Development and Evaluation of Conformal Prediction Methods for Quantitative Structure-Activity Relationship.

The quantitative structure-activity relationship (QSAR) regression model is a commonly used technique for predicting the biological activities of compounds using their molecular descriptors. Besides accurate activity estimation, obtaining a prediction uncertainty metric like a prediction interval is highly desirable. Quantifying prediction uncertainty is an active research area in statistical and machine learning (ML), but the implementation for QSAR remains challenging. However, most ML algorithms with high predictive performance require add-on companions for estimating the uncertainty of their prediction. Conformal prediction (CP) is a promising approach as its main components are agnostic to the prediction modes, and it produces valid prediction intervals under weak assumptions on the data distribution. We proposed computationally efficient CP algorithms tailored to the most widely used ML models, including random forests, deep neural networks, and gradient boosting. The algorithms use a novel approach to the derivation of nonconformity scores from the estimates of prediction uncertainty generated by the ensembles of point predictions. The validity and efficiency of proposed algorithms are demonstrated on a diverse collection of QSAR data sets as well as simulation studies. The provided software implementing our algorithms can be used as stand-alone or easily incorporated into other ML software packages for QSAR modeling.

Fractional CO2 Laser for Burn Scars: A Comparison of Patient Reported Outcomes Between Those With and Without Laser Treatment.

Burn reconstruction outcomes are an area of growing investigation. Although there is evidence of measured physical improvements in scar characteristics after laser treatment, there is little information on patient reported outcomes. The purpose of this study is to compare patient reported outcomes between burn survivors with and without laser treatment. The study included participants in the Burn Model Systems National Database at a single center; participants that received outpatient laser treatment for burn scars were compared to a matched group of burn survivors that did not receive laser. The following outcomes were examined: Satisfaction With Life Scale, Mental and Physical Component Summary of the Veterans Rand Survey, and the PROMIS Pain Intensity Scale. Regression analyses examined the associations between laser treatment and each outcome at 12 and 24 months. The study population included 287 adult burn survivors (65 laser group, 222 control group). The significant differences found between the two groups included: burn size (laser: 14.9, 13.5 SD, control: 8.9, 11.1 SD; p<0.001), insurance type (p=0.036), inhalation injury (laser: 17.2%, control: 2.7%; p<0.001), and ventilator requirement (laser: 27.7%, control: 13.5%; p=0.013). Laser treatment was not associated with any of the outcomes at both follow-up time points. Further research is needed to develop patient reported outcome measures that are more sensitive to the clinical changes experienced by burn survivors receiving laser treatment.

Critical Care of the Pediatric Burn Patient.

Life-saving pediatric burn care is often initiated in hospitals that are not designated as a pediatric burn center. Therefore, familiarity with critical care of pediatric burn patients is crucial for physicians working in all healthcare settings equipped to care for children. Management of airway, mechanical ventilation, preservation of ideal circulatory status, and establishment of vascular access in pediatric burn patients requires many unique considerations. This article aims to summarize important principles of critical care of children with significant burn injuries for review by physicians and surgeons working in hospitals designated as a pediatric burn center and those that stabilize these patients prior to referral.

Analysis and Visualization of Longitudinal Genomic and Clinical Data from the AACR Project GENIE Biopharma Collaborative in cBioPortal.

International cancer registries make real-world genomic and clinical data available, but their joint analysis remains a challenge. AACR Project GENIE, an international cancer registry collecting data from 19 cancer centers, makes data from >130,000 patients publicly available through the cBioPortal for Cancer Genomics (https://genie.cbioportal.org). For 25,000 patients, additional real-world longitudinal clinical data, including treatment and outcome data, are being collected by the AACR Project GENIE Biopharma Collaborative using the PRISSMM data curation model. Several thousand of these cases are now also available in cBioPortal. We have significantly enhanced the functionalities of cBioPortal to support the visualization and analysis of this rich clinico-genomic linked dataset, as well as datasets generated by other centers and consortia. Examples of these enhancements include (i) visualization of the longitudinal clinical and genomic data at the patient level, including timelines for diagnoses, treatments, and outcomes; (ii) the ability to select samples based on treatment status, facilitating a comparison of molecular and clinical attributes between samples before and after a specific treatment; and (iii) survival analysis estimates based on individual treatment regimens received. Together, these features provide cBioPortal users with a toolkit to interactively investigate complex clinico-genomic data to generate hypotheses and make discoveries about the impact of specific genomic variants on prognosis and therapeutic sensitivities in cancer. SIGNIFICANCE: Enhanced cBioPortal features allow clinicians and researchers to effectively investigate longitudinal clinico-genomic data from patients with cancer, which will improve exploration of data from the AACR Project GENIE Biopharma Collaborative and similar datasets.

