Clinician Assessment Research Articles

Claims-Based Algorithm to Identify Pre-Exposure Prophylaxis Indications for Tenofovir Disoproxil Fumarate and Emtricitabine Prescriptions (2012-2014): Validation Study.

To monitor the use of tenofovir disoproxil fumarate and emtricitabine (TDF/FTC) and related medicines for pre-exposure prophylaxis (PrEP) as HIV prevention using commercial pharmacy data, it is necessary to determine whether TDF/FTC prescriptions are used for PrEP or for some other clinical indication. This study aimed to validate an algorithm to distinguish the use of TDF/FTC for HIV prevention or infectious disease treatment. An algorithm was developed to identify whether TDF/FTC prescriptions were for PrEP or for other indications from large-scale administrative databases. The algorithm identifies TDF/FTC prescriptions and then excludes patients with International Classification of Diseases (ICD)-9 diagnostic codes, medications, or procedures that suggest indications other than for PrEP (eg, documentation of HIV infection, chronic hepatitis B, or use of TDF/FTC for postexposure prophylaxis). For evaluation, we collected data by clinician assessment of medical records for patients with TDF/FTC prescriptions and compared the assessed indication identified by the clinician review with the assessed indication identified by the algorithm. The algorithm was then applied and evaluated in a large, urban, community-based sexual health clinic. The PrEP algorithm demonstrated high sensitivity and moderate specificity (99.6% and 49.6%) in the electronic medical record database and high sensitivity and specificity (99% and 87%) in data from the urban community health clinic. The PrEP algorithm classified the indication for PrEP in most patients treated with TDF/FTC with sufficient accuracy to be useful for surveillance purposes. The methods described can serve as a basis for developing a robust and evolving case definition for antiretroviral prescriptions for HIV prevention purposes.

Bayesian additive regression trees for predicting childhood asthma in the CHILD cohort study

BackgroundAsthma is a heterogeneous disease that affects millions of children and adults. There is a lack of objective gold standard diagnosis that spans the ages; instead, diagnoses are made by clinician assessment based on a cluster of signs, symptoms and objective tests dependent on age. Yet, there is a clear morbidity associated with chronic asthma symptoms. Machine learning has become a popular tool to improve asthma diagnosis and classification. There is a paucity of literature on the use of Bayesian machine learning algorithms to predict asthma diagnosis in children. This paper develops a prediction model using the Bayesian additive regression trees (BART) and compares its performance to various machine learning algorithms in predicting the diagnosis of childhood asthma.MethodsClinically relevant variables collected at or before 3 years of age from 2794 participants in the CHILD Cohort Study were used to predict physician-diagnosed asthma at age 5. BART and six other commonly used machine learning algorithms, namely adaptive boosting, logistic regression, decision tree, neural network, random forest, and support vector machine were trained. Measures of performance including sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve were calculated. The confidence intervals were calculated using Bootstrapping samples. Important predictors and interaction effects associated with asthma were also identified using BART.ResultsBART, logistic regression and random forest showed the highest area under the ROC curve compared to other machine learning algorithms. Based on BART, recurrent wheeze, respiratory infection and food sensitization at 3 years of age were the most important predictors. The three most important interaction effects were found to be interaction terms of respiratory infection at 3 years and recurrent wheezing at 3 years, maternal asthma and paternal asthma, and maternal wheezing and inhalant sensitization of child at 3 years.ConclusionsBART demonstrated promising prediction performance when compared to other machine learning algorithms. Future research could validate the BART in an external cohort to evaluate its reliability and generalizability.

