Search

Rationale and Objectives To train and validate machine learning models capable of classifying suspicious thoracic lesions as benign or malignant and to further classify malignant lesions by pathologic subtype while quantifying feature importance for each classification. Materials and Methods 796 patients who had undergone CT guided thoracic biopsy for a concerning thoracic lesion (79.3% lung, 11.4% mediastinum, 6.5% pleura, 2.7% chest wall) were retrospectively enrolled. Lesions were classified as malignant or benign based on ground-truth pathology result, and malignant lesions were classified as primary or secondary cancer. Clinical variables were extracted from EMR and radiology reports. Supervised binary and multiclass classification models were trained to classify lesions based on the input features and evaluated on a held-out test set. Model specific feature analyses were performed to identify variables most predictive of each class, as well as to assess the independent importance of clinical, and imaging features. Results Binary classification models achieved a top accuracy of 80.6%, with predictive features included smoking history, age, lesion size, and lesion location. Multiclass classification models achieved a top weighted average f1-score of 0.73. Features predictive of primary cancer included smoking history, race, and age, while features predictive of secondary cancer included lesion location, and a history of cancer. Conclusion Machine learning models enable classification of suspicious thoracic lesions based on clinical and imaging variables, achieving clinically useful performance while identifying importance of individual input features on a pathology-proven dataset. We believe models such as these are more likely to be trusted and adopted by clinicians.

Background Despite accounting for a minority of malignant pleural mesothelioma (MPM) diagnoses, females may experience differential survival relative to males. It is unclear if there are gender-based differences in receipt of treatment or disease-related outcomes for patients with MPM. We therefore utilized the National Cancer Database (NCDB) to assess patterns-of-care and overall survival (OS) among patients with MPM by gender. Materials and Methods Patients with histologically confirmed MPM treated from 2004 to 2013 were identified from the NCDB. The association between female gender and OS was assessed using multivariable Cox proportional hazards models with propensity score matching. Patterns-of-care were assessed using multivariable logistic regression. The overall treatment effect was tested in subsets of patients by treatment strategy, histology, and clinical stage. Results A total of 18,799 patients were identified, of whom 14,728 (78%) were male and 4071 (22%) were female. Females were statistically more likely to present at a younger age, with fewer comorbidities, and with epithelioid histology. Despite these favorable prognostic features, women were less likely to receive surgery (P ≤ .001) or chemotherapy (P ≤ .001) compared with males. On multivariable analysis, female gender was associated with improved OS (hazard ratio, 0.83; 95% confidence interval, 0.80-0.86; P ≤ .001). Gender-based survival differences were seen across all stages, but only among patients with epithelioid (P ≤ .001) and not biphasic (P = .17) or sarcomatoid (P = 1.00) histology. Conclusions Surgery and chemotherapy are disproportionately underutilized in female patients with MPM. Despite this concerning disparity, female gender is independently associated with improved survival relative to males. Further research to understand factors that lead to gender disparities in MPM is warranted.

The applicability of the results of any clinical trial will depend to a large extent on whether the study population is representative of the population seen in clinical practice. The growing older surgical population presents challenges for peri-operative researchers to ensure there is adequate representation of patients in terms of their age, sex, race and ethnicity in clinical trials. A review of purposively sampled published randomised controlled trials was performed to establish the age, sex, race and ethnicity of study participants. These data were compared to national registry data for the relevant surgical populations. We included 224 peri-operative trials that had been cited in 469 retrieved meta-analyses. Of these, 50 (22.3%) had an upper age limit to recruitment. The median (range [IQR]) difference in study population age from the registry population age was -2.4 (-6.2 to 1.0 [-34.7 to 14.5]) years for all the randomised controlled trials identified, -6.2 (-9.4 to -2.8 [-18.6 to 4.6]) years for randomised controlled trials investigating patients undergoing hip arthroplasty and - 3.4 (-9.6 to -1.1 [-34.7 to 2.9]) years for trials involving patients undergoing surgery for fractured neck of femur. In 92 (41.1%) randomised controlled trials, the proportion of each sex in the study population was more than 25% different from the proportion in the registry population. Only 5 (2.2%) published data on the race or ethnicity of participants. We conclude that peri-operative randomised controlled trials are unlikely to be representative of the age and sex of clinically treated surgical populations. Researchers must endeavour to ensure representative study populations are recruited to future clinical trials.

