Development and Validation of a Machine Learning COVID-19 Veteran (COVet) Deterioration Risk Score.

BACKGROUND AND OBJECTIVE: To develop the COVid Veteran (COVet) score for clinical deterioration in Veterans hospitalized with COVID-19 and further validate this model in both Veteran and non-Veteran samples. No such score has been derived and validated while incorporating a Veteran sample. DERIVATION COHORT: Adults (age ≥ 18 yr) hospitalized outside the ICU with a diagnosis of COVID-19 for model development to the Veterans Health Administration (VHA) (n = 80 hospitals). VALIDATION COHORT: External validation occurred in a VHA cohort of 34 hospitals, as well as six non-Veteran health systems for further external validation (n = 21 hospitals) between 2020 and 2023. PREDICTION MODEL: eXtreme Gradient Boosting machine learning methods were used, and performance was assessed using the area under the receiver operating characteristic curve and compared with the National Early Warning Score (NEWS). The primary outcome was transfer to the ICU or death within 24 hours of each new variable observation. Model predictor variables included demographics, vital signs, structured flowsheet data, and laboratory values. RESULTS: A total of 96,908 admissions occurred during the study period, of which 59,897 were in the Veteran sample and 37,011 were in the non-Veteran sample. During external validation in the Veteran sample, the model demonstrated excellent discrimination, with an area under the receiver operating characteristic curve of 0.88. This was significantly higher than NEWS (0.79; p < 0.01). In the non-Veteran sample, the model also demonstrated excellent discrimination (0.86 vs. 0.79 for NEWS; p < 0.01). The top three variables of importance were eosinophil percentage, mean oxygen saturation in the prior 24-hour period, and worst mental status in the prior 24-hour period. CONCLUSIONS: We used machine learning methods to develop and validate a highly accurate early warning score in both Veterans and non-Veterans hospitalized with COVID-19. The model could lead to earlier identification and therapy, which may improve outcomes.

Multicenter Development and Prospective Validation of eCARTv5: A Gradient Boosted Machine Learning Early Warning Score.

Rationale: Early detection of clinical deterioration using early warning scores may improve outcomes. However, most implemented scores were developed using logistic regression, only underwent retrospective internal validation, and were not tested in important patient subgroups. Objectives: To develop a gradient boosted machine model (eCARTv5) for identifying clinical deterioration and then validate externally, test prospectively, and evaluate across patient subgroups. Methods: All adult patients hospitalized on the wards in seven hospitals from 2008- 2022 were used to develop eCARTv5, with demographics, vital signs, clinician documentation, and laboratory values utilized to predict intensive care unit transfer or death in the next 24 hours. The model was externally validated retrospectively in 21 hospitals from 2009-2023 and prospectively in 10 hospitals from February to May 2023. eCARTv5 was compared to the Modified Early Warning Score (MEWS) and the National Early Warning Score (NEWS) using the area under the receiver operating characteristic curve (AUROC). Measurements and Main Results: The development cohort included 901,491 admissions, the retrospective validation cohort included 1,769,461 admissions, and the prospective validation cohort included 46,330 admissions. In retrospective validation, eCART had the highest AUROC (0.835; 95%CI 0.834, 0.835), followed by NEWS (0.766 (95%CI 0.766, 0.767)), and MEWS (0.704 (95%CI 0.703, 0.704)). eCART's performance remained high (AUROC ≥0.80) across a range of patient demographics, clinical conditions, and during prospective validation. Conclusions: We developed eCARTv5, which accurately identifies early clinical deterioration in hospitalized ward patients. Our model performed better than the NEWS and MEWS retrospectively, prospectively, and across a range of subgroups.

Electroconvulsive Therapy Credentialing for Psychiatrists-Review of Required Standards Across States and Territories in Australia.

