Graphical Association Analysis for Identifying Variation in Provider Claims for Joint Replacement Surgery.

Identifying potentially fraudulent or wasteful medical insurance claims can be difficult due to the large amounts of data and human effort involved. We applied unsupervised machine learning to construct interpretable models which rank variations in medical provider claiming behaviour in the domain of unilateral joint replacement surgery, using data from the Australian Medicare Benefits Schedule. For each of three surgical procedures reference models of claims for each procedure were constructed and compared analytically to models of individual provider claims. Providers were ranked using a score based on fees for typical claims made in addition to those in the reference model. Evaluation of the results indicated that the top-ranked providers were likely to be unusual in their claiming patterns, with typical claims from outlying providers adding up to 192% to the cost of a procedure. The method is efficient, generalizable to other procedures and, being interpretable, integrates well into existing workflows.

Effectiveness of a purified type I collagen matrix plus the antimicrobial polyhexamethylene biguanide for use in cutaneous wounds: analysis of a population of three combined registries.

INTRODUCTION: Chronic wounds represent a significant burden to the health care system and patients. OBJECTIVE: This study determined the effectiveness of a wound scaffold comprised of PCMP for use in nonhealing, cutaneous wounds; this study analyzes pooled data from the population of 3 combined registries. MATERIALS AND METHODS: A total of 3 combined registry populations were pooled from a single-center study of 41 patients, a single-center study of 86 patients, and the RESPOND Registry of 307 patients treated at 28 centers. All 434 patients received PCMP and were followed for up to 48 weeks. Male and female patients 18 years or older with wounds between 0.2 cm2 and 200 cm2 were included. RESULTS: In total, there were 95 VLUs, 78 DFUs, 90 PIs, 73 PSWs, and 98 wounds of other etiologies analyzed. The mean baseline area, depth, and volume of all 434 wounds was 15.1 cm2, 4.9 mm, and 7.2 cm3, respectively. K-M median time to wound closure for all wounds was 19 weeks. At weeks 20, 24, 28, and 48, the frequency of wound closure for all wounds was 51%, 56%, 62%, and 72%, respectively. The median time to closure by wound type was 22 weeks for VLUs, 24 weeks for DFUs, 23 weeks for PIs, 12 weeks for PSWs, and 14 weeks for other wounds. The proportion of wounds closed were 72% (VLUs), 52% (DFUs), 63% (PIs), 95% (PSWs), and 67% (other etiologies). CONCLUSIONS: This 434-patient PCMP cohort analysis showed 72% wound closure and median time to wound closure of 19 weeks. PCMP demonstrated effectiveness for use in multiple wound types.

A Prospective Noninterventional Study of Type I Collagen Matrix Plus Polyhexamethylene Biguanide Antimicrobial for the Treatment of Venous Leg Ulcers: A Secondary Analysis.

BACKGROUND: The RESPOND registry study was the first prospective noninterventional study evaluating the real-world effectiveness of a native type 1 collagen matrix plus polyhexamethylene biguanide antimicrobial (PCMP) barrier in nonhealing wounds. PURPOSE: The objective of this secondary analysis was to describe the effects of PCMP in the subgroup of patients with venous leg ulcers (VLUs) in the RESPOND registry. METHODS: RESPOND was a 28-site, prospective, noninterventional study for up to 32 weeks. All patients (N = 307) in RESPOND received PCMP. Eligibility criteria included patients being 18 years of age and older and having cutaneous wounds, not including third-degree burns. Kaplan-Meier methods analyzed the frequency and median time to wound closure. RESULTS: For the cohort of PCMP-treated VLUs (n = 67), the mean baseline wound area was 20.07 cm2 and mean wound duration was 89 days. Wound closure frequencies were 33%, 42%, 45%, 53%, and 73% at weeks 8, 12, 16, 24, and 32, respectively. The median time to closure was 22 weeks. Incidences of achieving >60% reduction in baseline area and depth were 78% and 70%, respectively, with 87% showing a reduction of >75% in volume. CONCLUSION: PCMP appears to be a valuable adjunct for treating venous leg ulcers.