Effect of early tranexamic acid treatment on fatigue in patients with mild traumatic brain injury: data from the CRASH-3 clinical trial

Background Each year world-wide about 65 million people sustain a mild traumatic brain injury (mTBI). Fatigue is a common and distressing symptom after mTBI. We examine the effect of tranexamic acid (TXA) on fatigue in patients with mTBI using data from the CRASH-3 trial. Methods The CRASH-3 trial randomised 9,202 patients with traumatic brain injury and no significant extracranial bleeding to receive TXA or placebo within 3 hours of injury. The primary outcome was death from head injury within 28 days of injury. The methods and results are presented elsewhere. Fatigue was recorded as “None”, “Moderate” or “Extreme.” This study examines the effect of TXA on extreme fatigue in the 2,632 patients with mTBI (Glasgow Coma Scale [GCS] score≥13). Our analyses were not prespecified. Results Our study primary outcome, extreme fatigue, was reported for 10 (0.8%) of 1,328 patients receiving TXA and 19 (1.5%) of 1,288 patients receiving placebo (risk ratio [RR]=0.51, 95% confidence interval [CI] 0.24-1.09). Death within 28 days of injury was reported for 34 (2.6%) of 1,328 patients receiving TXA versus 47 (3.6%) of 1,288 patients receiving placebo (RR=0.70, 95% CI 0.45-1.08). Among patients allocated to TXA, 44 (3.3%) patients either died or reported extreme fatigue versus 66 (5.1%) patients among those allocated to placebo (RR=0.65, 95% CI 0.44-0.94). This composite outcome is disproportionately influenced by deaths which account for 74% (81 from 110) of events. Conclusions We found no evidence that tranexamic acid reduces fatigue in patients with mTBI. Given, 1) our analyses were not prespecified, 2) our outcome measure is not based on a validated fatigue severity scale, and 3) TBI patients can suffer from hospital-induced delirium, which hinders clinician assessment, these results need to be replicated in another study. Registration ISRCTN (ISRCTN15088122, 19/07/2011), ClinicalTrials.gov (NCT01402882, 26/07/2011), EudraCT (2011-003669-14, 25/07/2011), Pan African Clinical Trial Registry (PACTR20121000441277, 30/10/2012).

Clinician assessment of kidney function from plasma creatinine values during critical illness: A scenario-based international multi-professional survey

PurposeDuring critical illness interpretation of serum creatinine is affected by non-steady state conditions, reduced creatinine generation, and altered distribution. We evaluated healthcare professionals' ability to adjudicate underlying kidney function, based on simulated creatinine values. MethodsWe developed an online survey, incorporating 12 scenarios with simulated trajectories of creatinine based on profiles of muscle mass, GFR and fluid balance using bespoke kinetic modelling. Participants predicted true underlying GFR (<5, 5–14, 15–29, 30–44, 45–59, 60–90, >90 ml.min−1.1.73 m−2) and AKI stage (stages 1–3, defined as 33 %, 50 %, 66 % decrease in GFR from baseline) during the first 7-days and at ICU discharge. Results100 of 103 respondents from 16 countries, 94 completed 1 or more scenarios. 43(43 %) were senior physicians, 74(74 %) critical care and 31(31 %) nephrology physicians. Over the first 7-days, true GFR was correctly estimated 43 % of the time and underlying AKI stage in 57 % of patient days. At ICU discharge GFR was predicted 35 % of the time. At all timepoints, over and under-estimation of GFR was observed. ConclusionParticipants displayed marked variation in estimation of kidney function, suggesting difficulty in accounting for multiple confounders. There is need for alternative, unbiased measures of kidney function in critical illness to avoid misclassifying kidney disease.

Using patient-reported performance status to guide management of advanced cancer: A quality improvement initiative.

