Postsurgical Pain Risk Stratification to Enhance Pain Management Workflow in Adult Patients: Design, Implementation, and Pilot Evaluation.

BACKGROUND: Exposure to opioids after surgery is the initial contact for some people who develop chronic opioid use disorder. Hence, effective postoperative pain management, with less reliance on opioids, is critical. The Perioperative Opioid Quality Improvement (POQI) program developed (1) a digital health platform leveraging patient-survey-reported risk factors and (2) a postsurgical pain risk stratification algorithm to personalize perioperative care by integrating several commercially available digital health solutions into a combined platform. Development was reduced in scope by the COVID-19 pandemic. OBJECTIVE: This pilot study aims to assess the screening performance of the risk algorithm, quantify the use of the POQI platform, and evaluate clinicians' and patients' perceptions of its utility and benefit. METHODS: A POQI platform prototype was implemented in a quality improvement initiative at a Canadian tertiary care center and evaluated from January to September 2022. After surgical booking, a preliminary risk stratification algorithm was applied to health history questionnaire responses. The estimated risk guided the patient assignment to a care pathway based on low or high risk for persistent pain and opioid use. Demographic, procedural, and medication administration data were extracted retrospectively from the electronic medical record. Postoperative inpatient opioid use of >90 morphine milligram equivalents per day was the outcome used to assess algorithm performance. Data were summarized and compared between the low- and high-risk groups. POQI use was assessed by completed surveys on postoperative days 7, 14, 30, 60, 90, and 120. Semistructured patient and clinician interviews provided qualitative feedback on the platform. RESULTS: Overall, 276 eligible patients were admitted for colorectal procedures. The risk algorithm stratified 203 (73.6%) as the low-risk group and 73 (26.4%) as the high-risk group. Among the 214 (77.5%) patients with available data, high-risk patients were younger than low-risk patients (age: median 53, IQR 40-65 years, vs median 59, IQR 49-69 years, median difference five years, 95% CI 1-9; P=.02) and were more often female patients (45/73, 62% vs 80/203, 39.4%; odds ratio 2.5, 95% CI 1.4-4.5; P=.002). The risk stratification was reasonably specific (true negative rate=144/200, 72%) but not sensitive (true positive rate=10/31, 32%). Only 39.7% (85/214) patients completed any postoperative quality of recovery questionnaires (only 14, 6.5% patients beyond 60 days after surgery), and 22.9% (49/214) completed a postdischarge medication survey. Interviewed participants welcomed the initiative but noted usability issues and poor platform education. CONCLUSIONS: An initial POQI platform prototype was deployed operationally; the risk algorithm had reasonable specificity but poor sensitivity. There was a significant loss to follow-up in postdischarge survey completion. Clinicians and patients appreciated the potential impact of preemptively addressing opioid exposure but expressed shortcomings in the platform's design and implementation. Iterative platform redesign with additional features and reevaluation are required before broader implementation.

Identification and validation of a machine learning model of complete response to radiation in rectal cancer reveals immune infiltrate and TGFß as key predictors.

BACKGROUND: It is uncertain which biological features underpin the response of rectal cancer (RC) to radiotherapy. No biomarker is currently in clinical use to select patients for treatment modifications. METHODS: We identified two cohorts of patients (total N = 249) with RC treated with neoadjuvant radiotherapy (45Gy/25) plus fluoropyrimidine. This discovery set included 57 cases with pathological complete response (pCR) to chemoradiotherapy (23%). Pre-treatment cancer biopsies were assessed using transcriptome-wide mRNA expression and targeted DNA sequencing for copy number and driver mutations. Biological candidate and machine learning (ML) approaches were used to identify predictors of pCR to radiotherapy independent of tumour stage. Findings were assessed in 107 cases from an independent validation set (GSE87211). FINDINGS: Three gene expression sets showed significant independent associations with pCR: Fibroblast-TGFß Response Signature (F-TBRS) with radioresistance; and cytotoxic lymphocyte (CL) expression signature and consensus molecular subtype CMS1 with radiosensitivity. These associations were replicated in the validation cohort. In parallel, a gradient boosting machine model comprising the expression of 33 genes generated in the discovery cohort showed high performance in GSE87211 with 90% sensitivity, 86% specificity. Biological and ML signatures indicated similar mechanisms underlying radiation response, and showed better AUC and p-values than published transcriptomic signatures of radiation response in RC. INTERPRETATION: RCs responding completely to chemoradiotherapy (CRT) have biological characteristics of immune response and absence of immune inhibitory TGFß signalling. These tumours may be identified with a potential biomarker based on a 33 gene expression signature. This could help select patients likely to respond to treatment with a primary radiotherapy approach as for anal cancer. Conversely, those with predicted radioresistance may be candidates for clinical trials evaluating addition of immune-oncology agents and stromal TGFß signalling inhibition. FUNDING: The Stratification in Colorectal Cancer Consortium (S:CORT) was funded by the Medical Research Council and Cancer Research UK (MR/M016587/1).