The adoption of steam engines for oceangoing vessels in the mid nineteenth century revolutionized shipping. On the face of it shipbuilders were presented with two choices. They could either strive ...

Purpose Fire setters who have an intellectual disability (ID) are often identified as posing a particular danger to the community although relatively little is known about their characteristics, treatment and support needs. The paper aims to discuss this issue. Design/methodology/approach This study describes the characteristics of 134 residents of low, medium and high security ID facilities in the UK who have either an index offence of arson, a violent index offence or a sexual index offence. Findings Index arson offenders who had an ID had multiple prior convictions, a history of violent offending and a high likelihood of having a comorbid mental disorder. There were many shared characteristics across the three groups. Practical implications The current study suggests that offenders who have ID who set fires have treatment needs that are similar to those of violent and sex offenders. It follows that fire setters who have an ID may also benefit from participating in more established offending behaviour treatment programs, such as cognitive behaviour therapy programs, developed for other types of offender. Originality/value This study is one of the few which has investigated the characteristics and treatment needs of persons who have an ID who set fires. In particular, it is one of the first to compare the characteristics and treatment needs for persons with ID who set fires, to those who have committed violent and sexual offences.

Background Structured assessments have been shown to assist professionals to evaluate the risk of aggression in secure services for general offender populations and more recently among adults with intellectual disabilities. There is a need to develop intellectual disability sensitive measures for predicting risk of aggression in community samples, especially tools with a focus on dynamic variables. Methods The study prospectively followed 28 participants for up to 2 months to test whether the Current Risk of Violence (CuRV) and Short Dynamic Risk Scale (SDRS) were able to predict verbal and physical aggression in a community sample of adults with intellectual disability. Results CuRV and SDRS ratings significantly predicted verbal and physical aggression over a 2-month period. Conclusions The current study supports the use of the CuRV with adults with intellectual disability living in community settings. The CuRV and SDRS are worthy of future development and evaluation in independent investigations.

Purpose/Objective(s): The COVID-19 pandemic has had considerable impact on volume of outpatient procedures, including radiation therapy, a critical treatment option for cancer patients. In order to measure the impact, we performed a retrospective review of patients treated at our multicenter institution with curative or palliative radiation over the past three years. Materials/Methods: Patients treated with radiation (n = 7,935) at our institution between 1/1/2018 and 12/31/2020 were retroactively enrolled in this IRB exempt study. Data elements such as primary cancer site, age, sex, and treatment intent were captured through our oncology analytics platform. Pearson's Chi square test for significance was used to assess a null hypothesis that there was no significant difference in treatment volume or treatment intent by disease system between 2018-2019 and 2020. Results: Median patient age in 2018-2019 was 67.3 (IQR: 59-75) vs. 67.55 (59-75) in 2020. The total number of patients starting treatment per year declined between 2018-2019 and 2020 from 1774.5 to 1606 (curative intent) and 1001 to 778 (palliative intent). Patient counts by disease system and treatment intent are summarized in the table. There were significant differences in the distribution of disease systems over time (X2 = 30.386, df = 10, P

Quantitative functional imaging has improved clinical understanding of lung disease, enhanced researchers’ abilities to develop new treatments, and has the potential to improve care for millions of patients who suffer from COPD, asthma, cystic fibrosis, and other diseases. While all imaging modalities rely on physics and computation, functional lung imaging is especially amenable to and dependent on computational approaches. Functional imaging modalities, such as hyperpolarized noble gas magnetic resonance imaging (MRI), inhaled contrast computed tomography (CT), and nuclear imaging, require complex processing strategies for synthesis, quantification, and computer-aided diagnosis. Early investigation into the use of such modalities for the development of computational metrics specifically tailored for the quantitative assessment of lung function has led to advanced machine learning strategies for classifying patients and predicting disease progression. Such developments will have a lasting impact on future diagnostic capabilities and the potential treatment of lung disease. In this chapter, we review these functional lung imaging modalities, their corresponding computational methodologies, and potential clinical significance.