ABSTRACT: Electroconvulsive therapy (ECT) is a complex medical procedure, the delivery of which requires specialist knowledge and skills. We reviewed the standards required for ECT credentialing in different jurisdictions in Australia. We reviewed the Chief Psychiatrist guidelines and statewide policy standards on ECT and focused on standards required for initial credentialing and ongoing privileging in ECT. We compared the credentialing requirements within these documents with the standards specified in the Royal Australian and New Zealand College of Psychiatrists professional practice guideline for ECT. Most of the jurisdictions had specific standards for initial credentialing and maintenance of this credentialing; however, there was significant variance in the credentialing process and standards required. It would be useful to have a minimum standard for credentialing for ECT psychiatrists and prescribers. This standard would be relevant for practice of ECT internationally. States and territories would have the responsibility for implementation of these standards. Appropriate training and establishing good clinical governance processes are essential to the provision of high quality ECT.

Prescribing electroconvulsive therapy for depression: Not as simple as it used to be.

In the last century, prescribing electroconvulsive therapy usually involved considering the relative merits of unilateral versus bilateral electroconvulsive therapy, with most other parameters fixed. However, research over the last 30 years has discovered that several parameters of the electroconvulsive therapy stimulus can have a significant impact on efficacy and cognitive side effects. The stimulus dose relative to seizure threshold was shown to significantly affect efficacy, especially for right unilateral electroconvulsive therapy, where suprathreshold doses in the vicinity of 5-6 times seizure threshold were far more efficacious than doses closer to threshold. However, this did not hold for bitemporal electroconvulsive therapy, where near-threshold stimuli were equally effective as suprathreshold stimuli. Then, changes in stimulus pulse width were found to also have a significant impact on both efficacy and side effects, with ultrabrief pulse widths of 0.3 ms having significantly fewer cognitive side effects in unilateral electroconvulsive therapy than standard brief pulse widths of 1.0 ms, with only slightly reduced efficacy. Therefore, choosing the optimum electroconvulsive therapy prescription for an individual patient now requires consideration of placement, pulse width and stimulus dose relative to seizure threshold, and how these three interact with each other. This viewpoint aims to raise awareness of these issues for psychiatrists involved in electroconvulsive therapy practice.

The place of non-invasive brain stimulation in the RANZCP clinical practice guidelines for mood disorders.

Clinical practice guidelines are important documents as they have the capacity to significantly influence and shape clinical practice in important areas of therapeutics. As such, they need to be developed informed by comprehensive and quality-based systematic reviews, involve consensus deliberations representative of the appropriate experts in the field and be subject to thorough critical review. A revised clinical practice guideline for the management of patients with mood disorders was recently published under the auspices of the Royal Australian and New Zealand College of Psychiatrists. However, this clinical practice guideline was not developed in a manner that reflects the appropriate standards that should apply to clinical practice guideline development and it has critical flaws, especially as it pertains to the use of repetitive transcranial magnetic stimulation treatment for patients with depression. The revision of the college clinical practice guideline has explicitly removed clear and unequivocal evidence-based recommendations that were found in a previous version of the clinical practice guideline and replaced these with consensus-based recommendations. However, the consensus-based recommendations were developed without consultation of the appropriate expert body within the college and contradict the scientific literature. There is substantive and unequivocal evidence supporting the antidepressant use of repetitive transcranial magnetic stimulation in the treatment of patients with depression and its use after a patient with depression has failed a limited number (typically around two) of antidepressant medication trials. Readers should refer to the college Professional Practice Guidelines for repetitive transcranial magnetic stimulation published in 2018 for thorough information about the use of this important new treatment.

Feasibility of the Audio Recorded Cognitive Screen in the Assessment of Individuals Undergoing Electroconvulsive Therapy.

BACKGROUND: Monitoring for cognitive deficits during a course of electroconvulsive therapy (ECT) is recommended, but cognitive assessment can be time consuming. The Audio Recorded Cognitive Screen (ARCS) is a cognitive test instrument with good psychometric properties that places minimal demands on clinicians' time, but until now, it has not been formally evaluated for monitoring cognition in the context of ECT treatment. OBJECTIVES: This study aimed to assess the feasibility/utility of using the ARCS in the assessment of depressed patients undergoing ECT. METHODS: Depressed patients undergoing ECT were tested with the ARCS and a comparison instrument, the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS), in counterbalance order immediately before any ECT and after the sixth ECT treatment episode. Apathy (Apathy Scale) and depression (Profile of Mood states Short Form) were measured on both occasions. Analyses compared performances on the 2 cognitive instruments and examined for associations with the measures of apathy or depression. RESULTS: Twenty-eight individuals (9 male, 19 female) aged 19 to 84 years underwent testing. Performances on the total ARCS were similar to those on the total RBANS, and both showed decline from baseline to follow-up. The total ARCS and RBANS measures correlated well (r = 0.75, P < 0.001). Neither apathy nor depression scores were significantly associated with scores on either the RBANS or ARCS. CONCLUSIONS: The ARCS was acceptable and convenient in the assessment of cognition in patients undergoing treatment with ECT. In light of its practical advantages, further evaluation of the ARCS for detecting cognitive impairment and tracking cognitive changes during ECT seems warranted.