Acute Respiratory Distress Syndrome, Mechanical Ventilation, and Inhalation Injury in Burn Patients.

Respiratory failure occurs with some frequency in seriously burned patients, driven by a combination of inflammatory and infection factors. Inhalation injury contributes to respiratory failure in some burn patients via direct mucosal injury and indirect inflammation. In burn patients, respiratory failure leading to acute respiratory distress syndrome, with or without inhalation injury, is effectively managed using principles evolved for non-burn critically ill patients.

A PREVENTIVE TOOL FOR PREDICTING BLOODSTREAM INFECTIONS IN CHILDREN WITH BURNS.

ABSTRACT: Introduction: Despite significant advances in pediatric burn care, bloodstream infections (BSIs) remain a compelling challenge during recovery. A personalized medicine approach for accurate prediction of BSIs before they occur would contribute to prevention efforts and improve patient outcomes. Methods: We analyzed the blood transcriptome of severely burned (total burn surface area [TBSA] ≥20%) patients in the multicenter Inflammation and Host Response to Injury ("Glue Grant") cohort. Our study included 82 pediatric (aged <16 years) patients, with blood samples at least 3 days before the observed BSI episode. We applied the least absolute shrinkage and selection operator (LASSO) machine-learning algorithm to select a panel of biomarkers predictive of BSI outcome. Results: We developed a panel of 10 probe sets corresponding to six annotated genes ( ARG2 [ arginase 2 ], CPT1A [ carnitine palmitoyltransferase 1A ], FYB [ FYN binding protein ], ITCH [ itchy E3 ubiquitin protein ligase ], MACF1 [ microtubule actin crosslinking factor 1 ], and SSH2 [ slingshot protein phosphatase 2 ]), two uncharacterized ( LOC101928635 , LOC101929599 ), and two unannotated regions. Our multibiomarker panel model yielded highly accurate prediction (area under the receiver operating characteristic curve, 0.938; 95% confidence interval [CI], 0.881-0.981) compared with models with TBSA (0.708; 95% CI, 0.588-0.824) or TBSA and inhalation injury status (0.792; 95% CI, 0.676-0.892). A model combining the multibiomarker panel with TBSA and inhalation injury status further improved prediction (0.978; 95% CI, 0.941-1.000). Conclusions: The multibiomarker panel model yielded a highly accurate prediction of BSIs before their onset. Knowing patients' risk profile early will guide clinicians to take rapid preventive measures for limiting infections, promote antibiotic stewardship that may aid in alleviating the current antibiotic resistance crisis, shorten hospital length of stay and burden on health care resources, reduce health care costs, and significantly improve patients' outcomes. In addition, the biomarkers' identity and molecular functions may contribute to developing novel preventive interventions.

The use of TASER devices in UK policing: an update for clinicians following the recent introduction of the TASER 7.

Taser was introduced into UK policing in 2003 to bridge the operational gap between use of incapacitant sprays and firearms. Use of force reporting in the UK indicates that Taser is relatively safe provided that it is used lawfully. Taser use can result in injuries and has been implicated in a small number of deaths. The latest version of the weapon, the TASER 7, has entered UK policing. The TASER 7 uses a novel probe that has implications for the medical community. A review of Taser medical effects and probe removal for TASER 7 are presented.

Hydrogels for the management of second-degree burns: currently available options and future promise.

Burn wounds result from exposure to hot liquids, chemicals, fire, electric discharge or radiation. Wound severity ranges from first-degree injury, which is superficial, to fourth-degree injury, which exposes bone, tendons and muscles. Rapid assessment of burn depth and accurate wound management in the outpatient setting is critical to prevent injury progression into deeper layers of the dermis. Injury progression is of particular pertinence to second-degree burns, which are the most common form of thermal burn. As our understanding of wound healing advances, treatment options and technologies for second-degree burn management also evolve. Polymeric hydrogels are a class of burn wound dressings that adhere to tissue, absorb wound exudate, protect from the environment, can be transparent facilitating serial wound evaluation and, in some cases, enable facile removal for dressing changes. This review briefly describes the burn level classification and common, commercially available dressings used to treat second-degree burns, and then focuses on new polymeric hydrogel burn dressings under preclinical development analyzing their design, structure and performance. The review presents the follow key learning points: (1) introduction to the integument system and the wound-healing process; (2) classification of burns according to severity and clinical appearance; (3) available dressings currently used for second-degree burns; (4) introduction to hydrogels and their preparation and characterization techniques; and (5) pre-clinical hydrogel burn wound dressings currently being developed.