Credit Risk Modeling Using Transfer Learning and Domain Adaptation.

In the domain of credit risk assessment lenders may have limited or no data on the historical lending outcomes of credit applicants. Typically this disproportionately affects Micro, Small, and Medium Enterprises (MSMEs), for which credit may be restricted or too costly, due to the difficulty of predicting the Probability of Default (PD). However, if data from other related credit risk domains is available Transfer Learning may be applied to successfully train models, e.g., from the credit card lending and debt consolidation (CD) domains to predict in the small business lending domain. In this article, we report successful results from an approach using transfer learning to predict the probability of default based on the novel concept of Progressive Shift Contribution (PSC) from source to target domain. Toward real-world application by lenders of this approach, we further address two key questions. The first is to explain transfer learning models, and the second is to adjust features when the source and target domains differ. To address the first question, we apply Shapley values to investigate how and why transfer learning improves model accuracy, and also propose and test a domain adaptation approach to address the second. These results show that adaptation improves model accuracy in addition to the improvement from transfer learning. We extend this by proposing and testing a combined strategy of feature selection and adaptation to convert values of source domain features to better approximate values of target domain features. Our approach includes a strategy to choose features for adaptation and an algorithm to adapt the values of these features. In this setting, transfer learning appears to improve model accuracy by increasing the contribution of less predictive features. Although the percentage improvements are small, such improvements in real world lending could be of significant economic importance.

Type I collagen matrix plus polyhexamethylene biguanide antimicrobial for the treatment of cutaneous wounds.

Aim: Determine the effectiveness of purified native type I collagen matrix plus polyhexamethylene biguanide antimicrobial (PCMP) on cutaneous wounds. Materials & methods: A prospective cohort study of 307 patients (67 venous leg ulcers, 62 diabetic foot ulcers, 45 pressure ulcers, 54 post-surgical wounds and 79 other wounds) was conducted. Results: Cox wound closure for PCMP was 73% at week 32. The median time to wound closure was 17 weeks (Kaplan-Meier). The incidence of PCMP-treated wounds showing >60% reductions in areas, depths and volumes were 81, 71 and 85%, respectively. Conclusion: PCMP demonstrated clinically meaningful benefits to patients with various types of cutaneous wounds. Clinical Trial registration number: NCT03286452.

The Pathophysiology of Skin Failure vs. Pressure Injury: Conditions That Cause Integument Destruction and Their Associated Implications.

INTRODUCTION: Although integument failure commonly is attributed to pressure alone, especially when a wound develops over a bony prominence (pressure injury), all skin failure should not be attributed to pressure injuries. OBJECTIVE: A systematic review of the literature was conducted to: (1) differentiate the types of integument injury and etiology; (2) describe the anatomic and pathophysiologic factors affecting integument failure; (3) differentiate avoidable vs. unavoidable integumentary injury of nonpressure-related sources; (4) describe factors leading to integument injury, including comorbid and risk factors; and (5) briefly discuss clinical and economic importance of delineating pressure injuries from integument failure and associated risk factors in order to determine the pathophysiology underlying wound development and multiple factors capable of interacting with pressure to synergistically influence integumentary failure. METHODS: The PubMed database was searched for English-language studies during March 2020 using the key words pathophysiology, etiology, pressure ulcers, pressure injury, pressure wounds, and risk factors. RESULTS: The PubMed search yielded 1561 publications in total; of these, 59 were selected for review based on their relevance, timeliness, and subject matter, including 50 original studies of any study design, 5 review articles, and 4 public agency reports that addressed the 5 study purpose components. CONCLUSIONS: Clinicians need to better understand the pathophysiology and classification of integument injuries by underlying etiologies both avoidable and unavoidable. A more accurate diagnosis would lead to more appropriate treatment strategies, an improved quality of care for affected patients, less wasted resources and reduced financial penalties for healthcare providers, and decreased medicolegal claims.