Tissue-free liquid biopsies combining genomic and methylation signals for minimal residual disease detection in patients with early colorectal cancer from the UK TRACC Part B study.

PURPOSE: Absence of post-operative circulating tumour DNA (ctDNA) identifies resected colorectal cancer (CRC) patients with low recurrence risk for adjuvant chemotherapy (ACT) de-escalation. We present the largest resected CRC cohort to date with tissue-free minimal residual disease (MRD) detection. DESIGN: TRACC included stage I-III resectable CRC patients. Prospective longitudinal plasma collection for ctDNA occurred pre- and post-surgery, post-ACT, every 3m for year 1 and every 6m in years 2 and 3 with imaging annually. The Guardant Reveal assay evaluated genomic and methylation signals. The primary endpoint was 2yr recurrence free survival (RFS) by post-operative ctDNA detection. (NCT04050345) Results: Between December 2016 and August 2022, 1203 were patients enrolled. Plasma samples (n=997) from 214 patients were analysed. 143 patients were evaluable for the primary endpoint; 92 (64.3%) colon, 51 (35.7%) rectal; 2 (1.4%) stage I, 64 (44.8%) stage II, 77 (53.8%) stage III. Median follow-up was 30.3m (95% CI: 29.5-31.3). 2yr RFS was 91.1% in patients with ctDNA not detected post-operatively and 50.4% in those with ctDNA detected (HR 6.5 [2.96-14.5] p<0.0001). Landmark negative predictive value (NPV) was 91.2% (95% CI 83.9-95.9). Longitudinal sensitivity and specificity were 62.1% (95% CI 42.2-79.3) and 85.9% (95% CI 78.9-91.3) respectively. Median lead-time from ctDNA detection to radiological recurrence was 7.3m (IQR 3.3-12.5; n=9). CONCLUSIONS: Tissue-free MRD detection with longitudinal sampling predicts recurrence in stage I-III CRC without need for tissue sequencing. NPV is high supporting ACT de-escalation in patients with ctDNA not detected post-operatively, now being investigated in the UK TRACC Part C study.

Deep learning for dual detection of microsatellite instability and POLE mutations in colorectal cancer histopathology.

In the spectrum of colorectal tumors, microsatellite-stable (MSS) tumors with DNA polymerase ε (POLE) mutations exhibit a hypermutated profile, holding the potential to respond to immunotherapy similarly to their microsatellite-instable (MSI) counterparts. Yet, due to their rarity and the associated testing costs, systematic screening for these mutations is not commonly pursued. Notably, the histopathological phenotype resulting from POLE mutations is theorized to resemble that of MSI. This resemblance not only could facilitate their detection by a transformer-based Deep Learning (DL) system trained on MSI pathology slides, but also indicates the possibility for MSS patients with POLE mutations to access enhanced treatment options, which might otherwise be overlooked. To harness this potential, we trained a Deep Learning classifier on a large dataset with the ground truth for microsatellite status and subsequently validated its capabilities for MSI and POLE detection across three external cohorts. Our model accurately identified MSI status in both the internal and external resection cohorts using pathology images alone. Notably, with a classification threshold of 0.5, over 75% of POLE driver mutant patients in the external resection cohorts were flagged as "positive" by a DL system trained on MSI status. In a clinical setting, deploying this DL model as a preliminary screening tool could facilitate the efficient identification of clinically relevant MSI and POLE mutations in colorectal tumors, in one go.

Erdosteine in children and adults with bronchiectasis (BETTER trial): study protocol for a multicentre, double-blind, randomised controlled trial.