379 Background: Performance status is a key prognostic factor among patients with advanced cancer and can inform the need for supportive care services. However, assessment and documentation of performance status is inconsistently integrated into standard oncology care. Patient-reported performance status (PRPS) is a surrogate for clinician-assessed performance status and has the potential to address this challenge. We piloted a decision support tool in our electronic health record (EHR) that uses PRPS to prompt clinician assessment of performance status and suggest referrals to supportive care services. Methods: We identified patients with advanced cancer using a pre-built and validated registry driven by ICD codes in our EHR (EPIC). For patients with advanced cancer seen at one of our clinics, a multiple-choice question with options derived from the Eastern Cooperative Oncology Group (ECOG) scale in patient-friendly language was added to the pre-visit questionnaire sent electronically prior to oncology visits. For patients with a poor PRPS (2 or greater), a clinical decision support tool alerted providers of the patient’s self-reported performance status, encouraged input of the clinician’s ECOG assessment, and suggested referral orders to supportive care services such as palliative care, nutrition, and social work. We are currently evaluating how our PRPS-driven decision support tool impacts the rate of clinician-assessed ECOG documentation, referral rates, and clinical outcomes. Results: Between 3/13/24 and 5/13/24, of 336 patients identified by the advanced cancer registry, 70% (235) of patients completed the PRPS questionnaire. Among patients with an available PRPS score, 18% (42) of patients reported a poor performance status (2 or greater) at least once, triggering the decision support tool. Providers entered ECOG assessments for 93% (39) of patients and sent referrals to supportive care services for 10% (4) of the patients. Three patients died during this time period, and all three of them reported a poor performance status of 3 or 4. Oncologists at the clinic reported no significant disruption to routine workflow. Conclusions: Preliminary results suggest feasibility of a PRPS-driven decision support tool to flag patients with advanced cancer and declining function and improve discrete documentation of clinician-assessed performance status. Notably, the rate of referrals to supportive care services remains low. Next steps include obtaining longitudinal data from this pilot, assessing the impact of the pilot on goals of care documentation, and validating the concordance of PRPS and ECOG and their effect on clinical outcomes. Ultimately, we aim to use the resulting data and harness our dashboard of patients with advanced cancer and poor performance status to develop innovative, automated, and targeted quality improvement interventions.

National assessment of clinicians participating in stroke treatment decisions at strokenet regional coordinating centers: Clinicians Making Stroke Treatment Decisions

ObjectivesSince the introduction of thrombolytics, stroke teams evolved to improve thrombolytic care delivery. The impact of the advent of endovascular therapy on the composition of acute stroke teams is unknown. Materials and MethodsA two-part pilot-tested survey was deployed to site-Principal Investigators (PIs) of the 27 StrokeNet Regional Coordinating Centers (RCCs) regarding institutional acute stroke teams. Part A inquired about the participation of personnel in each type of stroke response. Part B identified stroke team physicians and the types of responses in which they participate to assess training background of stroke team members. ResultsResponse rates for Part A and B were 66% and 48%, respectively. In Part A, 67% (12/18) of sites reported trainees always responded to ED stroke activations with significant autonomy. 44% (7/16) and 27% (4/15) of sites reported NP and PA response to ED stroke alerts, respectively, but with limited autonomy. In Part B, 124 physicians involved in ED stroke alerts were identified, the large majority of whom (79%, 95% CI: 71-85) were vascular neurology trained. The 39 (23%) stroke team members involved in endovascular therapy had the following training: 49% (34-64) neurosurgery, 28% (17-44) radiology, 18% (9-33) vascular neurology 5% (1-16) neurology. ConclusionsWe identified modest heterogeneity in the composition of acute stroke team members across StrokeNet RCCs. Individuals performing endovascular therapy had a variety of clinical specializations, reflecting the evolving multidisciplinary nature of interventional acute stroke care. At StrokeNet RCCs, teams have significant trainee involvement in both ED and inpatient acute stroke responses.

CONNECT: Coordinating Options for Neurovascular Patients Needing Electrophysiology Consults and Treatments

