Search

PURPOSE: Treatment of non–muscle-invasive bladder cancer (NMIBC) is guided by risk stratification using clinical and pathologic criteria. This study aimed to develop a natural language processing (NLP) model for identifying patients with high-risk NMIBC retrospectively from unstructured electronic medical records (EMRs) and to apply the model to describe patient and tumor characteristics. METHODS: We used three independent EMR-derived data sets including adult patients with a bladder cancer diagnosis in 2011-2020 for NLP model development and training (n = 140), validation (n = 697), and application for the retrospective cohort analysis (n = 4,402). Deep learning methods were used to train NLP recognition of medical chart terminology to identify seven high-risk NMIBC criteria; model performance was assessed using the F1 score, weighted across features. An algorithm was then used to classify each patient as high-risk NMIBC (yes/no). Manually reviewed records served as the gold standard. RESULTS: The F1 scores after model training were >0.7 for all but one uncommon feature (prostatic urethral involvement). The highest area under the receiver operating curves (AUC) was observed for Ta (0.897) and T1 (0.897); the lowest AUC was for carcinoma in situ (CIS; 0.617). For high-risk NMIBC classification, positive predictive value was 79.4%, negative predictive value was 93.2%, and false-positive rate was 8.9%. Sensitivity and specificity were 83.7% and 91.1%, respectively. Of 748 patients manually confirmed as having high-risk NMIBC, 196 (26%) had CIS (of whom 19% also had T1 and 23% also had Ta disease); 552 tumors (74%) had no associated CIS. CONCLUSION: The NLP model, combined with a rule-based algorithm, identified high-risk NMIBC with good performance and will enable future work to study real-world treatment patterns and clinical outcomes for high-risk NMIBC. [ABSTRACT FROM AUTHOR]

Introduction Innovative care delivery programs that support primary care providers are needed to reduce the burden of cardiovascular disease (CVD). HeartBeat Connections (HBC) is a primary prevention telemedicine program utilizing registered dietitian nutritionists (RDNs) and registered nurses (RNs) to deliver health coaching and medication therapy protocols for dyslipidaemia and hypertension among patients at high risk for developing CVD. Methods This retrospective cohort study documents the reach and six-month effectiveness of the HBC program for improving CVD risk factors. The sample included 1028 high-risk individuals aged 40-79 (without CVD or diabetes) served between 2010 and 2013 (326 participants, 702 eligible non-participants). Mixed-model analyses of variance were used to compare changes in outcome measures between baseline and six-month follow-up for participants and non-participants. Outcomes were also examined for three groups: non-participants, participants with 1-4 encounters, and participants with > 5 encounters. Results Nearly one-third of all eligible patients participated. There were no significant differences over time between HBC participants and non-participants in blood pressure or body mass. A higher proportion of HBC participants quit using tobacco (7.0 vs. 3.2%, p = 0.004) and achieved the low-density lipoprotein (LDL) program goal of < 100 mg/dL (8.9 vs. -1.1%, p = 0.009). Also, more favourable improvements in total and LDL cholesterol were observed among HBC participants with higher program engagement ( p < 0.05). Discussion The HBC telemedicine program resulted in significant improvement in some, but not all, CVD risk factors over six months. HBC reached many high-CVD-risk patients in the target region, which may confer population-level health benefits if this program can be scaled and sustained. Innovative, collaborative care delivery models like HBC can serve as a platform to systematically target and proactively engage at-risk populations, perhaps reducing patients' CVD risk. [ABSTRACT FROM AUTHOR]

Background: Despite a highly recognized priority for public health and healthcare to implement population-level strategies to reduce the burden of cardiovascular disease (CVD), limited evidence exists on the most effective strategies. Data collection and evaluation of large scale, community based-prevention programs can be challenging and costly to achieve. The Heart of New Ulm (HONU) Project, begun in 2009, is a population-based initiative with healthcare, community, and workplace interventions addressing multiple levels of the social-ecological model designed to reduce modifiable CVD risk factors in rural New Ulm, MN. The community is served by one health system, enabling the use of electronic health record (EHR) data for surveillance. Objective: To assess trends for CVD risk factors, events, and healthcare utilization for New Ulm residents compared to a matched control population. Methods: We matched New Ulm residents (n = 4,077) with controls (n = 4,077) from a regional community served by the same health system using refined covariate balance techniques to match on baseline demographics, CVD risk factors, and health care utilization. Mixed effects longitudinal models with adjustment for age and gender, and an interaction for time by community, were run. Model based estimates were constructed for the entire cohort at each time period. Results: Over the first 6 years of the HONU Project, blood pressure, LDL, total cholesterol, and triglycerides were managed better in New Ulm than the matched comparison community. The proportion of New Ulm residents with controlled blood pressure increased by 6.2 percentage points while the control group increased by 2 points. 10-year ASCVD risk scores showed less decline for New Ulm residents than controls (16 vs. 18.4). The intervention and control groups did not differ with regard to inpatient stays, CVD events, smoking, or glucose. Conclusions: Compared to a matched control population, we found improved control of CVD risk factors in the New Ulm Population exposed to the HONU Project. [ABSTRACT FROM AUTHOR]