INTRODUCTION: Bronchiectasis is a worldwide chronic lung disorder where exacerbations are common. It affects people of all ages, but especially Indigenous populations in high-income nations. Despite being a major contributor to chronic lung disease, there are no licensed therapies for bronchiectasis and there remain relatively few randomised controlled trials (RCTs) conducted in children and adults. Our RCT will address some of these unmet needs by evaluating whether the novel mucoactive agent, erdosteine, has a therapeutic role in children and adults with bronchiectasis.Our primary aim is to determine in children and adults aged 2-49 years with bronchiectasis whether regular erdosteine over a 12-month period reduces acute respiratory exacerbations compared with placebo. Our primary hypothesis is that people with bronchiectasis who regularly use erdosteine will have fewer exacerbations than those receiving placebo.Our secondary aims are to determine the effect of the trial medications on quality of life (QoL) and other clinical outcomes (exacerbation duration, time-to-next exacerbation, hospitalisations, lung function, adverse events). We will also assess the cost-effectiveness of the intervention. METHODS AND ANALYSIS: We are undertaking an international multicentre, double-blind, placebo-RCT to evaluate whether 12 months of erdosteine is beneficial for children and adults with bronchiectasis. We will recruit 194 children and adults with bronchiectasis to a parallel, superiority RCT at eight sites across Australia, Malaysia and Philippines. Our primary endpoint is the rate of exacerbations over 12 months. Our main secondary outcomes are QoL, exacerbation duration, time-to-next exacerbation, hospitalisations and lung function. ETHICS AND DISSEMINATION: The Human Research Ethics Committees (HREC) of Children's Health Queensland (for all Australian sites), University of Malaya Medical Centre (Malaysia) and St. Luke's Medical Centre (Philippines) approved the study. We will publish the results and share the outcomes with the academic and medical community, funding and relevant patient organisations. TRIAL REGISTRATION NUMBER: ACTRN12621000315819.

Effect of repeated post-resistance exercise cold or hot water immersion on in-season inflammatory responses in academy rugby players: a randomised controlled cross-over design.

PURPOSE: Uncertainty exists if post-resistance exercise hydrotherapy attenuates chronic inflammatory and hormone responses. The effects of repeated post-resistance exercise water immersion on inflammatory and hormone responses in athletes were investigated. METHODS: Male, academy Super Rugby players (n = 18, 19.9 ± 1.5 y, 1.85 ± 0.06 m, 98.3 ± 10.7 kg) participated in a 12-week programme divided into 3 × 4-week blocks of post-resistance exercise water immersion (either, no immersion control [CON]; cold [CWI]; or hot [HWI] water immersion), utilising a randomised cross-over pre-post design. Fasted, morning blood measures were collected prior to commencement of first intervention block, and every fourth week thereafter. Linear mixed-effects models were used to analyse main (treatment, time) and interaction effects. RESULTS: Repeated CWI (p = 0.025, g = 0.05) and HWI (p < 0.001, g = 0.62) reduced creatine kinase (CK), compared to CON. HWI decreased (p = 0.013, g = 0.59) interleukin (IL)-1ra, compared to CON. HWI increased (p < 0.001-0.026, g = 0.06-0.17) growth factors (PDGF-BB, IGF-1), compared to CON and CWI. CWI increased (p = 0.004, g = 0.46) heat shock protein-72 (HSP-72), compared to HWI. CONCLUSION: Post-resistance exercise CWI or HWI resulted in trivial and moderate reductions in CK, respectively, which may be partly due to hydrostatic effects of water immersion. Post-resistance exercise HWI moderately decreased IL-1ra, which may be associated with post-resistance exercise skeletal muscle inflammation influencing chronic resistance exercise adaptive responses. Following post-resistance exercise water immersion, CWI increased HSP-72 suggesting a thermoregulatory response indicating improved adaptive inflammatory responses to temperature changes, while HWI increased growth factors (PDGF-BB, IGF-1) indicating different systematic signalling pathway activation. Our data supports the continued use of post-resistance exercise water immersion recovery strategies of any temperature during in-season competition phases for improved inflammatory adaptive responses in athletes.

Prediction models for post-discharge mortality among under-five children with suspected sepsis in Uganda: A multicohort analysis.