Background and Purpose Though Event Monitors (EM) and Implantable Loop Recorders (ILR) are prevalent in stroke workups, complex processes to obtain placement of these device might result in delays. Our aim was to determine if the CONNECT (Coordinating Options for Neurovascular patients Needing Electrophysiology Consults and Treatments) pathway could improve Stroke-to-Electrophysiology (EP) communications, increase EM and ILR device placements prior to discharge, shorten placement time, and preserve satisfaction. Methods We assessed device placements when an EP consult was obtained [Pre-CONNECT (5/1/21-4/30/22), CONNECT (5/1/22-4/30/23)] for patients with stroke. In the Pre- period, consults were sent via EPIC electronic medical record (EMR), with additional direct communication when desired. In the CONNECT period, the pathway and module allowed for immediate communication between services. Outcomes included case rate, times, length of stay, and satisfaction. Hospital reports detailed Order to Activation (O-A) days. EM report review was used to obtain O-A time. Clinician satisfaction was assessed using Qualtrics survey. Patient satisfaction was assessed with Hospital Consumer Assessment of Health care Clinicians and Systems (HCAHPS) survey. Man-Whitney U test was used. Results 78 patients were included (30EM(38.5%), 48ILR(61.5%)). Age was 68 years ( P = 0.58). For ILRs, inpatient placements prior to discharge increased (3Pre vs 51 CONNECT; P &lt; 0.0001) as did outpatient placements (5 vs 16; P = 0.02). Order to Activation (O-A) time savings were significant for ILR overall (32 days vs 1 day; P = 0.03) and for Inpatient EM (13 days vs 3 days; P = 0.003). Time for consultant to view was 4 min and to respond was 6 min. Devices were placed at a median 6 hrs 32 min (EM: 4 hrs 19 min; ILR:7 hrs36 min). All (12/12) clinicians preferred the technique. Patient satisfaction improved on 13/19 (68%) questions. Conclusions There was a 1600% increase in ILR placements prior to discharge that was associated with the time period that the CONNECT process was in place. The robust improvement in ILR placements prior to discharge, high satisfaction, ease of use, closed loop communication, and respect for autonomy allowing more organic parallel discussions with patients improved clinician workflow which could potentially improve future risk reduction strategies.

Accuracy of Speech Sound Analysis: Comparison of an Automatic Artificial Intelligence Algorithm With Clinician Assessment.

Automatic speech analysis (ASA) and automatic speech recognition systems are increasingly being used in the treatment of speech sound disorders (SSDs). When utilized as a home practice tool or in the absence of the clinician, the ASA system has the potential to facilitate treatment gains. However, the feedback accuracy of such systems varies, a factor that may impact these gains. The current research analyzes the feedback accuracy of a novel ASA algorithm (Amplio Learning Technologies), in comparison to clinician judgments. A total of 3,584 consonant stimuli, produced by 395 American English-speaking children and adolescents with SSDs (age range: 4-18 years), were analyzed with respect to automatic classification of the ASA algorithm, clinician-ASA agreement, and interclinician agreement. Further analysis of results as related to phoneme acquisition categories (early-, middle-, and late-acquired phonemes) was conducted. Agreement between clinicians and ASA classification for sounds produced accurately was above 80% for all phonemes, with some variation based on phoneme acquisition category (early, middle, late). This variation was also noted for ASA classification into "acceptable," "unacceptable," and "unknown" (which means no determination of phoneme accuracy) categories, as well as interclinician agreement. Clinician-ASA agreement was reduced for misarticulated sounds. The initial findings of Amplio's novel algorithm are promising for its potential use within the context of home practice, as it demonstrates high feedback accuracy for correctly produced sounds. Furthermore, complexity of sound influences consistency of perception, both by clinicians and by automated platforms, indicating variable performance of the ASA algorithm across phonemes. Taken together, the ASA algorithm may be effective in facilitating speech sound practice for children with SSDs, even in the absence of the clinician.

Differences in Patient-Reported Outcome Measures in Patients With Cancer Six Months Before Death.