Factors Associated With Mechanical Ventilation Duration in Pediatric Burn Patients in a Regional Burn Center in the United States.

OBJECTIVES: Among burned children who arrive at a burn center and require invasive mechanical ventilation (IMV), some may have prolonged IMV needs. This has implications for patient-centered outcomes as well as triage and resource allocation decisions. Our objective was to identify factors associated with the duration of mechanical ventilation in pediatric patients with acute burn injury in this setting. DESIGN: Single-center, retrospective cohort study. SETTING: Registry data from a regional, pediatric burn center in the United States. PATIENTS: Children less than or equal to 18 years old admitted with acute burn injury who received IMV between January 2005 and December 2020. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Ventilator days were defined as any full or partial day having received IMV via an endotracheal tube or tracheostomy, not inclusive of time spent ventilated for procedures. Of 5,766 admissions for acute burn care, 4.3% ( n = 249) required IMV with a median duration of 10 days. A multivariable model for freedom from mechanical ventilation showed that the presence of inhalational injury (subhazard ratio [sHR], 0.62; 95% CI, 0.46-0.85) and burns to the head and neck region (sHR, 0.94; 95% CI, 0.90-0.98) were associated with increased risk of remaining mechanically ventilated at any time point. Older (sHR, 1.03; 95% CI, 1.01-1.04) and male children (sHR, 1.39; 95% CI, 1.05-1.84) were more likely to discontinue mechanical ventilation. A majority of children (94.8%) survived to hospital discharge. CONCLUSIONS: The presence of inhalational injury and burns to the head and neck region were associated with a longer duration of mechanical ventilation. Older age and male gender were associated with a shorter duration of mechanical ventilation. These factors should help clinicians better estimate a burned child's expected trajectory and resource-intensive needs upon arrival to a burn center.

An analysis of officer-reported TASER X2™ probe discharge effectiveness in the United Kingdom.

Conducted energy devices (CEDs) are designed to immobilise aggressive individuals through the application of an electrical discharge administered via probes fired at the subject. Although the discharge is intended to disrupt voluntary movement, CEDs have their limitations and several factors are qualitatively understood to adversely influence CED effectiveness. The introduction of the twin-cartridge TASER X2™ into UK policing in 2017 provided a unique opportunity to undertake a quantitative assessment of the factors modulating probe discharge effectiveness based on data reported by police officers firing the device operationally. The overall operational subdual effectiveness of the TASER X2™ was 68.5%. However, several factors were identified that could alter the likelihood of achieving subdual of the subject. The officer-reported data show that probe discharge was highly effective at subduing subjects when both probes had penetrated the skin, least effective when both probes were in clothing and confirmed the reduced effectiveness of narrow probe spreads. The most commonly cited reasons why probe discharge failed to subdue the subject were thick or loose clothing, probe misses and narrow probe spread. These findings, which are likely to generalise to other types of CED, may be used to inform tactics and training to optimise the likelihood of achieving incapacitation when probes are deployed, with benefits for the safety of both the police and the public. The findings may also assist investigations requiring the reconstruction of incidents in which probe discharge has been deployed.

Prediction Accuracy of Production ADMET Models as a Function of Version: Activity Cliffs Rule.

As with many other institutions, our company maintains many quantitative structure-activity relationship (QSAR) models of absorption, distribution, metabolism, excretion, and toxicity (ADMET) end points and updates the models regularly. We recently examined version-to-version predictivity for these models over a period of 10 years. In this approach we monitor the goodness of prediction of new molecules relative to the training set of model version V before they are incorporated in the updated model V+1. Using a cell-based permeability assay (Papp) as an example, we illustrate how the QSAR models made from this data are generally predictive and can be utilized to enrich chemical designs and synthesis. Despite the obvious utility of these models, we turned up unexpected behavior in Papp and other ADMET activities for which the explanation is not obvious. One such behavior is that the apparent predictivity of the models as measured by root-mean-square-error can vary greatly from version to version and is sometimes very poor. One intuitively appealing explanation is that the observed activities of the new molecules fall outside the bulk of activities in the training set. Alternatively, one may think that the new molecules are exploring different regions of chemical space than the training set. However, the real explanation has to do with activity cliffs. If the observed activities of the new molecules are different than expected based on similar molecules in the training set, the predictions will be less accurate. This is true for all our ADMET end points.