In many low-income countries, over five percent of hospitalized children die following hospital discharge. The lack of available tools to identify those at risk of post-discharge mortality has limited the ability to make progress towards improving outcomes. We aimed to develop algorithms designed to predict post-discharge mortality among children admitted with suspected sepsis. Four prospective cohort studies of children in two age groups (0-6 and 6-60 months) were conducted between 2012-2021 in six Ugandan hospitals. Prediction models were derived for six-months post-discharge mortality, based on candidate predictors collected at admission, each with a maximum of eight variables, and internally validated using 10-fold cross-validation. 8,810 children were enrolled: 470 (5.3%) died in hospital; 257 (7.7%) and 233 (4.8%) post-discharge deaths occurred in the 0-6-month and 6-60-month age groups, respectively. The primary models had an area under the receiver operating characteristic curve (AUROC) of 0.77 (95%CI 0.74-0.80) for 0-6-month-olds and 0.75 (95%CI 0.72-0.79) for 6-60-month-olds; mean AUROCs among the 10 cross-validation folds were 0.75 and 0.73, respectively. Calibration across risk strata was good: Brier scores were 0.07 and 0.04, respectively. The most important variables included anthropometry and oxygen saturation. Additional variables included: illness duration, jaundice-age interaction, and a bulging fontanelle among 0-6-month-olds; and prior admissions, coma score, temperature, age-respiratory rate interaction, and HIV status among 6-60-month-olds. Simple prediction models at admission with suspected sepsis can identify children at risk of post-discharge mortality. Further external validation is recommended for different contexts. Models can be digitally integrated into existing processes to improve peri-discharge care as children transition from the hospital to the community.

Multi-institutional evaluation of a Pareto navigation guided automated radiotherapy planning solution for prostate cancer.

BACKGROUND: Current automated planning solutions are calibrated using trial and error or machine learning on historical datasets. Neither method allows for the intuitive exploration of differing trade-off options during calibration, which may aid in ensuring automated solutions align with clinical preference. Pareto navigation provides this functionality and offers a potential calibration alternative. The purpose of this study was to validate an automated radiotherapy planning solution with a novel multi-dimensional Pareto navigation calibration interface across two external institutions for prostate cancer. METHODS: The implemented 'Pareto Guided Automated Planning' (PGAP) methodology was developed in RayStation using scripting and consisted of a Pareto navigation calibration interface built upon a 'Protocol Based Automatic Iterative Optimisation' planning framework. 30 previous patients were randomly selected by each institution (IA and IB), 10 for calibration and 20 for validation. Utilising the Pareto navigation interface automated protocols were calibrated to the institutions' clinical preferences. A single automated plan (VMATAuto) was generated for each validation patient with plan quality compared against the previously treated clinical plan (VMATClinical) both quantitatively, using a range of DVH metrics, and qualitatively through blind review at the external institution. RESULTS: PGAP led to marked improvements across the majority of rectal dose metrics, with Dmean reduced by 3.7 Gy and 1.8 Gy for IA and IB respectively (p < 0.001). For bladder, results were mixed with low and intermediate dose metrics reduced for IB but increased for IA. Differences, whilst statistically significant (p < 0.05) were small and not considered clinically relevant. The reduction in rectum dose was not at the expense of PTV coverage (D98% was generally improved with VMATAuto), but was somewhat detrimental to PTV conformality. The prioritisation of rectum over conformality was however aligned with preferences expressed during calibration and was a key driver in both institutions demonstrating a clear preference towards VMATAuto, with 31/40 considered superior to VMATClinical upon blind review. CONCLUSIONS: PGAP enabled intuitive adaptation of automated protocols to an institution's planning aims and yielded plans more congruent with the institution's clinical preference than the locally produced manual clinical plans.

Digital Spatial Profiling Identifies Distinct Molecular Signatures of Vascular Lesions in Pulmonary Arterial Hypertension.