Royal Australian and New Zealand College of Psychiatrists professional practice guidelines for the administration of electroconvulsive therapy.

OBJECTIVES: To provide guidance for the optimal administration of electroconvulsive therapy, in particular maintaining the high efficacy of electroconvulsive therapy while minimising cognitive side-effects, based on scientific evidence and supplemented by expert clinical consensus. METHODS: Articles and information were sourced from existing guidelines and the published literature. Information was revised and discussed by members of the working group of the Royal Australian and New Zealand College of Psychiatrists' Section for Electroconvulsive Therapy and Neurostimulation, and findings were then formulated into consensus-based recommendations and guidance. The guidelines were subjected to rigorous successive consultation and external review within the Royal Australian and New Zealand College of Psychiatrists, involving the full Section for Electroconvulsive Therapy and Neurostimulation membership, and expert and clinical advisors and professional bodies with an interest in electroconvulsive therapy administration. RESULTS: The Royal Australian and New Zealand College of Psychiatrists' professional practice guidelines for the administration of electroconvulsive therapy provide up-to-date advice regarding the use of electroconvulsive therapy in clinical practice and are informed by evidence and clinical experience. The guidelines are intended for use by psychiatrists and also others with an interest in the administration of electroconvulsive therapy. The guidelines are not intended as a directive about clinical practice or instructions as to what must be done for a given patient, but provide guidance to facilitate best practice to help optimise outcomes for patients. The outcome is guidelines that strive to find the appropriate balance between promoting best evidence-based practice and acknowledging that electroconvulsive therapy is a continually evolving practice. CONCLUSION: The guidelines provide up-to-date advice for psychiatrists to promote optimal standards of electroconvulsive therapy practice.

HCC complicated by PVT: Outcome and the role of anticoagulation therapy.

Background: This retrospective study investigated the clinical impact of PVT on the course of patients with HCC who were and were not treated with anticoagulation (AC). Methods: We retrospectively evaluated a cohort of 60 patients diagnosed with HCC and PVT. Nine patients were excluded for lack of follow-up. HCC, PVT diagnosis, and imaging follow-up were performed using contrast-enhanced computed tomography or MRI. Of the 51 patients evaluated, 12 received AC and 39 did not. Results: Forty-two patients were male; mean age was 60.3 years. Mean survival after HCC diagnosis was 32.9 months; after PVT diagnosis, it was 18.4 months. No symptoms directly related to PVT development were reported. AC therapy was initiated for 12 patients and had to be discontinued for 3 patients because of complications. AC was not associated with a difference in PVT progression (49% in non-AC group vs. 50% in AC group). After adjusting for age, HCC type (single vs. multifocal), and Child-Pugh score, AC was associated with an improved survival after HCC diagnosis (adjusted hazard ratio [HR] = 0.37; 95% confidence interval [CI] 0.14 to 0.99) and after PVT diagnosis (HR = 0.34; 95% CI 0.13 to 0.88). Conclusion: Patients with HCC complicated by PVT in both AC and non-AC groups had a similar rate of progression. Neither group had symptoms attributable to PVT. Possible AC-related complications need to be considered before proceeding with therapy in patients with HCC and PVT. AC may be associated with a survival advantage in patients with HCC and PVT.

A randomized trial comparing winged versus conventional plastic stents for malignant bile duct strictures.