Stability of Prediction in Production ADMET Models as a Function of Version: Why and When Predictions Change.

As with other pharma companies, we maintain production QSAR models of ADMET end points and update them regularly. Here, for six ADMET end points, we examine the predictions of test set molecules on multiple versions of random forest models spanning a period of 10 years. For any given end point, the predictions for the majority of molecules are similar for all model versions. However, for a small minority of molecules, the prediction shifts substantially over the span of a few versions. For most molecules that shift, the prediction becomes more accurate at later times. This Perspective investigates metrics that can help indicate which molecules will shift substantially in prediction and when the shift will occur.

Genome Nexus: A Comprehensive Resource for the Annotation and Interpretation of Genomic Variants in Cancer.

PURPOSE: Interpretation of genomic variants in tumor samples still presents a challenge in research and the clinical setting. A major issue is that information for variant interpretation is fragmented across disparate databases, and aggregation of information from these requires building extensive infrastructure. To this end, we have developed Genome Nexus, a one-stop shop for variant annotation with a user-friendly interface for cancer researchers and clinicians. METHODS: Genome Nexus (1) aggregates variant information from sources that are relevant to cancer research and clinical applications, (2) allows high-performance programmatic access to the aggregated data via a unified application programming interface, (3) provides a reference page for individual cancer variants, (4) provides user-friendly tools for annotating variants in patients, and (5) is freely available under an open source license and can be installed in a private cloud or local environment and integrated with local institutional resources. RESULTS: Genome Nexus is available at https://www.genomenexus.org. It displays annotations from more than a dozen resources including those that provide variant effect information (variant effect predictor), protein sequence annotation (Uniprot, Pfam, and dbPTM), functional consequence prediction (Polyphen-2, Mutation Assessor, and SIFT), population prevalences (gnomAD, dbSNP, and ExAC), cancer population prevalences (Cancer hotspots and SignalDB), and clinical actionability (OncoKB, CIViC, and ClinVar). We describe several use cases that demonstrate the utility of Genome Nexus to clinicians, researchers, and bioinformaticians. We cover single-variant annotation, cohort analysis, and programmatic use of the application programming interface. Genome Nexus is unique in providing a user-friendly interface specific to cancer that allows high-performance annotation of any variant including unknown ones. CONCLUSION: Interpretation of cancer genomic variants is improved tremendously by having an integrated resource for annotations. Genome Nexus is freely available under an open source license.

Specific patterns of vital sign fluctuations predict infection and enable sepsis diagnosis in pediatric burn patients.

Early recognition of the clinical signs of bloodstream infection in pediatric burn patients is key to improving survival rates in the burn unit. The objective of this study was to propose a simple scoring criteria that used readily available temperature, heart rate (HR) and mean arterial pressure (MAP) data to accurately predict bloodstream infection in pediatric burn patients. A retrospective chart review included 100 patients admitted to the pediatric burn unit for >20% total body surface area (TBSA) burn injuries. Each patient had multiple blood culture tests, and each test was treated as a separate and independent "infection event" for analysis. The time at each blood culture draw was time 0 for that event, and temperature, HR and MAP data was collected for 24 hours after the blood culture was drawn. "Infection events" included in this study had at least six complete sets of temperature, HR and MAP data entries. Median temperature, HR and MAP, as well as mean fever spikes, HR spikes and MAP dips, were compared between infection group (positive blood cultures) and control group (negative blood cultures). These vital sign fluctuations were evaluated individually and as a combination of all three as timely predictors of bloodstream infection. In addition, we tested the prediction of Gram-negative bacteria versus Gram-positive or fungi present in blood cultures. Patients in the infection group had significantly higher median temperatures (p<0.001), mean fever spikes (p<0.001) and mean HR spikes (p<0.001), compared to the control group. Using the combination scoring criteria to predict bloodstream infection, the strongest predictive values in the 24-hour timeframe had high sensitivity (93%) and specificity (81%). The predictive test metric based on vital sign spikes predicted Gram-negative bacteria, but with limited sensitivity (57%) and specificity (44%). A simple scoring criteria using a combination of fever spikes, HR spikes and MAP dips predicted bloodstream infection in pediatric burn patients, and can be feasibly implemented in routine clinical care. There is also potential to use the predictive metric to detect a few select organisms based on vital signs, however further work is necessary to enhance accuracy to levels that would allow consideration for clinical use.

