learning (ML) models to identify candidates for resective epilepsy surgery earlier in the disease course. In this study, we report the prospective validation. METHODS: In this multicenter, prospective, longitudinal cohort study, random forest models were validated at a pediatric epilepsy center consisting of 2 hospitals and 14 outpatient neurology clinic sites and an adult epilepsy center with 2 hospitals and 27 outpatient neurology clinic sites. The models used neurology visit notes, EEG and MRI reports, visit patterns, hospitalizations, and medication, laboratory, and procedure orders to identify candidates for surgery. The models were trained on historical data up to May 10, 2019. Patients with an ICD-10 diagnosis of epilepsy who visited from May 11, 2019, to May 10, 2020, were screened by the algorithm and assigned surgical candidacy scores. The primary outcome was area under the curve (AUC), which was calculated by comparing scores from patients who underwent epilepsy surgery before November 10, 2020, against scores from nonsurgical patients. Nonsurgical patients' charts were reviewed to determine whether patients with high scores were more likely to be missed surgical candidates. Delay to surgery was defined as the time between the first visit that a surgical candidate was identified by the algorithm and the date of the surgery. RESULTS: A total of 5,285 pediatric and 5,782 adult patients were included to train the ML algorithms. During the study period, 41 children and 23 adults underwent resective epilepsy surgery. In the pediatric cohort, AUC was 0.91 (95% CI 0.87-0.94), positive predictive value (PPV) was 0.08 (0.05-0.10), and negative predictive value (NPV) was 1.00 (0.99-1.00). In the adult cohort, AUC was 0.91 (0.86-0.97), PPV was 0.07 (0.04-0.11), and NPV was 1.00 (0.99-1.00). The models first identified patients at a median of 2.1 years (interquartile range [IQR]: 1.2-4.9 years, maximum: 11.1 years) before their surgery and 1.3 years (IQR: 0.3-4.0 years, maximum: 10.1 years) before their presurgical evaluations. DISCUSSION: ML algorithms can identify surgical candidates earlier in the disease course. Even at specialized epilepsy centers, there is room to shorten the time to surgery. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that a machine learning algorithm can accurately distinguish patients with epilepsy who require resective surgery from those who do not.
Subject(s)
Epilepsy , Adult , Humans , Child , Longitudinal Studies , Epilepsy/diagnosis , Epilepsy/surgery , Prospective Studies , Cohort Studies , Machine Learning , Retrospective StudiesABSTRACT
Eating disorders have been shown to be associated with epilepsy, typically associated with the temporal lobe and usually of non-dominant hemisphere origin. We report the case of a 56-year-old woman with drug resistant epilepsy, localized to the dominant left hippocampus. She experienced an increasing frequency of seizures over a two-year period associated with loss of appetite and substantial weight loss independent of antiseizure medication changes. Extensive workup eliminated gastrointestinal and paraneoplastic etiologies. There was no history of psychiatric illness, including anorexia nervosa. Pre-surgical workup showed mesial temporal sclerosis on MRI and video-EEG was consistent with ipsilateral medial temporal seizure onset. The patient underwent laser interstitial ablation of the left amygdala and hippocampus, which resulted in a cessation of seizures. Within 24 h of the laser ablation, her appetite returned to normal and, within 8 months she regained 26 lbs. To our knowledge, this is the first case report of a patient with dominant temporal lobe epilepsy with anorexia that was temporally associated with escalating seizure frequency and stopped with treatment and cessation of seizures, suggesting a causal and pathogenic relationship.
ABSTRACT
We present a case report of a 20-year-old male with diabetes mellitus type 1, who developed severe painful peripheral neuropathy while on the second of a 10-day course with levofloxacin for the treatment of epididymitis. The intensity of the pain rapidly reached scores of 10/10 in a numeric scale 0/10, and the patient was transferred to an inpatient pain unit where he was treated aggressively with minimal improvement. A skin biopsy revealed small fiber neuropathy. Then the patient was treated with intravenous immunoglobulin, which improved the pain. Now the patient is on outpatient intravenous immunoglobulin infusions bimonthly and making a slow recovery.