Effect of Native Type I Collagen with Polyhexamethylene Biguanide Antimicrobial on Wounds: Interim Registry Results.

BACKGROUND: Biofilm can impair wound healing by maintaining an elevated, but ineffective, inflammatory state. This article describes interim results from the prospective RESPOND postmarketing registry evaluating the use of a native type 1, porcine collagen matrix with the embedded antimicrobial polyhexamethylene biguanide (PCMP) in the management of chronic wounds. METHODS: Adults ≥18 years of age with ≥1 appropriate wound were eligible for inclusion. Data that were final on January 26, 2018 were included in this analysis. At week 0, wounds were cleaned, debrided, and prepared as necessary and PCMP was applied, with a dressing to fix it in place. Patients received standard wound care plus PCMP weekly, up to 24 weeks, at the investigator's discretion. At each visit, wounds were assessed for area and quality of granulation tissue. RESULTS: Most common wound types (N = 63) were venous ulcers (28.6%), trauma and lacerations (22.2%), postsurgical open wounds (15.9%), pressure injuries (12.7%), and diabetic ulcers (9.5%). Median baseline wound area was 6.5 cm2; mean wound duration at baseline was 4 months. Of the 63 wounds, 43 (68.3%) achieved complete wound closure, 41 of 43 (95.3%) closed after PCMP treatment, and 2 of 43 (4.7%) after bridging to other modalities and surgical closure. Twelve out of 63 wounds were bridged to other modalities after PCMP treatment. Mean time to closure for PCMP wounds was 5.0 weeks. CONCLUSIONS: PCMP appears to be a useful adjunct for treating various wound types. PCMP use should be considered when managing chronic or acute wounds.

TIME CDST: an updated tool to address the current challenges in wound care.

Despite the understanding that wounds are a common problem affecting the individual, the health service and society as a whole, there continues to be a lack of a systematic, structured, evidence-based approach to wound management. The TIME principle was first published in 2003, 1 and has since been integrated by many into clinical practice and research. However, this tool has been criticised for its tendency to focus mainly on the wound rather than on the wider issues that the patient is presenting with. At an expert meeting held in London in 2018, this conundrum was addressed and the TIME clinical decision support tool (CDST) was elaborated upon. This article introduces the TIME CDST, explains why it is required and describes how its use is likely to benefit patients, clinicians and health-service organisations. It also explores the framework in detail, and shows why this simple and accessible framework is robust enough to facilitate consistency in the delivery of wound care and better patient outcomes. Finally, it outlines the next steps for the rollout, use and evaluation of the impact of the TIME CDST.

Management of a Complex Excoriation Disorder-induced Wound with a Viable Cryopreserved Placental Membrane.

Excoriation disorder (ED), also known as dermatotillomania, is a condition characterized by repeated "skin picking" that leads to the formation of skin lesions. Because of the similarity of its symptoms to obsessive compulsive disorder, ED is classified as a subcategory of obsessive compulsive disorder by Diagnostic and Statistical Manual of Mental Disorders Fifth Edition. Although the majority of the self-inflicted wounds are not clinically significant, many wounds lead to social and occupational dysfunction by becoming infected, chronic, and life threatening. This report describes the successful use of a viable intact cryopreserved human amniotic membrane in conjunction with selective serotonin re-uptake inhibitors in treating an ED patient who presented with a large calvarial wound of 3-year duration that had failed previous extensive medical and surgical interventions.

Visual analytics of signalling pathways using time profiles.