RATIONALE: Idiopathic Pulmonary Arterial Hypertension (IPAH) is characterized by extensive pulmonary vascular remodeling due to plexiform and obliterative lesions, media hypertrophy, inflammatory cell infiltration, and alterations of the adventitia. OBJECTIVE: Test the hypothesis that microscopic IPAH vascular lesions express unique molecular profiles, which collectively are different from control pulmonary arteries. METHODS: We used digital spatial transcriptomics to profile the genome-wide differential transcriptomic signature of key pathological lesions (plexiform, obliterative, intima+media hypertrophy, and adventitia) in IPAH lungs (n= 11) and compared these data to the intima+media and adventitia of control pulmonary artery (n=5). RESULTS: We detected 8273 transcripts in the IPAH lesions and control lung pulmonary arteries. Plexiform lesions and IPAH adventitia exhibited the greatest number of differentially expressed genes when compared with intima-media hypertrophy and obliterative lesions. Plexiform lesions in IPAH showed enrichment for (i) genes associated with TGFß-signaling and (ii) mutated genes affecting the extracellular matrix and endothelial-mesenchymal transformation. Plexiform lesions and IPAH adventitia showed upregulation of genes involved in immune and interferon signaling, coagulation, and complement pathways. Cellular deconvolution indicated variability in the number of vascular and inflammatory cells between IPAH lesions, which underlies the differential transcript profiling. CONCLUSIONS: IPAH lesions express unique molecular transcript profiles enriched for pathways involving pathogenetic pathways, including genetic disease drivers, innate and acquired immunity, hypoxia sensing, and angiogenesis signaling. These data provide a rich molecular-structural framework in IPAH vascular lesions that inform novel biomarkers and therapeutic targets in this highly morbid disease.

Gut Microbiome and Metabolic and Immune Indices in Males with or without Evidence of Metabolic Dysregulation.

Background: The contributions of the gut microbiota to obesity and metabolic disease represent a potentially modifiable factor that may explain variation in risk between individuals. This study aimed to explore relationships among microbial composition and imputed functional attributes, a range of soluble metabolic and immune indices, and gene expression markers in males with or without evidence of metabolic dysregulation (MetDys). Methods: This case-control study included healthy males (n=15; 41.9±11.7 years; body mass index [BMI], 22.9±1.2 kg/m2) and males with evidence of MetDys (n=14; 46.6±10.0 years; BMI, 35.1±3.3 kg/m2) who provided blood and faecal samples for assessment of a range of metabolic and immune markers and microbial composition using 16S rRNA gene sequencing. Metagenomic functions were imputed from microbial sequence data for analysis. Results: In addition to elevated values in a range of traditional metabolic, adipokine and inflammatory indices in the MetDys group, 23 immunomodulatory genes were significantly altered in the MetDys group. Overall microbial diversity did not differ between groups; however, a trend for a higher relative abundance of the Bacteroidetes (P=0.06) and a lower relative abundance of the Verrucomicrobia (P=0.09) phyla was noted in the MetDys group. Using both family- and genera-level classifications, a partial least square discriminant analysis revealed unique microbial signatures between the groups. Conclusion: These findings confirm the need for ongoing investigations in human clinical cohorts to further resolve the relationships between the gut microbiota and metabolic and immune markers and risk for metabolic disease.

Multi-centre evaluation of variation in cumulative dose assessment in reirradiation scenarios.

BACKGROUND AND PURPOSE: Safe reirradiation relies on assessment of cumulative doses to organs at risk (OARs) across multiple treatments. Different clinical pathways can result in inconsistent estimates. Here, we quantified the consistency of cumulative dose to OARs across multi-centre clinical pathways. MATERIAL AND METHODS: We provided DICOM planning CT, structures and doses for two reirradiation cases: head & neck (HN) and lung. Participants followed their standard pathway to assess the cumulative physical and EQD2 doses (with provided α/ß values), and submitted DVH metrics and a description of their pathways. Participants could also submit physical dose distributions from Course 1 mapped onto the CT of Course 2 using their best available tools. To assess isolated impact of image registrations, a single observer accumulated each submitted spatially mapped physical dose for every participating centre. RESULTS: Cumulative dose assessment was performed by 24 participants. Pathways included rigid (n = 15), or deformable (n = 5) image registration-based 3D dose summation, visual inspection of isodose line contours (n = 1), or summation of dose metrics extracted from each course (n = 3). Largest variations were observed in near-maximum cumulative doses (25.4 - 41.8 Gy for HN, 2.4 - 33.8 Gy for lung OARs), with lower variations in volume/dose metrics to large organs. A standardised process involving spatial mapping of the first course dose to the second course CT followed by summation improved consistency for most near-maximum dose metrics in both cases. CONCLUSION: Large variations highlight the uncertainty in reporting cumulative doses in reirradiation scenarios, with implications for outcome analysis and understanding of published doses. Using a standardised workflow potentially including spatially mapped doses improves consistency in determination of accumulated dose in reirradiation scenarios.