ABSTRACT
Introducción. La depresión tiene un fuerte vínculo en pacientes con insuficiencia cardíaca, influyendo en su morbilidad, mortalidad y tratamiento. Objetivos. Describir las características clínicas, de laboratorio, electrocardiográficas, ecocardiográficas y factores de riesgo cardiovasculares de los pacientes con diagnóstico de insuficiencia cardíaca crónica (ICC) con y sin presencia de diagnóstico probable de depresión. Evaluar la asociación existente entre presencia de depresión y mal pronóstico en pacientes con insuficiencia cardíaca crónica sistólica y/o diastólica. Material y métodos. Se realizó un estudio de cohorte prospectivo en 80 pacientes con diagnóstico de ICC. La evaluación psicológica se realizó con el test de la Organización Mundial de la Salud (OMS) para determinar probabilidad de depresión. Se evaluaron parámetros de laboratorio, clínicos y electrocardiográficos. Se realizó ecocardiograma (modo M y bidimensional) al momento del ingreso al servicio y se consideró tanto la insuficiencia cardíaca sistólica y/o diastólica. Resultados. Se incluyeron 80 pacientes, 38 pacientes con diagnóstico probable de depresión y 42 sin diagnóstico probable de depresión con una edad promedio de 59,53 ± 12,34 vs 66,88 ± 15,67 años, respectivamente; el 49% de sexo femenino. La depresión se asoció significativamente con la edad (59,53 ± 12,34 años vs 66,88 ± 15,67 años; p=0,01), con la presión arterial diastólica (78,82 ± 11,36 mm Hg vs 80,00 ± 11,09 mm Hg; p=0,01), con la presión arterial sistólica (124,08 ± 18,74 mm Hg vs 127,50 ± 14,63 mm Hg; p=0,01), con la frecuencia cardíaca (71,74 ± 10,77 lpm vs 72,85 ± 13,49 lpm; p=0,01), con la creatininemia (11,01 ± 3,42 mg/dL vs 12,63 ± 4,47 mg/ dL; p=0,01), con la natremia (138,82 ± 3,76 mEq/L vs 136,58 ± 3,53 mEq/L; p=0,01), con la hemoglobinemia (13,76 ± 1,56 mg/dL vs 13,01 ± 1,79 mg/dL; p=0,01), con la fracción de eyección del ventrículo izquierdo (56,87 ± 12,69% vs 58,87 ± 12,61%; p=0,01) e infarto agudo de miocardio previo (80,62% vs 54,65%; p=0,01). No se encontró asociación estadísticamente significativa en tipo de IC, clase funcional (según New York Heart Association), en hospitalizaciones y en mortalidad de la población. Conclusión. Aunque la prevalencia de depresión en pacientes con insuficiencia cardíaca tanto sistólica como diastólica es alta, aun serán necesarias nuevas investigaciones y estudios randomizados para completar los conocimientos y detectar tempranamente esta comorbilidad cuyo efecto potencial es negativo en los pacientes con insuficiencia cardíaca.