Background: Increased operative time in colorectal surgery is associated with worse surgical outcomes. Laparoscopic and robotic operations have improved outcomes, despite longer operative times. Furthermore, the definition of "prolonged" operative time has not been consistently defined., Objective: The first objective was to define prolonged operative time across multiple colorectal operations and surgical approaches. The second was to describe the impact of prolonged operative time on length of stay and short-term outcomes., Design: A retrospective cohort study., Setting: Forty-two hospitals in the Surgical Care Outcomes Assessment Program from 2011 to 2019., Patients: There were a total of 23,098 adult patients (age 18 years or older) undergoing 6 common, elective colorectal operations: right colectomy, left/sigmoid colectomy, total colectomy, low anterior resection, IPAA, or abdominoperineal resection., Main Outcome Measures: Prolonged operative time defined as the 75th quartile of operative times for each operation and approach. Outcomes were length of stay, discharge home, and complications. Adjusted models were used to account for factors that could impact operative time and outcomes across the strata of open and minimally invasive approaches., Results: Prolonged operative time was associated with longer median length of stay (7 vs 5 days open, 5 vs 4 days laparoscopic, 4 vs 3 days robotic) and more frequent complications (42% vs 28% open, 24% vs 17% laparoscopic, 27% vs 13% robotic) but similar discharge home (86% vs 87% open, 94% vs 94% laparoscopic, 93% vs 96% robotic). After adjustment, each additional hour of operative time above the median for a given operation was associated with 1.08 (1.06-1.09) relative risk of longer length of stay for open operations and 1.07 (1.06-1.09) relative risk for minimally invasive operations., Limitations: Our study was limited by being retrospective, resulting in selection bias, possible confounders for prolonged operative time, and lack of statistical power for subgroup analyses., Conclusions: Operative time has consistent overlap across surgical approaches. Prolonged operative time is associated with longer length of stay and higher probability of complications, but this negative effect is diminished with minimally invasive approaches. See Video Abstract ., El Impacto Del Tiempo Operatorio Prolongado Asociado Con La Ciruga Colorrectal Mnimamente Invasiva Un Informe Del Programa De Evaluacin De Resultados De Atencin Quirrgica: ANTECEDENTES:El aumento del tiempo operatorio en la cirugía colorrectal se asocia con peores resultados quirúrgicos. Las operaciones laparoscópicas y robóticas han mejorado los resultados, a pesar de los tiempos operatorios más prolongados. Además, la definición de tiempo operatorio "prolongado" no se ha definido de manera consistente.OBJETIVO:Primero, definir el tiempo operatorio prolongado a través de múltiples operaciones colorrectales y enfoques quirúrgicos. En segundo lugar, describir el impacto del tiempo operatorio prolongado sobre la duración de la estancia y los resultados a corto plazo.DISEÑO:Estudio de cohorte retrospectivo.ESCENARIO:42 hospitales en el Programa de Evaluación de Resultados de Atención Quirúrgica de 2011-2019.PACIENTES:23 098 pacientes adultos (de 18 años de edad y mayores), que se sometieron a seis operaciones colorrectales electivas comunes: colectomía derecha, colectomía izquierda/sigmoidea, colectomía total, resección anterior baja, anastomosis ileoanal con bolsa o resección abdominoperineal.PRINCIPALES MEDIDAS DE RESULTADO:Tiempo operatorio prolongado definido como el cuartil 75 de tiempos operatorios para cada operación y abordaje. Los resultados fueron la duración de la estancia hospitalaria, el alta domiciliaria y las complicaciones. Se usaron modelos ajustados para tener en cuenta los factores que podrían afectar tanto el tiempo operatorio como los resultados en los estratos de abordajes abiertos y mínimamente invasivos.RESULTADOS:El tiempo operatorio prolongado se asoció con una estancia media más prolongada (7 vs. 5 días abiertos, 5 vs. 4 días laparoscópicos, 4 vs. 3 días robóticos), complicaciones más frecuentes (42 % vs. 28 % abiertos, 24 % vs. 17 % laparoscópica, 27% vs. 13% robótica), pero similar alta domiciliaria (86% vs. 87% abierta, 94% vs. 94% laparoscópica, 93% vs. 96% robótica). Después del ajuste, cada hora adicional de tiempo operatorio por encima de la mediana para una operación determinada se asoció con un riesgo relativo de 1,08 (1,06, 1,09) de estancia hospitalaria más larga para operaciones abiertas y un riesgo relativo de 1,07 (1,06, 1,09) para operaciones mínimamente invasivas.LIMITACIONES:Nuestro estudio estuvo limitado por ser retrospectivo, lo que resultó en un sesgo de selección, posibles factores de confusión por un tiempo operatorio prolongado y falta de poder estadístico para los análisis de subgrupos.CONCLUSIONES:El tiempo operatorio tiene una superposición constante entre los enfoques quirúrgicos. El tiempo operatorio prolongado se asocia con una estadía más prolongada y una mayor probabilidad de complicaciones, pero este efecto negativo disminuye con los enfoques mínimamente invasivos. ( Traducción-Dr. Mauricio Santamaria )., (Copyright © The ASCRS 2023.)