Data visualisation is usually a crucial first step in analysing and exploring large-scale complex data. The visualisation of proteomics time-course data on post-translational modifications presents a particular challenge that is largely unmet by existing tools and methods. To this end, we present Minardo, a novel visualisation strategy tailored for such proteomics data, in which data layout is driven by both cellular topology and temporal order. In this work, we utilised the Minardo strategy to visualise a dataset showing phosphorylation events in response to insulin. We evaluated the visualisation together with experts in diabetes and obesity, which led to new insights into the insulin response pathway. Based on this success, we outline how this layout strategy could be automated into a web-based tool for visualising a broad range of proteomics time-course data. We also discuss how the approach could be extended to include protein 3D structure information, as well as higher dimensional data, such as a range of experimental conditions. We also discuss our entry of Minardo in the international DREAM8 competition.

Defining reference sequences for Nocardia species by similarity and clustering analyses of 16S rRNA gene sequence data.

BACKGROUND: The intra- and inter-species genetic diversity of bacteria and the absence of 'reference', or the most representative, sequences of individual species present a significant challenge for sequence-based identification. The aims of this study were to determine the utility, and compare the performance of several clustering and classification algorithms to identify the species of 364 sequences of 16S rRNA gene with a defined species in GenBank, and 110 sequences of 16S rRNA gene with no defined species, all within the genus Nocardia. METHODS: A total of 364 16S rRNA gene sequences of Nocardia species were studied. In addition, 110 16S rRNA gene sequences assigned only to the Nocardia genus level at the time of submission to GenBank were used for machine learning classification experiments. Different clustering algorithms were compared with a novel algorithm or the linear mapping (LM) of the distance matrix. Principal Components Analysis was used for the dimensionality reduction and visualization. RESULTS: The LM algorithm achieved the highest performance and classified the set of 364 16S rRNA sequences into 80 clusters, the majority of which (83.52%) corresponded with the original species. The most representative 16S rRNA sequences for individual Nocardia species have been identified as 'centroids' in respective clusters from which the distances to all other sequences were minimized; 110 16S rRNA gene sequences with identifications recorded only at the genus level were classified using machine learning methods. Simple kNN machine learning demonstrated the highest performance and classified Nocardia species sequences with an accuracy of 92.7% and a mean frequency of 0.578. CONCLUSION: The identification of centroids of 16S rRNA gene sequence clusters using novel distance matrix clustering enables the identification of the most representative sequences for each individual species of Nocardia and allows the quantitation of inter- and intra-species variability.

MINER: exploratory analysis of gene interaction networks by machine learning from expression data.

BACKGROUND: The reconstruction of gene regulatory networks from high-throughput "omics" data has become a major goal in the modelling of living systems. Numerous approaches have been proposed, most of which attempt only "one-shot" reconstruction of the whole network with no intervention from the user, or offer only simple correlation analysis to infer gene dependencies. RESULTS: We have developed MINER (Microarray Interactive Network Exploration and Representation), an application that combines multivariate non-linear tree learning of individual gene regulatory dependencies, visualisation of these dependencies as both trees and networks, and representation of known biological relationships based on common Gene Ontology annotations. MINER allows biologists to explore the dependencies influencing the expression of individual genes in a gene expression data set in the form of decision, model or regression trees, using their domain knowledge to guide the exploration and formulate hypotheses. Multiple trees can then be summarised in the form of a gene network diagram. MINER is being adopted by several of our collaborators and has already led to the discovery of a new significant regulatory relationship with subsequent experimental validation. CONCLUSION: Unlike most gene regulatory network inference methods, MINER allows the user to start from genes of interest and build the network gene-by-gene, incorporating domain expertise in the process. This approach has been used successfully with RNA microarray data but is applicable to other quantitative data produced by high-throughput technologies such as proteomics and "next generation" DNA sequencing.

iHMMune-align: hidden Markov model-based alignment and identification of germline genes in rearranged immunoglobulin gene sequences.