Patient-reported outcome measures (PROMs) provide a direct report of the patient's perspective, complementary to clinician assessment. Currently, understanding the real-time changes in PROM scores near the end of life remains limited. This study evaluated differences in mean PROM scores between patients with cancer within 6 months before death compared with surviving patients with cancer. This retrospective case-control study uses the National Institutes of Health's Patient-Reported Outcomes Measurement Information System computer adaptive testing instruments to assess pain interference, physical function, fatigue, and depression. Patients dying within 6 months of PROM completion were selected as cases and matched to controls 1:3 by age at PROM completion, sex, cancer disease site, and cancer stage at diagnosis. Generalized estimating equation models assessed the difference in mean PROM score in cases compared with controls. A total of 461 cases and 1,270 controls from September 2020 to January 2023 were included. After adjustment for ethnicity, Charlson Comorbidity Index, and census tract median household income, significant differences in mean scores were demonstrated. Physical function domain showed the largest difference, with cases averaging 6.52 points lower than controls (95% CI, -8.25 to -4.80). Fatigue and pain interference domains showed a rise in PROMs scores by 4.83 points (95% CI, 2.94 to 6.72) and 4.33 points (95% CI, 2.53 to 6.12), respectively. Compared with controls, patients dying within 6 months of PROM completion demonstrated worse PROM scores in the four domains assessed. These findings suggest the utility of routinely collected PROMs as a real-time indicator of the terminal stage of life among patients with cancer to allow for earlier intervention with supportive oncology services.

Effect of early tranexamic acid treatment on fatigue in patients with mild traumatic brain injury: data from the CRASH-3 clinical trial.

Each year world-wide about 65 million people sustain a mild traumatic brain injury (mTBI). Fatigue is a common and distressing symptom after mTBI. We examine the effect of tranexamic acid (TXA) on fatigue in patients with mTBI using data from the CRASH-3 trial. The CRASH-3 trial randomised 9,202 patients with traumatic brain injury and no significant extracranial bleeding to receive TXA or placebo within 3 hours of injury. The primary outcome was death from head injury within 28 days of injury. The methods and results are presented elsewhere. Fatigue was recorded as "None", "Moderate" or "Extreme." This study examines the effect of TXA on extreme fatigue in the 2,632 patients with mTBI (Glasgow Coma Scale [GCS] score≥13). Our analyses were not prespecified. Our study primary outcome, extreme fatigue, was reported for 10 (0.8%) of 1,328 patients receiving TXA and 19 (1.5%) of 1,288 patients receiving placebo (risk ratio [RR]=0.51, 95% confidence interval [CI] 0.24-1.09). Death within 28 days of injury was reported for 34 (2.6%) of 1,328 patients receiving TXA versus 47 (3.6%) of 1,288 patients receiving placebo (RR=0.70, 95% CI 0.45-1.08). Among patients allocated to TXA, 44 (3.3%) patients either died or reported extreme fatigue versus 66 (5.1%) patients among those allocated to placebo (RR=0.65, 95% CI 0.44-0.94). This composite outcome is disproportionately influenced by deaths which account for 74% (81 from 110) of events. We found no evidence that tranexamic acid reduces fatigue in patients with mTBI. Given, 1) our analyses were not prespecified, 2) our outcome measure is not based on a validated fatigue severity scale, and 3) TBI patients can suffer from hospital-induced delirium, which hinders clinician assessment, these results need to be replicated in another study. ISRCTN (ISRCTN15088122, 19/07/2011), ClinicalTrials.gov (NCT01402882, 26/07/2011), EudraCT (2011-003669-14, 25/07/2011), Pan African Clinical Trial Registry (PACTR20121000441277, 30/10/2012).

Training and Assessment of Clinician’s Utilization of the Los Angeles Classification for Reflux Esophagitis

Training and Assessment of Clinician’s Utilization of the Los Angeles Classification for Reflux Esophagitis

Building and validating trend-based multiple sclerosis case definitions: a population-based cohort study for Manitoba, Canada

ObjectiveThis study aims to (1) build and validate model-based case definitions for multiple sclerosis (MS) that use trends (ie, trend-based case definitions) and (2) to apply dynamic classification to identify...