Digital spatial profiling identifies molecular changes involved in development of colitis-associated colorectal cancer.

Objective: Chronic colonic inflammation seen in inflammatory bowel disease (IBD) is a risk factor for colorectal cancer (CRC). Colitis-associated cancers (CAC) are molecularly different from sporadic CRC. This study aimed to evaluate spatially defined molecular changes associated with neoplastic progression to identify mechanisms of action and potential biomarkers for prognostication. Design: IBD patients who had undergone colectomy for treatment of their IBD or dysplasia were identified from an institutional database. Formalin-fixed paraffin embedded samples from areas of normal, inflamed, dysplastic and adenocarcinoma tissue were identified for digital spatial profiling using the Nanostring GeoMx™ Cancer Transcriptome Atlas. RNA expression and quantification of 1812 genes was measured and analysed in a spatial context to compare differences in gene expression. Results: Sixteen patients were included, nine patients had CAC, two had dysplasia only and five had colitis only. Significant, step-wise differences in gene expression were seen between tissue types, mainly involving progressive over-expression of collagen genes associated with stromal remodelling. Similarly, MYC over-expression was associated with neoplastic progression. Comparison of normal and inflamed tissue from patients who progressed to those who did not also showed significant differences in immune-related genes, including under-expression of thte chemokines CCL18, CCL25 and IL-R7, as well as CD3, CD6 and lysozyme. The known oncogene CD24 was significantly overexpressed. Conclusion: Both tissue types and patient groups are molecularly distinguishable on the basis of their gene expression patterns. Further prospective work is necessary to confirm these differences and establish their clinical significance and potential utility as biomarkers.

Synthesis of steroidal inhibitors for Mycobacterium tuberculosis.

Oxidised derivatives of cholesterol have been shown to inhibit the growth of Mycobacterium tuberculosis (Mtb). The bacteriostatic activity of these compounds has been attributed to their inhibition of CYP125A1 and CYP142A1, two metabolically critical cytochromes P450 that initiate degradation of the sterol side chain. Here, we synthesise and characterise an extensive library of 28 cholesterol derivatives to develop a structure-activity relationship for this class of inhibitors. The candidate compounds were evaluated for MIC with virulent Mtb and in binding studies with CYP125A1 and CYP142A1 from Mtb.

TcrXY is an acid-sensing two-component transcriptional regulator of Mycobacterium tuberculosis required for persistent infection.

The ability of Mycobacterium tuberculosis (Mtb) to persist in the host complicates and prolongs tuberculosis (TB) patient chemotherapy. Here we demonstrate that a neglected two-component system (TCS) of Mtb, TcrXY, is an autoregulated acid-sensing TCS that controls a functionally diverse 70-gene regulon required for bacterial persistence. Characterisation of two representatives of this regulon, Rv3706c and Rv3705A, implicate these genes as key determinants for the survival of Mtb in vivo by serving as important effectors to mitigate redox stress at acidic pH. We show that genetic silencing of the response regulator tcrX using CRISPR interference attenuates the persistence of Mtb during chronic mouse infection and improves treatment with the two front-line anti-TB drugs, rifampicin and isoniazid. We propose that targeting TcrXY signal transduction blocks the ability of Mtb to sense and respond to acid stress, resulting in a disordered program of persistence to render the organism vulnerable to existing TB chemotherapy.

Automated curation of large-scale cancer histopathology image datasets using deep learning.