Reconstruction of the Upper Extremity High-Voltage Electrical Injury: A Pediatric Burn Hospital's 13-Year Experience.

High-voltage electrical injury is a rare yet destructive class of burn injury that persists as a serious public health issue. High-voltage exposure is commonly associated with complex wounds to the upper extremities, which can be a significant challenge for burn and plastic surgeons to reconstruct. This intensive and multistage reconstructive process is especially difficult in the growing child. Maximizing upper extremity function is a top priority, as it can have a significant impact on a patient's quality of life. Therefore, the purpose of this retrospective review was to describe lessons learned during a 13-year experience at a specialized pediatric burn hospital with reconstruction of the upper extremity after severe high-voltage injury in 37 children. We found that adherence to the following principles can help promote meaningful functional recovery. These include 1) frequent assessment during early acute care for the evolving need of decompression or amputation; 2) serial surgical debridement that follows a tissue-sparing technique; 3) wound closure by skin grafting or use of flaps (particularly groin or abdominal pedicled flaps) when deep musculoskeletal structures are involved; 4) early multidisciplinary intervention for contracture prevention and management, including physical and occupational therapy, splinting, and fixation; 5) reconstructive care that focuses on the simplest possible techniques to repair chronic skin defects such as laser therapy, local tissue rearrangements, and skin grafting; 6) complex reconstruction to address deeper tissue contractures or tendon and peripheral nerve deficits; and 7) amputation with preservation of growth plates, tissue transfer, and long-term prosthetic management when limb salvage is unlikely.

Evaluating Burn Recovery Outcomes in Children With Neurodevelopmental Symptoms.

Neurodevelopmental symptoms (NS) including attention and behavioral problems, developmental delays, intellectual disabilities, and learning problems are prevalent in children with burn injuries. The presence of NS may predispose children to poorer burn injury recovery outcomes compared to children without these symptoms (non-NS). The Multicenter Benchmarking Study (MCBS) monitored recovery outcomes in children with burn injuries in real time using the Burn Outcomes Questionnaire (BOQ). The objective of this study was to retrospectively assess the long-term burn recovery outcomes in NS patients vs non-NS patients from the MCBS population. This study assessed parent-reported BOQ outcomes in a sample of 563 patients aged 5 to 18 years who were admitted for burn injuries to a pediatric burn center. A subsample of patients had reported NS (n = 181). Analyses compared BOQ outcomes within the NS subsample and the non-NS subsample (n = 382) across three longitudinal points postdischarge. The prevalence rate of NS was 32.1% in the full sample. Findings revealed statistically significant improvement in the recovery curves in all five BOQ subscales for the non-NS group and all subscales except for Compliance for the NS group across all longitudinal points. When compared to non-NS patients, NS patients had significantly poorer burn recovery outcomes on the Satisfaction and Compliance subscales. Although it is important to educate all clinicians, parents, and children on burn prevention efforts, targeted education is necessary for children with NS because they may be at greater risk for burn injury as well as worse recovery outcomes.

Health professionals' perceptions of maggot debridement therapy.

BACKGROUND: Maggot debridement therapy (MDT), or the use of maggots in dead tissue removal, has been shown to be beneficial in wound healing. Yet MDT in the US is often only used once conventional debridement methods have failed. METHOD: In this study, nine health professionals, experienced in MDT, were interviewed in order to identify and analyse the perceived societal barriers to MDT acceptance and usage in the US. RESULTS: Through qualitative analysis, using the grounded theory framework, this study found that among those interviewed, insurance reimbursement restrictions and stigmatisation of medicinal maggots were the factors driving resistance to MDT use. CONCLUSION: Specifically, the 'yuck' factor and the perception of MDT as an 'ancient' modality contributed towards MDT stigma; in addition, lack of outpatient insurance coverage deterred MDT use. These findings provide useful information regarding the perceptual and systemic barriers that prevent greater acceptance of MDT. Ultimately, these barriers must be understood if we are to facilitate MDT implementation and improve MDT usage in the future.