Abstract
The severe acute respiratory syndrome (SARS-CoV-2) pandemic and high hospitalization rates placed a tremendous strain on hospital resources, necessitating the use of models to predict ...hospital volumes and the associated resource requirements. Complex epidemiologic models have been developed and published, but many require continued adjustment of input parameters. We developed a simplified model for short-term bed need predictions that self-adjusts to changing patterns of disease in the community and admission rates. The model utilizes public health data on community new case counts for SARS-CoV-2 and projects anticipated hospitalization rates. The model was retrospectively evaluated after the second wave of SARS-CoV-2 in New York, New York (October 2020–April 2021) for its accuracy in predicting numbers of coronavirus disease 2019 (COVID-19) admissions 3, 5, 7, and 10 days into the future, comparing predicted admissions with actual admissions for each day at a large integrated health-care delivery network. The mean absolute percent error of the model was found to be low when evaluated across the entire health system, for a single region of the health system or for a single large hospital (6.1%–7.6% for 3-day predictions, 9.2%–10.4% for 5-day predictions, 12.4%–13.2% for 7-day predictions, and 17.1%–17.8% for 10-day predictions).
Background
Non-arrivals to scheduled ambulatory visits are common and lead to a discontinuity of care, poor health outcomes, and increased subsequent healthcare utilization. Reducing non-arrivals is ...important given their association with poorer health outcomes and cost to health systems.
Objective
To develop and validate a prediction model for ambulatory non-arrivals.
Design
Retrospective cohort study.
Patients or Subjects
Patients at an integrated health system who had an outpatient visit scheduled from January 1, 2020, to February 28, 2022.
Main Measures
Non-arrivals to scheduled appointments.
Key Results
There were over 4.3 million ambulatory appointments from 1.2 million adult patients. Patients with appointment non-arrivals were more likely to be single, racial/ethnic minorities, and not having an established primary care provider compared to those who arrived at their appointments. A prediction model using the XGBoost machine learning algorithm had the highest AUC value (0.768 0.767–0.770). Using SHAP values, the most impactful features in the model include rescheduled appointments, lead time (number of days from scheduled to appointment date), appointment provider, number of days since last appointment with the same department, and a patient’s prior appointment status within the same department. Scheduling visits close to an appointment date is predicted to be less likely to result in a non-arrival. Overall, the prediction model calibrated well for each department, especially over the operationally relevant probability range of 0 to 40%. Departments with fewer observations and lower non-arrival rates generally had a worse calibration.
Conclusions
Using a machine learning algorithm, we developed a prediction model for non-arrivals to scheduled ambulatory appointments usable for all medical specialties. The proposed prediction model can be deployed within an electronic health system or integrated into other dashboards to reduce non-arrivals. Future work will focus on the implementation and application of the model to reduce non-arrivals.
Improving the patient experience has become an essential component of any healthcare system's performance metrics portfolio. In this study, we developed a machine learning model to predict a ...patient's response to the Hospital Consumer Assessment of Healthcare Providers and Systems survey's "Doctor Communications" domain questions while simultaneously identifying most impactful providers in a network.
This is an observational study of patients admitted to a single tertiary care hospital between 2016 and 2020. Using machine learning algorithms, electronic health record data were used to predict patient responses to Hospital Consumer Assessment of Healthcare Providers and Systems survey questions in the doctor domain, and patients who are at risk for responding negatively were identified. Model performance was assessed by area under receiver-operating characteristic curve. Social network analysis metrics were also used to identify providers most impactful to patient experience.
Using a random forest algorithm, patients' responses to the following 3 questions were predicted: "During this hospital stay how often did doctors. 1) treat you with courtesy and respect? 2) explain things in a way that you could understand? 3) listen carefully to you?" with areas under the receiver-operating characteristic curve of 0.876, 0.819, and 0.819, respectively. Social network analysis found that doctors with higher centrality appear to have an outsized influence on patient experience, as measured by rank in the random forest model in the doctor domain.
A machine learning algorithm identified patients at risk of a negative experience. Furthermore, a doctor social network framework provides metrics for identifying those providers that are most influential on the patient experience.
Background
Post-hospital discharge follow-up appointments are intended to evaluate patients’ recovery following a hospitalization, but it is unclear how appointment statuses are associated with ...readmissions.
Objective
To examine the association between post-discharge ambulatory follow-up status, (1) having a scheduled appointment and (2) arriving to said appointment, and 30-day readmission.
Design and Setting
A retrospective cohort study of patients hospitalized at 12 hospitals in an Integrated Delivery Network and their ambulatory appointments in that same network.
Patients and Main Measures
We included 50,772 patients who had an ambulatory appointment within 18 months of an inpatient admission in 2018. Primary outcome was readmission within 30 days post-discharge.