BACKGROUND: Artificial intelligence (AI) has numerous applications in pathology, supporting diagnosis and prognostication in cancer. However, most AI models are trained on highly selected data, typically one tissue slide per patient. In reality, especially for large surgical resection specimens, dozens of slides can be available for each patient. Manually sorting and labelling whole-slide images (WSIs) is a very time-consuming process, hindering the direct application of AI on the collected tissue samples from large cohorts. In this study we addressed this issue by developing a deep-learning (DL)-based method for automatic curation of large pathology datasets with several slides per patient. METHODS: We collected multiple large multicentric datasets of colorectal cancer histopathological slides from the United Kingdom (FOXTROT, N = 21,384 slides; CR07, N = 7985 slides) and Germany (DACHS, N = 3606 slides). These datasets contained multiple types of tissue slides, including bowel resection specimens, endoscopic biopsies, lymph node resections, immunohistochemistry-stained slides, and tissue microarrays. We developed, trained, and tested a deep convolutional neural network model to predict the type of slide from the slide overview (thumbnail) image. The primary statistical endpoint was the macro-averaged area under the receiver operating curve (AUROCs) for detection of the type of slide. RESULTS: In the primary dataset (FOXTROT), with an AUROC of 0.995 [95% confidence interval [CI]: 0.994-0.996] the algorithm achieved a high classification performance and was able to accurately predict the type of slide from the thumbnail image alone. In the two external test cohorts (CR07, DACHS) AUROCs of 0.982 [95% CI: 0.979-0.985] and 0.875 [95% CI: 0.864-0.887] were observed, which indicates the generalizability of the trained model on unseen datasets. With a confidence threshold of 0.95, the model reached an accuracy of 94.6% (7331 classified cases) in CR07 and 85.1% (2752 classified cases) for the DACHS cohort. CONCLUSION: Our findings show that using the low-resolution thumbnail image is sufficient to accurately classify the type of slide in digital pathology. This can support researchers to make the vast resource of existing pathology archives accessible to modern AI models with only minimal manual annotations.

Mycobacterium tuberculosis Deficient in PdtaS Cytosolic Histidine Kinase Displays Attenuated Growth and Affords Protective Efficacy against Aerosol M. tuberculosis Infection in Mice.

New control measures are urgently required to control tuberculosis (TB), as the current vaccine, Bacille Calmette-Guérin (BCG), has had a limited impact on disease spread. The identification of virulence mechanisms of Mycobacterium tuberculosis is an important strategy in vaccine design, as it permits the development of strains attenuated for growth that may have vaccine potential. In this report, we determined the role of the PdtaS response regulator in M. tuberculosis virulence and defined the vaccine potential of a pdtaS-deficient strain. Deletion of pdtaS (MtbΔpdtaS) resulted in reduced persistence of M. tuberculosis within mouse organs, which was equivalent to the persistence of the BCG vaccine in the lung and liver of infected mice. However, the generation of effector CD4+ and CD8+ T cells (CD44+CD62LloKLRG1+) was similar between wild-type M. tuberculosis and MtbΔpdtaS and greater than that elicited by BCG. Heightened immunity induced by MtbΔpdtaS compared to BCG was also observed by analysis of antigen-specific IFN-γ-secreting T cell responses induced by vaccination. MtbΔpdtaS displayed improved protection against aerosol M. tuberculosis compared to BCG, which was most apparent in the lung at 20 weeks post-infection. These results suggest that the deletion of the PdtaS response regulator warrants further appraisal as a tool to combat TB in humans.

Reassessing the putative molecular Target(s) of potent antitubercular 2-(Alkylsulfonyl)acetamides.

Simple alkyl-sulfonylacetamides have potent antitubercular activity and significantly decrease mycolic acid levels in mycobacteria. Although these compounds were originally designed to inhibit the ketoacyl synthase domain of fatty acid synthase, structure-activity relationships and biochemical evidence do not fully support fatty acid synthase as the target. In 2004, an enzyme family involved in the activation and transfer of fatty acids as acyl-adenylates was identified in mycobacteria, separate from the universal acetyl-CoA carrier mechanism. These fatty acyl-AMP ligases (FAAL), encoded by the FadD family play important roles in the biosynthesis of mycolic acids along with fatty acid metabolism and are hypothesised here to be the molecular target of the sulfonylacetamides. Due to structural similarities with the ligase's natural substrate, it is believed these compounds are exerting action via competitive inhibition of these highly potent molecular targets. The primary aim of this investigation was to synthesize an extended library of sulfonylacetamide derivatives, building upon existing structural activity relations to validate the molecular mechanism with the aid of molecular modelling, while also attempting to explore novel structural isosteres for further drug design and development. Sulfonylacetamide derivatives were modified based on the putative molecular target resulting in derivatives with improved activities towards Mycobacteriumtuberculosis (H37Rv). The most active novel derivatives reported were 19, 22b, 22c and 46 displaying MIC90 levels of 1.4, 16.0, 13.0 and 5.9 µg/mL, respectively.

seco-1-Azacubane-2-carboxylic Acid: Derivative Scope and Comparative Biological Evaluation.