MOTIVATION: Immunoglobulin heavy chain (IGH) genes in mature B lymphocytes are the result of recombination of IGHV, IGHD and IGHJ germline genes, followed by somatic mutation. The correct identification of the germline genes that make up a variable VH domain is essential to our understanding of the process of antibody diversity generation as well as to clinical investigations of some leukaemias and lymphomas. RESULTS: We have developed iHMMune-align, an alignment program that uses a hidden Markov model (HMM) to model the processes involved in human IGH gene rearrangement and maturation. The performance of iHMMune-align was compared to that of other immunoglobulin gene alignment utilities using both clonally related and randomly selected IGH sequences. This evaluation suggests that iHMMune-align provides a more accurate identification of component germline genes than other currently available IGH gene characterization programs. AVAILABILITY: iHMMune-align cross-platform Java executable and web interface are freely available to academic users and can be accessed at http://www.emi.unsw.edu.au/~ihmmune/.

The reliability of digital imaging in the remote assessment of wounds: defining a standard.

CONTEXT: Telemedicine has been used for remote management of many medical problems. Given the ever-expanding demands to provide increasing service with increasingly limited resources, quality care and practice efficiency can be enhanced by telemedicine. OBJECTIVE: This study was undertaken to explore the reliability of wound assessment using computer-transmitted digital imagery compared with a traditional bedside evaluation and also to assess its potential role in healthcare delivery. DESIGN/SETTING/PATIENTS: In the hospital setting, rounding vascular surgeons and a surgical resident evaluated the wounds on the service. A digital photograph was obtained with a 3.3 megapixel camera, and a wound-assessment tool was completed. A plastic surgery attending then reviewed the images at a later date and completed the same data tool. MAIN OUTCOME MEASURES: Wounds were rated for eschar, exposed bone, cellulitis, purulence, swelling, granulation tissue, granulation color, and depth using a standardized data collection tool. kappa statistics were computed for all variables, between raters. RESULTS: There were 2 phases of the study. In both phases, there was 100% agreement by the rounding physicians that the digital image was representative of the wound. Phase 1 agreement between evaluators was moderate to almost perfect, as demonstrated by kappa values (range, 0.50-0.87). In phase 2, all variable kappa values were rated as almost perfect, except the ability to evaluate depth of the wound to the millimeter, which was rated as substantial. CONCLUSIONS: The ability to accurately evaluate a wound on the basis of a digital image is possible. However, it requires training of participants and is facilitated by use of an assessment tool. With these caveats, evaluation of wounds using digital images is equivalent to bedside examination. This technology can improve practice efficiency, provide needed expertise at remote sites, and is an acceptable alternative method of wound assessment.

A triangular pattern for botox forehead rejuvenation.

The authors contend that their triangular pattern of Botox administration provides reproducible correction of both static and dynamic forehead wrinkles with minimal risk of brow and upper lid ptosis. Further, by varying dosage and injection technique, mimetic function may be preserved or obliterated.

Activation of macrophage promatrix metalloproteinase-9 by lipopolysaccharide-associated proteinases.

LPS induces an up-regulation of promatrix metalloproteinase-9 (proMMP9) gene expression in cells of the monocyte/macrophage lineage. We demonstrate here that LPS preparations are also able to activate proMMP9 made by human macrophages or THP-1 cells via LPS-associated proteinases, which cleave the N-terminal propeptide at a site or sites close to the one cleaved upon activation with organomercurial compounds. LPS-associated proteinases are serine proteinases that are able to cleave denatured collagens (gelatin) and the mammalian serine proteinase inhibitor, alpha(1)-proteinase inhibitor, thereby pushing the balance of extracellular matrix turnover even further toward degradation. A low molecular mass, low affinity inhibitor of MMP9, possibly derived from the propeptide, is generated during proMMP9 activation. However, inhibition of the LPS-associated proteinases had no effect on proMMP9 synthesis, indicating that their proteolytic activity was not required for signaling the up-regulation of the proMMP9 gene.