Key Results
There were 32,108 (63.2%) patients with scheduled follow-up appointments and 18,664 (36.8%) patients with no follow-up; 28,313 (88.2%) patients arrived, 3149 (9.8%) missed, and 646 (2.0%) were readmitted prior to their scheduled appointments. Overall 30-day readmission rate was 7.3%; 6.0% 5.75–6.31 for those who arrived, 8.8% 8.44–9.25 for those without follow-up, and 10.3% 9.28–11.40 for those who missed a scheduled appointment (
p
< 0.001). After adjusting for covariates, patients who arrived at their appointment in the first week following discharge were significantly less likely to be readmitted than those not having any follow-up scheduled (medical adjusted hazard ratio (aHR) 0.57 0.47–0.69,
p
< 0.001; surgical aHR 0.58 0.44–0.75,
p
< 0.001) There was an increased risk at weeks 3 and 4 for medical patients who arrived at a follow-up compared to those with no follow-up scheduled (week 3 aHR 1.29 1.10–1.51,
p
= 0.001; week 4 aHR 1.46 1.26–1.70,
p
< 0.001).
Conclusions
The benefit of patients arriving to their post-discharge appointments compared with patients who missed their follow-up visits or had no follow-up scheduled, is only significant during first week post-discharge, suggesting that coordination within 1 week of discharge is critical in reducing 30-day readmissions.
Impaired sleep for hospital patients is an all too common reality. Sleep disruptions due to unnecessary overnight vital sign monitoring are associated with delirium, cognitive impairment, weakened ...immunity, hypertension, increased stress, and mortality. It is also one of the most common complaints of hospital patients while imposing additional burdens on healthcare providers. Previous efforts to forgo overnight vital sign measurements and improve patient sleep used providers' subjective stability assessment or utilized an expanded, thus harder to retrieve, set of vitals and laboratory results to predict overnight clinical risk. Here, we present a model that incorporates past values of a small set of vital signs and predicts overnight stability for any given patient-night. Using data obtained from a multi-hospital health system between 2012 and 2019, a recurrent deep neural network was trained and evaluated using ~2.3 million admissions and 26 million vital sign assessments. The algorithm is agnostic to patient location, condition, and demographics, and relies only on sequences of five vital sign measurements, a calculated Modified Early Warning Score, and patient age. We achieved an area under the receiver operating characteristic curve of 0.966 (95% confidence interval CI 0.956-0.967) on the retrospective testing set, and 0.971 (95% CI 0.965-0.974) on the prospective set to predict overnight patient stability. The model enables safe avoidance of overnight monitoring for ~50% of patient-nights, while only misclassifying 2 out of 10,000 patient-nights as stable. Our approach is straightforward to deploy, only requires regularly obtained vital signs, and delivers easily actionable clinical predictions for a peaceful sleep in hospitals.
Recurrence of solid tumors renders patients vulnerable to advanced, treatment-refractory disease state with mutational and oncogenic landscape distinctive from initial diagnosis. Improving outcomes ...for recurrent cancers requires a better understanding of cell populations that expand from the post-therapy, minimal residual disease (MRD) state. We profile barcoded tumor stem cell populations through therapy at tumor initiation, MRD, and recurrence in our therapy-adapted, patient-derived xenograft models of glioblastoma (GBM). Tumors show distinct patterns of recurrence in which clonal populations exhibit either a pre-existing fitness advantage or an equipotency fitness acquired through therapy. Characterization of the MRD state by single-cell and bulk RNA sequencing reveals a tumor-intrinsic immunomodulatory signature with prognostic significance at the transcriptomic level and in proteomic analysis of cerebrospinal fluid (CSF) collected from patients with GBM. Our results provide insight into the innate and therapy-driven dynamics of human GBM and the prognostic value of interrogating the MRD state in solid cancers.
Display omitted
•Therapy-adapted model allows for temporal profiling of glioblastoma (GBM) recurrence•GBM recurrence arises from pre-existing or therapy-driven clonal populations•Post-therapy minimal residual disease (MRD) state is identified and characterized•MRD-derived tumor-intrinsic immunomodulatory signature is prognostic for survival
Using a therapy-adapted model and cellular barcoding, Qazi et al. show that glioblastoma recurrence arises from clonal populations that have pre-existing or therapy-driven fitness advantage. Further characterization of the post-therapy minimal residual disease state identifies a tumor-intrinsic immunomodulatory signature that is prognostic for glioblastoma survival.
Abstract
Delivering clinical decision support (CDS) at the point of care has long been considered a major advantage of computerized physician order entry (CPOE). Despite the widespread implementation ...of CPOE, medication ordering errors and associated adverse events still occur at an unacceptable level. Previous attempts at indication- and kidney function-based dosing have mostly employed intrusive CDS, including interruptive alerts with poor usability. This descriptive work describes the design, development, and deployment of the Adult Dosing Methodology (ADM) module, a novel CDS tool that provides indication- and kidney-based dosing at the time of order entry. Inclusion of several antimicrobials in the initial set of medications allowed for the additional goal of optimizing therapy duration for appropriate antimicrobial stewardship. The CDS aims to decrease order entry errors and burden on providers by offering automatic dose and frequency recommendations, integration within the native electronic health record, and reasonable knowledge maintenance requirements. Following implementation, early utilization demonstrated high acceptance of automated recommendations, with up to 96% of provided automated recommendations accepted by users.