Dry Powder Inhaler Use in Primary School Aged Children with Asthma: A Systematic Review

ObjectiveAsthma is the most common chronic disease in children. Dry powder inhalers (DPI) are effective for medication delivery in adults and adolescents, and provide a lower environmental footprint and more portability when compared to metered dose inhaler (MDI) with spacer. They require specific technique, and it is necessary to ascertain whether they can be used in younger age groups. We aimed to assess evidence regarding whether primary school aged (5–11 years) children can use DPI with adequate technique both during stable and acute asthma.DesignOvid MEDLINE, Embase and PubMed were searched for studies assessing DPI use in children aged 5–11 years with asthma or wheeze. Results of studies were synthesised by study design and outcome measure.ResultsThirty-eight studies were identified for analysis. These were analysed in three groups: (1) 25 studies assessing children's ability to use DPI by peak inspiratory flow measurement, (2) 10 studies assessing children's ability to use DPI by physician assessment, and (3) three studies measuring efficacy of DPI compared to gold standard (MDI with spacer). Five studies included children during acute exacerbations.ConclusionThe majority of primary school aged children have the ability to use a DPI with adequate training, support and practice. Some younger children may have difficulties, and clinician assessment and ongoing review is crucial in determining which children are likely to benefit from a DPI. Consistent correct use and adherence remains a challenge, but this is also an issue with MDI plus spacer and does not appear to be significantly worse with DPI. Evidence of the use of DPI during acute illness is limited, and more studies are required in this setting.

Evaluation of Real-World Tumor Response Derived From Electronic Health Record Data Sources: A Feasibility Analysis in Patients With Metastatic Non-Small Cell Lung Cancer Treated With Chemotherapy.

Real-world data (RWD) holds promise for ascribing a real-world (rw) outcome to a drug intervention; however, ascertaining rw-response to treatment from RWD can be challenging. Friends of Cancer Research formed a collaboration to assess available data attributes related to rw-response across RWD sources to inform methods for capturing, defining, and evaluating rw-response. This retrospective noninterventional (observational) study included seven electronic health record data companies (data providers) providing summary-level deidentified data from 200 patients diagnosed with metastatic non-small cell lung cancer (mNSCLC) and treated with first-line platinum doublet chemotherapy following a common protocol. Data providers reviewed the availability and frequency of data components to assess rw-response (ie, images, radiology imaging reports, and clinician response assessments). A common protocol was used to assess and report rw-response end points, including rw-response rate (rwRR), rw-duration of response (rwDOR), and the association of rw-response with rw-overall survival (rwOS), rw-time to treatment discontinuation (rwTTD), and rw-time to next treatment (rwTTNT). The availability and timing of clinician assessments was relatively consistent across data sets in contrast to images and image reports. Real-world response was analyzed using clinician response assessments (median proportion of patients evaluable, 77.5%), which had the highest consistency in the timing of assessments. Relative consistency was observed across data sets for rwRR (median 46.5%), as well as the median and directionality of rwOS, rwTTD, and rwTTNT. There was variability in rwDOR across data sets. This collaborative effort demonstrated the feasibility of aligning disparate data sources to evaluate rw-response end points using clinician-documented responses in patients with mNSCLC. Heterogeneity exists in the availability of data components to assess response and related rw-end points, and further work is needed to inform drug effectiveness evaluation within RWD sources.

Virtual Assessment of Functional Mobility in Lower Extremity Prosthesis Clients: An Exploratory Study

ObjectiveTo investigate the relationship between patient perception of lower extremity function and a home-based virtual clinician assessment of mobility in lower limb prosthesis clients. DesignDescriptive observational study using a clinician-administered functional mobility survey and timed Up and Go test to assess lower extremity function under supervision. SettingHealth Insurance Portability and Accountability Act-compliant online virtual platform. ParticipantsTwelve lower limb loss clients currently using prostheses, aged ≥19 years, not pregnant, and with no stroke, seizure disorder, or cancer. InterventionsNot applicable. Main Outcome MeasuresMain outcomes were mobility survey scores and mean timed Up and Go duration. ResultsMost participants reported significant ease of completing basic indoor ambulation and toileting tasks (66%-75%) and significant difficulty in running or prolonged ambulation activities (83%) requiring use of lower limb prosthesis. Timed Up and Go test was faster (11.0±2.9 s) than the reference range for transtibial prosthesis users and negatively associated with self-reported lower extremity functional status (r=−.70, P=.02). ConclusionsSelf-reported movement with lower limb prostheses at home and evaluation of mobility via a virtual platform is a feasible assessment modality that may reduce the frequency of therapy visits, defray some rehabilitation costs, and minimize the travel burden to distant prosthetic clinics.