The unusual and sterically constrained amino acid, seco-1-azacubane-2-carboxylic acid, was incorporated into a range of bioactive chemical templates, including enalaprilat, perindoprilat, endomorphin-2 and isoniazid, and subjected to biological testing. The endomorphin-2 derivative displayed increased activity at the δ opioid receptor, but a loss in activity was observed in the other cases, although human normal cell line evaluation suggests limited cytotoxic effects.

End-to-end prognostication in colorectal cancer by deep learning: a retrospective, multicentre study.

BACKGROUND: Precise prognosis prediction in patients with colorectal cancer (ie, forecasting survival) is pivotal for individualised treatment and care. Histopathological tissue slides of colorectal cancer specimens contain rich prognostically relevant information. However, existing studies do not have multicentre external validation with real-world sample processing protocols, and algorithms are not yet widely used in clinical routine. METHODS: In this retrospective, multicentre study, we collected tissue samples from four groups of patients with resected colorectal cancer from Australia, Germany, and the USA. We developed and externally validated a deep learning-based prognostic-stratification system for automatic prediction of overall and cancer-specific survival in patients with resected colorectal cancer. We used the model-predicted risk scores to stratify patients into different risk groups and compared survival outcomes between these groups. Additionally, we evaluated the prognostic value of these risk groups after adjusting for established prognostic variables. FINDINGS: We trained and validated our model on a total of 4428 patients. We found that patients could be divided into high-risk and low-risk groups on the basis of the deep learning-based risk score. On the internal test set, the group with a high-risk score had a worse prognosis than the group with a low-risk score, as reflected by a hazard ratio (HR) of 4·50 (95% CI 3·33-6·09) for overall survival and 8·35 (5·06-13·78) for disease-specific survival (DSS). We found consistent performance across three large external test sets. In a test set of 1395 patients, the high-risk group had a lower DSS than the low-risk group, with an HR of 3·08 (2·44-3·89). In two additional test sets, the HRs for DSS were 2·23 (1·23-4·04) and 3·07 (1·78-5·3). We showed that the prognostic value of the deep learning-based risk score is independent of established clinical risk factors. INTERPRETATION: Our findings indicate that attention-based self-supervised deep learning can robustly offer a prognosis on clinical outcomes in patients with colorectal cancer, generalising across different populations and serving as a potentially new prognostic tool in clinical decision making for colorectal cancer management. We release all source codes and trained models under an open-source licence, allowing other researchers to reuse and build upon our work. FUNDING: The German Federal Ministry of Health, the Max-Eder-Programme of German Cancer Aid, the German Federal Ministry of Education and Research, the German Academic Exchange Service, and the EU.

Encrypted federated learning for secure decentralized collaboration in cancer image analysis.

Artificial intelligence (AI) has a multitude of applications in cancer research and oncology. However, the training of AI systems is impeded by the limited availability of large datasets due to data protection requirements and other regulatory obstacles. Federated and swarm learning represent possible solutions to this problem by collaboratively training AI models while avoiding data transfer. However, in these decentralized methods, weight updates are still transferred to the aggregation server for merging the models. This leaves the possibility for a breach of data privacy, for example by model inversion or membership inference attacks by untrusted servers. Somewhat-homomorphically-encrypted federated learning (SHEFL) is a solution to this problem because only encrypted weights are transferred, and model updates are performed in the encrypted space. Here, we demonstrate the first successful implementation of SHEFL in a range of clinically relevant tasks in cancer image analysis on multicentric datasets in radiology and histopathology. We show that SHEFL enables the training of AI models which outperform locally trained models and perform on par with models which are centrally trained. In the future, SHEFL can enable multiple institutions to co-train AI models without forsaking data governance and without ever transmitting any decryptable data to untrusted servers.