Depression and its relation to prognosis in patients with heart failure Introduction. Depression has a strong link in patients with heart failure, influencing its morbidity, mortality and treatment. Objectives. To describe the clinical, laboratory, electrocardiographic, echocardiographic and cardiovascular risk factors of patients with chronic heart failure (CHF) with and without a probable diagnosis of depression. To evaluate the association between the presence of depression and poor prognosis in patients with chronic systolic and/or diastolic heart failure. Material and methods. A prospective cohort study was conducted in 80 patients with a diagnosis of CHF. The psychological evaluation was performed with the World Health Organization (WHO) test to determine probability of depression. Laboratory, clinical and electrocardiographic parameters were evaluated. Echocardiogram (M-mode and two-dimensional) was performed at the time of admission and both systolic and/or diastolic heart failure were considered. Results. We included 80 patients, 38 patients with probable diagnosis of depression and 42 without probable diagnosis of depression with an average age of 59.53 ± 12.34 vs 66.88 ± 15.67 years, respectively; 49% female. Depression was significantly associated with age (59.53 ± 12.34 years vs 66.88 ± 15.67 years, p=0.01), with diastolic blood pressure (78.82 ± 11.36 mm Hg vs 80.00 ± 11.09 mm Hg, p=0.01), with systolic blood pressure (124.08 ± 18.74 mm Hg vs 127.50 ± 14.63 mm Hg, p=0.01), with heart rate (71.74 ± 10.77 bpm vs 72.85 ± 13.49 bpm, p=0.01), with creatininemia (11.01 ± 3.42 mg/dL vs 12.63 ± 4,47 mg/dL; p=0.01), with natremia (138.82± 3.76 mEq/L vs 136.58 ± 3.53 mEq/L; p = 0.01), with hemoglobin levels (13.76 ± 1.56 mg/dL vs 13.01 ± 1.79 mg/dL, p=0.01), with the ejection fraction of the left ventricle (56.87 ± 12.69% vs 58.87 ± 12.61%, p=0.01) and previous acute myocardial infarction (80.62% vs 54.65%, p=0.01). No statistically significant association was found in type of HF, functional class (according to the New York Heart Association), in hospitalizations and mortality of the population. Conclusion. Although the prevalence of depression in patients with both systolic and diastolic heart failure is high, further investigations and randomized studies will be necessary to complete the knowledge and to detect this co-morbidity early, whose potential effect is negative in patients with heart failure.
Depressão e sua relação com o prognóstico em pacientes com insuficiência cardíaca Introdução. A depressão tem um forte vínculo em pacientes com insuficiência cardíaca, influenciando sua morbidade, mortalidade e tratamento. Objetivos. Descrever os fatores de risco clínicos, laboratoriais, eletrocardiográficos, ecocardiográficos e cardiovasculares de pacientes com insuficiência cardíaca crônica (ICC) com e sem diagnóstico provável de depressão. Avaliar a associação entre a presença de depressão e mau prognóstico em pacientes com insuficiência cardíaca crônica sistólica e/ou diastólica. Material e métodos. Um estudo prospectivo de coorte foi realizado em 80 pacientes com diagnóstico de ICC. A avaliação psicológica foi realizada com o teste da Organização Mundial de Saúde (OMS) para determinar a probabilidade de depressão. Os parâmetros laboratoriais, clínicos e eletrocardiográficos foram avaliados. O ecocardiograma (modo M e bidimensional) foi realizado no momento da admissão e foi considerada a insuficiência cardíaca sistólica e/ou diastólica. Resultados. Foram incluídos 80 pacientes, 38 pacientes com provável diagnóstico de depressão e 42 sem diagnóstico provável de depressão com idade média de 59,53 ± 12,34 vs 66,88 ± 15,67 anos, respectivamente; 49% feminino. A depressão foi significativamente associada à idade (59,53 ± 12,34 anos vs 66,88 ± 15,67 anos; p=0,01), com pressão arterial diastólica (78,82 ± 11,36 mm Hg vs 80,00 ± 11,09 mm Hg; p=0,01), com pressão arterial sistólica (124,08 ± 18,74 mm Hg vs 127,50 ± 14,63 mm Hg; p=0,01), com frequência cardíaca (71,74 ± 10,77 bpm vs 72,85 ± 13,49 bpm; p=0,01), com creatininemia (11,01 ± 3,42 mg/dL vs 12,63 ± 4,47 mg/dL; p=0,01), com natremia (138,82 ± 3,76 mEq/L vs 136,58 ± 3,53 mEq/L; p=0,01), com hemoglobinemia (13,76 ± 1,56 mg/dL vs 13,01 ± 1,79 mg/dL; p=0,01), com a fração de ejeção do ventrículo esquerdo (56,87 ± 12,69% vs 58,87 ± 12,61%; p=0,01) e infarto agudo do miocárdio prévio (80,62% vs 54,65%; p=0,01). Não foi encontrada associação estatisticamente significativa no tipo de ICC, classe funcional (de acordo com a New York Heart Association), nas internações e na mortalidade da população. Conclusão. Embora a prevalência de depressão em pacientes com insuficiência cardíaca sistólica e diastólica seja alta, novas investigações e estudos randomizados serão necessários para completar o conhecimento e detectar precocemente esta comorbidade, cujo efeito potencial é negativo em pacientes com insuficiência cardíaca.