How the CAHPS Clinician and Group Patient Experience Survey Data Have Been Used in Research: A Systematic Review.

Patient experience is a key aspect of care quality. The Consumer Assessment of Healthcare Providers and Systems Clinician and Group (CG-CAHPS®) survey measures experiences with ambulatory care providers to inform public reporting, pay-for-performance initiatives, interventions, patient choice of physicians/practices, and quality improvement. Since the survey's 2007 release, no systematic review of its use in research has been published. We reviewed English-language, peer-reviewed articles published since 2008 using CG-CAHPS survey data in the U.S. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and used the Checklist for Analytical Cross-Sectional Studies. We examined 126 articles and included 52. Twenty-seven articles focused on general primary care, and the others focused on ambulatory specialty care. Of the 52 studies, 37 were cross-sectional, and the majority conducted patient-level regression analysis, controlling for patient characteristics. The most-used CAHPS measures were overall provider rating and the provider communication composite. CG-CAHPS data were primarily utilized to evaluate interventions (24 studies) and examine cross-sectional associations (21 studies) of site-level (eg, organizational climate), provider-level (physician empathy), and patient-level (medication adherence) factors with patient experience. Four studies reported disparities in patient experience. The widespread use of CG-CAHPS data implies the survey's value in measuring and improving care quality. Unlike facility or plan surveys, the CG-CAHPS survey was designed to allow attribution to medical groups and clinicians, which, as evidence shows, is its main strength. Policymakers, researchers, clinicians, and health care leaders can leverage CG-CAHPS data in quality improvement efforts and interventions supporting patient-centered care.

Minimizing Survey Questions for PTSD Prediction Following Acute Trauma.

Traumatic experiences have the potential to give rise to post-traumatic stress disorder (PTSD), a debilitating psychiatric condition associated with impairments in both social and occupational functioning. There has been great interest in utilizing machine learning approaches to predict the development of PTSD in trauma patients from clinician assessment or survey-based psychological assessments. However, these assessments require a large number of questions, which is time consuming and not easy to administer. In this paper, we aim to predict PTSD development of patients 3 months post-trauma from multiple survey-based assessments taken within 2 weeks post-trauma. Our objective is to minimize the number of survey questions that patients need to answer while maintaining the prediction accuracy from the full surveys. We formulate this as a feature selection problem and consider 4 different feature selection approaches. We demonstrate that it is possible to achieve up to 72% accuracy for predicting the 3-month PTSD diagnosis from 10 survey questions using a mean decrease in impurity-based feature selector followed by a gradient boosting classifier.

Clinician Prediction of Survival vs Calculated Prediction Scores in Patients Requiring Extracorporeal Membrane Oxygenation.

Determining appropriate extracorporeal membrane oxygenation (ECMO) candidacy ensures appropriate utilization of this costly resource. The current ECMO survival prediction scores do not consider clinician assessment of patient viability. This study compared clinician prediction of survival to hospital discharge versus prediction scores. The aim of this study was to compare clinician prediction of patients' survival to hospital discharge versus prognostic prediction scores (Respiratory ECMO Survival Prediction [RESP] or Survival After Veno-Arterial ECMO [SAVE] score) to actual survival. This was an observational descriptive study from January 2020 to November 2021 conducted with interviews of nurses, perfusionists, and physicians who were involved during the initiation of ECMO within the first 24 hours of cannulation. Data were retrieved from the medical record to determine prediction scores and survival outcomes at hospital discharge. Accuracy of clinician prediction of survival was compared to the RESP or SAVE prediction scores and actual survival to hospital discharge. Accurate prediction of survival to hospital discharge for veno-venous ECMO by nurses was 47%, 64% by perfusionists, 45% by physicians, and 45% by the RESP score. Accurate predictions of patients on veno-arterial ECMO were correct in 54% of nurses, 77% of physicians, and 14% by the SAVE score. Physicians were more accurate than the SAVE score, P = .021, and perfusionists were significantly more accurate than the RESP score, P = .044. There was no relationship between ECMO specialists' years of experience and accuracy of predications. Extracorporeal membrane oxygenation clinicians may have better predictions of survival to hospital discharge than the prediction scores. Further research is needed to develop accurate prediction tools to help determine ECMO eligibility.