Proinflammatory mediators have been implicated in the pathogenesis of systemic inflammatory response syndrome and multiorgan system dysfunction. These mediators are of molecular weights that render ...them amenable to clearance by the hemodiafiltration mode of continuous renal replacement therapy.
To determine whether a period of 48 hrs of continuous renal replacement therapy in patients with multiorgan system dysfunction secondary to systemic inflammatory response syndrome improves their degree of anasarca as well as their cardiovascular and respiratory systems performances.
Retrospective chart review.
Charts of patients diagnosed with systemic inflammatory response syndrome, who were mechanically ventilated in the pediatric intensive care unit and at the same time were receiving continuous renal replacement therapy, from 2004 to 2008, were reviewed. Patients with preexisting renal failure and/or received extracorporeal membrane oxygenation were excluded. Changes in the patients' body weights, oxygenation indices, and vasopressor scores were used as markers for responsiveness to continuous renal replacement therapy. DATA ANALYSIS AND MAIN RESULTS: Data from twenty-two patients with systemic inflammatory response syndrome and with three to five concomitantly diagnosed organ system dysfunctions, at the time continuous renal replacement therapy was initiated, were analyzed. None of the six patients who had five organ system dysfunctions survived to be discharged from the pediatric intensive care unit. Of the remaining 16 patients with three or four organ system dysfunctions, eight (50%) survived and eight (50%) died. The patients' weight, oxygenation indices, and vasopressor scores did not significantly change with 48 hrs of continuous renal replacement therapy.
Mechanically ventilated patients with systemic inflammatory response syndrome and multiorgan system dysfunction demonstrated a precarious and insignificant response to 48 hrs of continuous renal replacement therapy in a hemodiafiltration mode. However, the patients' overall clinical status did not deteriorate during this therapy. More prospective studies are necessary to determine the effectiveness of continuous renal replacement therapy in patients with multiorgan system dysfunction.
The flow in the human trachea is turbulent. Thus, the tracheal resistance (R) and the pressure gradient (ΔP) required to maintain a given flow across the trachea is inversely related to its radius ...raised to the fifth power. If the caliber reduction ratio (X) after endotracheal intubation is calculated as X = radius of the endotracheal tube (rETT)/radius of the trachea (rT), then ΔP and/or R will be increased by (1/X)5.
To measure the actual ratio between rETT and rT following endotracheal intubation of pediatric patients with respiratory failure and to calculate the resulting increase in the tracheal R and ΔP for a given inspiratory flow rate.
Retrospective chart review.
Pediatric ICU in a tertiary-care teaching children's medical center.
Twenty consecutive pediatric patients (mean ± SD age, 6.4 ± 7.2 years) whose tracheas had been intubated for various causes of respiratory failure, and who had received a CT scan, were included in our study. All patients received an endotracheal tube the size of which was derived from the following formula: (age in years/4) + 4.
rT and rETT were measured from CT scan sections at and around the level of the thoracic inlet, and the average values were used to calculate X. These values ranged from 0.33 to 0.65 (mean, 0.55 ± 0.8). The factor (1/X)5 was calculated for each patient and then was multiplied by the known normal value for tracheal R for adolescents and adults (0.07 cm H2O/L/s) to obtain the value of R resulting from the artificial airway, (1/X)5 × 0.07. Our results showed that tracheal R increased due to caliber reduction of the trachea after endotracheal intubation by 33.9 ± 52.5-fold (range, 8.6- to 255.5-fold). In order to maintain an inspiratory flow of 1 L/s, the value of P for the intubated trachea would increase from 0.07 cm H2O to a mean of 2.4 ± 3.7 cm H2O (range, 0.6 to 18 cm H2O). In two of our patients, the rT/rETT ratios were < 0.5 (0.33 and 0.44, respectively); this translated into a more significant increase in the calculated ΔPs, 18 and 4.2 cm H2O, respectively.
The common value of X due to endotracheal intubation is between 0.5 and 0.6, which in and of itself results in an increase in R across the intubated trachea up to 32-fold. The calculated increase in P as a result of this is between 2 and 3 cm H2O for adolescents or young adults. The addition of pressure support of at least 3 cm H2O during spontaneous ventilation via an endotracheal tube, which is common practice in pediatric critical care, should alleviate any respiratory distress emanating from the increased R. However, a value for X < 0.5, which was found in 10% of our patients (2 of 20 patients), results in a much higher calculated increase in the pressure gradient and, therefore, a higher level of pressure support is required to overcome this increase.