IntroductionAn increasing number of people who have a history of acute coronary syndrome or cerebrovascular accident (termed cardiovascular events) are being considered for surgery. Up-to-date evidence of the impact of these prior events is needed to inform person-centred decision making. While perioperative risk for major adverse cardiac events immediately after a cardiovascular event is known to be elevated, the duration of time after the event for which the perioperative risk is increased is not clear.Methods and analysisThis is an individual patient-level database linkage study of all patients in England with at least one operation between 2007 and 2017 in the Hospital Episode Statistics Admitted Patient Care database. Data will be linked to mortality data from the Office for National Statistics up to 2018, for 30-day, 90-day and 1-year mortality and to the Myocardial Ischaemia National Audit Project, a UK registry of acute coronary syndromes. The primary outcome will be the association between time from cardiovascular event to index surgery and 30-day all-cause mortality. Additional associations we will report are all unplanned readmissions, prolonged length of stay, 30-day hospital free survival and incidence of new cardiovascular events within one postoperative year. Important subgroups will be surgery specific (invasiveness, urgency and subspecialty), type of acute coronary syndrome (ST or non-ST elevation myocardial infarction) and type of cerebrovascular accident (ischaemic or haemorrhagic stroke).Ethics and disseminationEthical approval for this observational study has been obtained from East Midlands—Nottingham 1 Research Ethics Committee; REC reference: 18/EM0403. The results of the study will be made available through peer-reviewed publications and via the Health Services Research Centre of the Royal College of Anaesthetists, London.

In this study, we present a method to identify radiologic findings associated with interstitial lung diseases (ILD), a heterogeneous collection of progressive lung diseases, from thoracic CT scans. Prior studies have relied on densely supervised methods using 2D slices or small 3D patches as input, requiring significant manual labor to create dense labels. This limits the amount of data available for algorithm development and thus hinders generalization performance. To harness available large, but sparsely labeled datasets, we present a weakly supervised method to identify imaging findings associated with ILD. We test this framework to classify and roughly localize 14 radiologic findings on the LTRC dataset of 3380 thoracic CT scans. We conduct 5-fold cross-validation and achieve 0.8 mean AUC scores on 5 out of 14 findings classification. We visualize attention energy maps which demonstrate that our classifier is able to learn representative features with meaningful differences between radiologic findings, and is capable of approximately localizing the findings of interest, thereby adding interpretability of our model (This work was supported by the USPHS under NIH grant R01-HL133889).

Knowledge about the assessment of personality disorder (PD) in people with intellectual and developmental disabilities (IDD) has improved significantly in the last 15 years. Guidelines have been developed starting with recommendations by Alexander and Cooray (2003) that informant information, observation, and interview should be employed in a convergent assessment. Specific considerations should be given to the features of IDD itself such as delay in perspective taking abilities. While initial research found widely differing prevalence of PD in people with IDD, more recent research following guidelines, has been more consistent. It has also been demonstrated that PD has an orderly relationship with the assessment of general personality and with emotional problems. Recent alterations in the assessment of PD in the general population have been found suitable for people with IDD and it has also been found that generic services for this population are suitable for those with IDD and PD.

PURPOSE The purpose of this study was to compare the effectiveness of ensemble methods (e.g., random forests) and single-model methods (e.g., logistic regression and decision trees) in predictive modeling of post-RT treatment failure and adverse events (AEs) for breast cancer patients using automatically extracted EMR data. METHODS Data from 1967 consecutive breast radiotherapy (RT) courses at one institution between 2008 and 2015 were automatically extracted from EMRs and oncology information systems using extraction software. Over 230 variables were extracted spanning the following variable segments: patient demographics, medical/surgical history, tumor characteristics, RT treatment history, and AEs tracked using CTCAEv4.0. Treatment failure was extracted algorithmically by searching posttreatment encounters for evidence of local, nodal, or distant failure. Individual models were trained using decision trees, logistic regression, random forests, and boosted decision trees to predict treatment failures and AEs. Models were fit on 75% of the data and evaluated for probability calibration and area under the ROC curve (AUC) on the remaining test set. The impact of each variable segment was assessed by retraining without the segment and measuring change in AUC (ΔAUC). RESULTS All AUC values were statistically significant (P