Hunting imaging biomarkers in pulmonary fibrosis: Benchmarks of the AIIB23 challenge

Airway-related quantitative imaging biomarkers are crucial for examination, diagnosis, and prognosis in pulmonary diseases. However, the manual delineation of airway structures remains prohibitively time-consuming. While significant efforts have been made towards enhancing automatic airway modelling, current public-available datasets predominantly concentrate on lung diseases with moderate morphological variations. The intricate honeycombing patterns present in the lung tissues of fibrotic lung disease patients exacerbate the challenges, often leading to various prediction errors. To address this issue, the 'Airway-Informed Quantitative CT Imaging Biomarker for Fibrotic Lung Disease 2023′ (AIIB23) competition was organized in conjunction with the official 2023 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). The airway structures were meticulously annotated by three experienced radiologists. Competitors were encouraged to develop automatic airway segmentation models with high robustness and generalization abilities, followed by exploring the most correlated QIB of mortality prediction. A training set of 120 high-resolution computerised tomography (HRCT) scans were publicly released with expert annotations and mortality status. The online validation set incorporated 52 HRCT scans from patients with fibrotic lung disease and the offline test set included 140 cases from fibrosis and COVID-19 patients. The results have shown that the capacity of extracting airway trees from patients with fibrotic lung disease could be enhanced by introducing voxel-wise weighted general union loss and continuity loss. In addition to the competitive image biomarkers for mortality prediction, a strong airway-derived biomarker (Hazard ratio>1.5, p < 0.0001) was revealed for survival prognostication compared with existing clinical measurements, clinician assessment and AI-based biomarkers.

Guidance on mucositis assessment from the MASCC Mucositis Study Group and ISOO: an international Delphi study

Mucositis is a common and highly impactful side effect of conventional and emerging cancer therapy and thus the subject of intense investigation. Although common practice, mucositis assessment is heterogeneously adopted and poorly guided, impacting evidence synthesis and translation. The Multinational Association of Supportive Care in Cancer (MASCC) Mucositis Study Group (MSG) therefore aimed to establish expert recommendations for how existing mucositis assessment tools should be used, in clinical care and trials contexts, to improve the consistency of mucositis assessment. This study was conducted over two stages (January 2022-July 2023). The first phase involved a survey to MASCC-MSG members (January 2022-May 2022), capturing current practices, challenges and preferences. These then informed the second phase, in which a set of initial recommendations were prepared and refined using the Delphi method (February 2023-May 2023). Consensus was defined as agreement on a parameter by >80% of respondents. Seventy-two MASCC-MSG members completed the first phase of the study (37 females, 34 males, mainly oral care specialists). High variability was noted in the use of mucositis assessment tools, with a high reliance on clinician assessment compared to patient reported outcome measures (PROMs, 47% vs 3%, 37% used a combination). The World Health Organization (WHO) and Common Terminology Criteria for Adverse Events (CTCAE) scales were most commonly used to assess mucositis across multiple settings. Initial recommendations were reviewed by experienced MSG members and following two rounds of Delphi survey consensus was achieved in 91 of 100 recommendations. For example, in patients receiving chemotherapy, the recommended tool for clinician assessment in clinical practice is WHO for oral mucositis (89.5% consensus), and WHO or CTCAE for gastrointestinal mucositis (85.7% consensus). The recommended PROM in clinical trials is OMD/WQ for oral mucositis (93.3% consensus), and PRO-CTCAE for gastrointestinal mucositis (83.3% consensus). These new recommendations provide much needed guidance on mucositis assessment and may be applied in both clinical practice and research to streamline comparison and synthesis of global data sets, thus accelerating translation of new knowledge into clinical practice. No funding was received.