BACKGROUND AND STUDY AIMS: Stent insertion at endoscopic retrograde cholangiopancreatography (ERCP) is an established therapy for managing malignant biliary obstruction. Conventional plastic stents with a tubular design are most commonly used despite limited patency. Plastic stents with a winged design may theoretically increase the duration of stent patency. The aim of this study was to compare stent patency of the winged versus conventional plastic stents in patients with malignant biliary obstruction. PATIENTS AND METHODS: A prospective, randomized subject-blinded trial was conducted. Patients with malignant biliary obstruction were randomized (1:1) to either a 10 French winged stent or 7 or 10 French conventional plastic stent. Strictures greater than 1 cm distal to the hilum were included. Patients were followed clinically to determine the frequency of stent failure until surgery, death or study closure. RESULTS: Fifty-eight patients were enrolled. Following 9 exclusions, 49 patients were randomized to a winged (n = 23) or conventional stent (n = 26). Median time to stent failure was 89 (95 % CI 26-NA) vs 143 (95 % CI 33 - 266) days ( P  = 0.963) for the winged and conventional group, respectively. Stent failure for the winged group occurred in 11 (48 %) compared to 14 (54 %) in the conventional group. Median survival was 123 (95 % CI 81 - 189) vs 342 days (95 % CI 123 - 704) (p = 0.084) in the winged and conventional group respectively. There were no procedure related adverse events. CONCLUSIONS: Improvement in stent patency was not seen with the winged stent when compared to the conventional plastic stent.

Tumor and circulating biomarkers in patients with second-line hepatocellular carcinoma from the randomized phase II study with tivantinib.

ARQ 197-215 was a randomized placebo-controlled phase II study testing the MET inhibitor tivantinib in second-line hepatocellular carcinoma (HCC) patients. It identified tumor MET as a key biomarker in HCC.Aim of this research was to study the prognostic and predictive value of tumor (MET, the receptor tyrosine kinase encoded by the homonymous MNNG-HOS transforming gene) and circulating (MET, hepatocyte growth factor [HGF], alpha-fetoprotein [AFP], vascular endothelial growth factor [VEGF]) biomarkers in second-line HCC. Tumor MET-High status was centrally assessed by immunohistochemistry. Circulating biomarkers were centrally analyzed on serum samples collected at baseline and every 4-8 weeks, using medians as cut-off to determine High/Low status. Tumor MET, tested in 77 patients, was more frequently High after (82%) versus before (40%) sorafenib. A significant interaction (p = 0.04) between tivantinib and baseline tumor MET in terms of survival was observed. Baseline circulating MET and HGF (102 patients) High status correlated with shorter survival (HR 0.61, p = 0.03, and HR 0.60, p = 0.02, respectively), while the association between AFP (104 patients) or VEGF (103 patients) status and survival was non-significant. CONCLUSIONS: Tumor MET levels were higher in patients treated with sorafenib. Circulating biomarkers such as MET and HGF may be prognostic in second-line HCC. These results need to be confirmed in larger randomized clinical trials.

Gastrointestinal Endoscopic Ultrasound-Guided Fine-Needle Aspiration Biopsy Specimens: Adequate Diagnostic Yield and Accuracy Can Be Achieved without On-Site Evaluation.

BACKGROUND: Endoscopic ultrasound-guided fine-needle aspiration biopsy (EUS-FNA) is the preferred method for biopsying the gastrointestinal tract, and rapid on-site cytological evaluation is considered standard practice. Our institution does not perform on-site evaluation; this study analyzes our overall diagnostic yield, accuracy, and incidence of nondiagnostic cases to determine the validity of this strategy. DESIGN: Data encompassing clinical information, procedural records, and cytological assessment were analyzed for gastrointestinal EUS-FNA procedures (n = 85) performed at Vancouver General Hospital from January 2012 to January 2013. We compared our results with those of studies that had on-site evaluation and studies that did not have on-site evaluation. RESULTS: Eighty-five biopsies were performed in 78 patients, from sites that included the pancreas, the stomach, the duodenum, lymph nodes, and retroperitoneal masses. Malignancies were diagnosed in 45 (53%) biopsies, while 24 (29%) encompassed benign entities. Suspicious and atypical results were recorded in 8 (9%) and 6 (7%) cases, respectively. Only 2 (2%) cases received a cytological diagnosis of 'nondiagnostic'. Our overall accuracy was 72%, our diagnostic yield was 98%, and our nondiagnostic rate was 2%. Our results did not significantly differ from those of studies that did have on-site evaluation. CONCLUSION: Our study highlights that adequate diagnostic accuracy can be achieved without on-site evaluation.