For the 3 histologic subtypes of malignant pleural mesothelioma (MPM)-epithelioid, sarcomatoid, and biphasic-the magnitude of benefit with surgical management remains underdefined.The National Cancer Data Base was queried for newly diagnosed nonmetastatic MPM with known histology. Patients in each histologic group were dichotomized into those receiving gross macroscopic resection versus lack thereof/no surgery. Kaplan-Meier analysis evaluated overall survival (OS) between cohorts; multivariable Cox proportional hazards modeling assessed factors associated with OS. After propensity matching, survival was evaluated for each histologic subtype with and without surgery.Overall, 4207 patients (68% epithelioid, 18% sarcomatoid, 13% biphasic) met the study criteria. Before propensity matching, patients with epithelioid disease experienced the highest median OS (14.4 months), followed by biphasic (9.5 months) and sarcomatoid (5.3 months) disease; this also persisted after propensity matching (P .001). After propensity matching, surgery was associated with significantly improved OS for epithelioid (20.9 vs. 14.7 months, P .001) and biphasic (14.5 vs. 8.8 months, P = .013) but not sarcomatoid (11.2 vs. 6.5 months, P = .140) disease. On multivariable analysis, factors predictive of poorer OS included advanced age, male gender, uninsured status, urban residence, treatment at community centers, and T4/N2 disease (all P .05). Chemotherapy and surgery were independently associated with improved OS, as was histology (all P .001).This large investigation evaluated surgical practice patterns and survival by histology for MPM and found that histology independently affects survival. Gross macroscopic resection is associated with significantly increased survival in epithelioid and biphasic, but not sarcomatoid, disease. However, the decision to perform surgery should continue to be individualized in light of available randomized data.

This study of a large, contemporary national database evaluated postoperative outcomes and overall survival (OS) for malignant pleural mesothelioma (MPM) by facility volume.The National Cancer Database was queried for newly-diagnosed non-metastatic MPM undergoing definitive surgery (extrapleural pneumonectomy (EPP) or pleurectomy/decortication (P/D)). Patients were dichotomized into those receiving therapy at a high-volume facility (HVF), defined a priori at the 90th percentile of case volume, with all others categorized as lower-volume facilities (LVFs). Statistics included multivariable logistic regression, Kaplan-Meier analysis, propensity-matching, and multivariable Cox proportional hazards modeling. Sensitivity analysis varied the dichotomized HVF-LVF cutoff and evaluated effects on postoperative outcomes and OS.Of 1307 patients, 621 (48%) were treated at LVFs and 686 (52%) at HVFs. HVFs were more often in the Middle/South Atlantic regions, and less likely in New England, South, and Midwest. Notably, 75% of procedures at HVFs were P/Ds, versus 84% at LVFs (p 0.001). Patients treated at HVFs experienced shorter length of postoperative hospitalization (p = 0.035), lower 30-day readmission rates (4.6% vs. 6.1%, p = 0.021), and lower 90-day mortality rates (10.0% vs. 14.6%, p = 0.029). Median OS for respective groups were 18 versus 15 months (p = 0.010), which were not significant following propensity-matching (p = 0.540). On multivariable analysis, facility volume did not independently predict for OS. Sensitivity analyses confirmed the postoperative outcomes and OS findings.This is the largest investigation to date assessing facility volume and outcomes following surgery for MPM. Although no independent effects on OS were observed, postoperative outcomes were more favorable at HVFs. These findings have implications for postoperative management, patient counseling, referring providers, and cost-effectiveness.