Effectiveness of left anterior right temporal electrode placement in electroconvulsive therapy: 3 case reports.

Unilateral and bitemporal electrode placement has been the dominant mode of delivery in electroconvulsive therapy. We report 3 patients receiving maintenance electroconvulsive therapy where the use of dominant electrode placements was ineffective. Changing to left anterior right temporal electrode placement resulted in marked clinical improvement. This supports the limited literature on this electrode placement.

The effect of doxorubicin loading on response and toxicity with drug-eluting embolization in resectable hepatoma: a dose escalation study.

AIM: The dose-response relationship between doxorubicin and superabsorbent drug-eluting microspheres has not been established. In this study, we investigated the relationships between dose and delivery parameters as they pertain to toxicity and response in surgically resectable hepatocellular carcinoma (HCC). PATIENTS AND METHODS: Twenty-five patients with resectable HCC were randomly assigned and divided into four groups, each receiving either bland, 25 mg, 50 mg or 75 mg of doxorubicin loaded Super Absorbent Polymer microspheres, with 24 patients undergoing surgical resection. Response Evaluation and Criteria in Solid Tumors (RECIST) 1.0 and European Association for the Study of the Liver (EASL)-based volumetric response was performed at one month and surgical resection of the reference tumor was performed at two months. Adverse events were collected at regular intervals. RESULTS: Fifty-six percent of patients demonstrated complete response according to EASL criteria as opposed to 0% according to RECIST (v1.0) criteria. Residual tumor was identified in all groups (0 mg: 35%±28.5%; 25 mg: 42%±30.4%; 50 mg: 3.6%±3.3%; and 75 mg: 49.29%±32.6%. A total of 112 adverse events of grades 1-3 occurred (average 5.1 per patient), with no grade 4 or 5. No difference was noted between bland embolic and drug-loaded groups. Subset analysis did demonstrate a significantly increased degree of necrosis in the 50 mg-loaded group (p=0.018). Strong correlation existed between arterial phase Computer Tomography EASL-based response and histopathology (r=0.81; p<0.0001). All groups had residual tumor. CONCLUSION: Histology correlates strongly with one-month post-procedural imaging and response optimized at 50 mg of loading per vial. Adverse events were a reflection of embolization, with no relationship between loading dose or administered dose of doxorubicin.

Response to endoscopic therapy for biliary anastomotic strictures in deceased versus living donor liver transplantation.

BACKGROUND: Endoscopic therapy has been successful in the management of biliary complications after both deceased donor liver transplantation (DDLT) and living donor liver transplantation (LDLT). LDLT is thought to be associated with higher rates of biliary complications, but there are few studies comparing the success of endoscopic management of anastomotic strictures between the two groups. This study aims to compare our experience in the endoscopic management of anastomotic strictures in DDLT versus LDLT. METHODS: This is a retrospective database review of all liver transplant patients undergoing endoscopic retrograde cholangiopancreatography (ERCP) after liver transplantation. The frequency of anastomotic stricture and the time to develop and to resolve anastomotic stricture were compared between DDLT and LDLT. The response of anastomotic stricture to endoscopic therapy was also analyzed. RESULTS: A total of 362 patients underwent liver transplantation between 2003 and 2011, with 125 requiring ERCP to manage biliary complications. Thirty-three (9.9%) cases of DDLT and 8 (27.6%) of LDLT (P=0.01) were found to have anastomotic stricture. When comparing DDLT and LDLT, there was no difference in the mean time to the development of anastomotic strictures (98+/-17 vs 172+/-65 days, P=0.11), likelihood of response to ERCP [22 (66.7%) vs 6 (75.0%), P=0.69], mean time to the resolution of anastomotic strictures (268+/-77 vs 125+/-37 days, P=0.34), and the number of ERCPs required to achieve resolution (3.9+/-0.4 vs 4.7+/-0.9, P=0.38). CONCLUSIONS: Endoscopic therapy is effective in the majority of biliary complications relating to liver transplantation. Anastomotic strictures occur more frequently in LDLT compared with DDLT, with equivalent endoscopic treatment response and outcomes for both groups.