BACKGROUND The Armidilo has two scales-the risk scale and the protective scale. Research has been confined to the risk scale which appears to predict future incidents with medium to large effect sizes. There have been no publications on the use of the protective scale. METHODS The Armidilo was completed on four individuals with IDD who were either moving on from their placement or whose placement was in jeopardy because of new information or altered policies in the organization. The Armidilo was completed in the usual fashion. RESULTS Risk and protective results show that for each individual, recommendations could be made that ensured the best outcome. For two participants, restrictive placements were avoided because of the data on protective factors. CONCLSIONS The protective scale can be a powerful support for the clinician's case in offenders with IDD. The protective scale should be completed routinely for clinical evaluation.

During the course of recent research, this author has discovered similarities between aspects of classical Chinese philosophies and practices of those of traditional Canadian First Nations (Indigenous) peoples. Included in this has been a discovery that aspects of traditional leadership skills from both cultures intersect and are applicable to the work happening in a modern Canadian university. The author has also personally observed an overlap in the culture and lives of Chinese and First Nations people in modern British Columbia, continuing a 150-year tradition in this part of Canada. This paper—tying aspects of these two cultural and historic threads together—will consider the questions: What fascinating observations can be made and what personal, philosophical, and leadership lessons can be contrasted and compared, learned and shared through this historic intersection of peoples, cultures, thoughts, and practices? And can these over-lapping examples assist in solving larger problems of identity in the modern world?

In DSM-5 there has been a move to dimensional personality disorder (PD) diagnosis, incorporating personality theory in the form of the five-factor model (FFM). It proposes an alternative assessment system based on diagnostic indicators and the FFM, while retaining DSM-IV categorical criteria. Four individuals with intellectual disability are assessed for PD utilizing the Assessment of Global Personality Functioning Index (AGPF), the International Personality Disorder Examination (IPDE), and, in terms of the FFM, through an adapted version of the NEO-PI short form. PD ratings (self, staff, and observer) tended to converge for borderline, antisocial, and narcissistic PDs. NEO-PI ratings converged on Neuroticism, Extraversion, and Openness, with discrepancies on Agreeableness and Conscientiousness (staff rating lower). A structured DSM-5 system is easily usable but takes more time than a diagnostic interview.

Background. The Dynamic Risk Assessment and Management System (DRAMS) was created to measure dynamic risk in individuals with intellectual disabilities (ID). Steptoe, Lindsay, Murphy, and Young, (2...

BackgroundThere is limited empirical information on service-level outcome domains and indicators for the large number of people with intellectual disabilities being treated in forensic psychiatric hospitals.AimsThis study identified and developed the domains that should be used to measure treatment outcomes for this population.MethodA systematic review of the literature highlighted 60 studies which met eligibility criteria; they were synthesised using content analysis. The findings were refined within a consultation and consensus exercises with carers, patients and experts.ResultsThe final framework encompassed three apriorisuperordinate domains: (a) effectiveness, (b) patient safety and (c) patient and carer experience. Within each of these, further sub-domains emerged from our systematic review and consultation exercises. These included severity of clinical symptoms, offending behaviours, reactive and restrictive interventions, quality of life and patient satisfaction.ConclusionsTo index recovery, services need to measure treatment outcomes using this framework.

PurposeOver the last ten years, there has been greater interest in the diagnosis of personality disorder (PD) in people with intellectual and developmental disabilities (IDD). One important characteristic of a diagnostic system is that it should have validity as a contribution to utility. PD has been found to have a predictive relationship with violence and the purpose of this paper is to review two methods for the diagnosis of PD in offenders with IDD in order to evaluate the utility of the diagnoses.Design/methodology/approachIn total, 212 offenders with ID were recruited from three settings – maximum-security, medium/low security and community services. Diagnoses of PD in the case files were compared with a structured system of diagnosis based on DSM-IV traits.FindingsThere were significant differences between the two systems with a significantly higher frequency of PD diagnosis in the community forensic setting in the structured assessment system. There was no relationship between the case files diagnosis of PD and future violence but there was a significant predictive relationship between the structured diagnosis of PD and future violence with an AUC=0.62.Research limitations/implicationsAs with all such studies, the research is limited by the quality of the case files available to the researchers.Practical implicationsOnly the structured assessment of PD had utility for the prediction of violence. Reasons for the differences between the systems are discussed and suggestions made on how a diagnosis of PD can be structured for the busy clinician.Social implicationsThe accurate diagnosis of PD has important implications since the PD is a crucial addition to any violence risk evaluation.Originality/valueThis study is the first of its kind to review the way in which clinicians assess PD.

Contains fulltext : 199747.pdf (Author’s version postprint ) (Open Access) Background: Poor anger regulation is considered a risk factor of aggression in individuals with mild or borderline intellectual disabilities. Psychomotor therapy (PMT) targets anger regulation through body- and movement-oriented interventions. This study aims to inform practitioners on efficacy and research-base of PMT in this population. Method: This systematic review evaluated nine studies which met inclusion criteria in terms of participants, intervention procedures, outcomes and certainty of evidence. Results: Seven studies revealed a substantial reduction of aggressive behaviour or anger. Certainty of evidence was rated inconclusive in most cases due to absence of experimental control. Conclusions: We can conclude that body-oriented PMT, involving progressive relaxation and meditation procedure 'Soles of the Feet', is a promising approach. However, the paucity of studies and methodological limitations preclude classifying it as an evidence-based practice. This suggests stronger methodological research and research aimed at PMT's mechanisms of action (e.g., improved interoceptive awareness) is warranted. 10 p.

Artificial intelligence (AI) is emerging as a technology with the power to transform established industries, and with applications from automated manufacturing to advertising and facial recognition to fully auton-omous transportation. Advances in each of these domains have led some to call AI the “fourth” industrial revolution [1]. In healthcare, AI is emerging as both a productive and disruptive force across many disci-plines. This is perhaps most evident in Diagnostic Radiology and Pathology, specialties largely built around the processing and complex interpretation of medical images, where the role of AI is increasingly seen as both a boon and a threat. In Radiation Oncology as well, AI seems poised to reshape the specialty in significant ways, though the impact of AI has been relatively limited at present, and may rightly seem more distant to many, given the predominantly interpersonal and complex interventional nature of the specialty. In this overview, we will explore the current state and anticipated future impact of AI on Radiation Oncology, in detail, focusing on key topics from multiple stakeholder perspectives, as well as the role our specialty may play in helping to shape the future of AI within the larger spectrum of medicine.

Sixteen years of medical records documenting 19 births within a herd of Asian elephants ( Elephas maximus) at a private facility in the southeastern United States were reviewed. Of the 19 calves, 11 were normal at birth, requiring no additional veterinary care, and eight were abnormal, requiring veterinary care immediately or within the first week of birth. Descriptive statistics were used to evaluate morphometrics, vital signs, and behavioral milestones in newborn calves both normal and abnormal. Blood work and urinalysis results from all calves were compared to values for adult elephants. Medical management of abnormal calves is described. All calves had faster heart rates and respiratory rates than did adult elephants, but rectal temperatures were the same. Calves were precocious with regard to sitting and standing but could be very slow to nurse. The most-common medical conditions of newborn calves were umbilical abnormalities and problems associated with nursing. Two calves required cardiopulmonary resuscitation after birth but made full recoveries. Some conditions were not apparent at birth but were recognized a few hours or days later. Following veterinary intervention, six of the eight calves made full recoveries, suggesting that early identification and treatment of problems can greatly decrease mortality. This is the first report of multiple veterinary and behavioral parameters in normal and abnormal neonatal Asian elephants from a facility with a calf survival rate above 90%. This information may be helpful to other elephant-holding facilities in providing care to their newborn elephant calves.

We reviewed medical records documenting 28 pregnancies occurring within a herd of Asian elephants ( Elephas maximus) over a 20-yr (1994-2014) period at a private facility in the southeastern United States. Twenty-six pregnancies resulted in live calves and two ended in stillbirths. The 26 live births represented the offspring of 11 cows and 5 bulls. Twenty-four calves survived their first year, including two critically ill calves born after dystocias. Male and female calves occurred in almost equal numbers. Mean duration of labor in this group was 36 hr although the median duration was 13 hr. Although oxytocin was administered to several cows, parturition did not always immediately ensue. Female fecundity ranged from 1-6 calves while female age at parturition ranged from 9-46 yr. Females delivered their first calves between 9 and 26 yr of age whereas bulls sired their first calves in their 20s, on average. The number of live births and the 93% calf survival rate are among the highest reported in any western hemisphere elephant-holding facility. This may reflect the intensive management of cows before, during, and after each pregnancy, the number of experienced multiparous cows, and the skill level of staff, most of whom had worked with each other and with this herd for many years. The data presented here may assist facilities planning to breed Asian elephants.

The goal of this study is to train and assess the performance of a deep 3D convolutional network (3D-CNN) in classifying indeterminate lung nodules as either benign or malignant based solely on diagnostic-grade thoracic CT imaging. While prior studies have relied upon subjective ratings of malignancy by radiologists, our study relies only on data from subjects with biopsy-proven ground truth labels. Our dataset includes 796 patients who underwent CT-guided lung biopsy at one institution between 2012 and 2017. All patients have pathology-confirmed diagnosis (from CT-guided biopsy) and high-resolution CT imaging data acquired immediately prior to biopsy. Lesion location was manually determined using the biopsy guidance CT scan as a reference for a subset of 86 patients for this proof-of-concept study. Rather than training the network without a priori knowledge, which risks over fitting on small datasets, we employed transfer learning, taking the initial layers of our network from an existing neural network trained on a distinct but similar dataset. We then evaluated our network on a held out test set, achieving an area under the receiver operating characteristic curve (AUC) of 0.70 and a classification accuracy of 71%.

Background: Risk assessments assist professionals in the identification and management of risk of aggression. The present study aimed to systematically review evidence on the efficacy of assessments for managing the risk of physical aggression in adults with intellectual disabilities (ID).\ud \ud Methods:\ud A literature search was conducted using the databases PsycINFO, EMBASE, MEDLINE, Web of Science, and Google Scholar. Electronic and hand searches identified 14 studies that met the inclusion criteria. Standardised mean difference effect sizes Area Under Curve (AUC) were calculated for studies. Random effects subgroup analysis was used to compare different types of risk measures (Actuarial, Structured Professional Judgment and dynamic), and prospective vs. catch-up longitudinal study designs.\ud \ud Results:\ud Overall, evidence of predictive validity was found for risk measures with ID populations: (AUC) = 0.724, 95% CI [0.681, 0.768]. There was no variation in the performance of different types of risk measures, or different study design.\ud \ud Conclusions:\ud Risk assessment measures predict the likelihood of aggression in ID population and are comparable to those in mainstream populations. Further meta-analysis is necessary when risk measures are more established in this population.

Introduction Controversy exists regarding the optimal surgical technique for malignant pleural mesothelioma (MPM). We evaluated national practice patterns and outcomes of MPM treated with extrapleural pneumonectomy (EPP) versus lung-sparing extended pleurectomy/decortication (P/D). Methods The National Cancer Database was queried for patients with newly diagnosed MPM undergoing EPP or P/D. Multivariable logistic regression ascertained clinical factors independently associated with P/D receipt. Kaplan-Meier analysis was used to evaluate overall survival (OS) between cohorts; multivariable Cox proportional hazards modeling was used to evaluate factors associated with OS. Survival was then evaluated between propensity-matched populations. Results Overall, 1307 patients (271 undergoing EPP [21%] and 1036 undergoing P/D [79%]) met the criteria. Patients receiving P/D were older ( p = 0.028), whereas those undergoing EPP were more likely to live in a rural area ( p = 0.044), live farther from the treating facility ( p = 0.039), and receive treatment at an academic center ( p = 0.050). There were no differences between cohorts in 30-day readmission or mortality (all p > 0.05). The median OS times in the EPP and P/D groups were 19 versus 16 months, respectively ( p = 0.120); no differences were observed after propensity matching ( p = 0.540). Conclusions In this largest analysis of its kind to date, findings from this contemporary cohort demonstrate that P/D comprised most surgical procedures for MPM. Procedure type was influenced by sociodemographic and geographical factors, without observed differences in survival or postoperative mortality and readmission rates between techniques.