Predict Treatment Outcome Research Articles

Cognition and Ventral Attention Network Connectivity: Associations With Treatment Response in Posttraumatic Stress Disorder.

Posttraumatic stress disorder (PTSD) is a highly heterogeneous disorder, which makes it difficult to link clinical phenotypes with biomarkers to improve treatment outcomes. Findings from previous studies suggest that cognitive measures such as verbal memory or attention paired with within-ventral attention network (VAN) or salience network resting-state functional connectivity may predict treatment response among individuals with PTSD. In a sample comprising 20 individuals with PTSD and 10 healthy control group individuals, the investigators subtyped individuals by using both discriminant function analysis and standardized norms for a single measure of memory and neuropsychological batteries of memory, attention, and executive functioning; attempted to replicate previous findings of lower within-VAN connectivity among individuals with cognitive impairment; and explored whether within-VAN connectivity paired with cognitive impairment predicted treatment outcomes. PTSD patients with cognitive impairment (defined by using a discriminant function analysis with verbal memory performance) had greater within-VAN resting-state functional connectivity compared with control group individuals and cognitively intact PTSD patients at a level that fell short of statistical significance (F=3.41; df=2, 21; ηp2=0.237). The interaction between verbal memory performance and within-VAN connectivity also predicted treatment-related change in PTSD symptoms at a level that also fell short of statistical significance (β=-0.442). These findings somewhat support the clinical utility of identifying cognitive phenotypes within PTSD (by using discriminant function analysis and verbal memory performance) to predict treatment outcomes.

Methodological choices and clinical usefulness for machine learning predictions of outcome in Internet-based cognitive behavioural therapy

BackgroundWhile psychological treatments are effective, a substantial portion of patients do not benefit enough. Early identification of those may allow for adaptive treatment strategies and improved outcomes. We aimed to evaluate the clinical usefulness of machine-learning (ML) models predicting outcomes in Internet-based Cognitive Behavioural Therapy, to compare ML-related methodological choices, and guide future use of these.MethodsEighty main models were compared. Baseline variables, weekly symptoms, and treatment activity were used to predict treatment outcomes in a dataset of 6695 patients from regular care.ResultsWe show that the best models use handpicked predictors and impute missing data. No ML algorithm shows clear superiority. They have a mean balanced accuracy of 78.1% at treatment week four, closely matched by regression (77.8%).ConclusionsML surpasses the benchmark for clinical usefulness (67%). Advanced and simple models perform equally, indicating a need for more data or smarter methodological designs to confirm advantages of ML.

Simple-Challenging-Difficult (SCD) Difficulty Classification for Vertical Bone Augmentation.

To propose a new difficulty classification for vertical bone augmentation (VBA) based on different defect morphologies. VBA procedures for dental implant placement present significant biological and technical challenges. Among the various techniques, guided bone regeneration (GBR) provides an optimal balance between the anticipated bone gain and the likelihood of postoperative complications. Understanding the specific configuration of defects and adjacent bone peaks is essential for tailoring treatment strategies and improving outcomes. The proposed Simple-Challenging-Difficult (SCD) difficulty classification was based on defect morphology (V-shaped, U-shaped, VV-shaped), including defect size (Height: < 5 mm, 5-8 mm, and > 8 mm), proximity of neighboring bony walls (Width: < 10 mm, 10-20 mm, and > 20 mm), as well as predictability of treatment outcomes. The proposed difficulty classification for VBA serves as a guide for selecting the most appropriate GBR treatment modality and sequence for safe and predictable management of VBA in implant therapy. In addition, when determining the preferred treatment, it is again essential to consider site-specific and patient-related factors alongside the clinician's surgical experience and skill. Identifying defect patterns and bone peak structures is crucial, and the proposed classification assists in decision-making in VBA treatment.

Multimodal imaging-based treatment recommendations for managing submacular hemorrhage.

Submacular haemorrhage (SMH) is an emergency, and the most important immediate action in the treatment of SMH is the early displacement or evacuation of subretinal heme from below the fovea, followed by simultaneous or sequential treatment of the underlying cause. Photoreceptor damage can occur immediately after the onset of SMH for a variety of reasons, including toxins released from the blood, the diffusion barrier created by the blood for oxygen delivery and nutrition to the outer retinal layers, and shearing forces on the outer retinal layers, resulting in permanent visual deterioration. A clinician's decision to treat SMH is influenced by a number of factors, including presenting visual acuity, duration of visual symptoms, SMH aetiology and characteristics, availability of intraocular gases and tissue plasminogen activator, and pars plana vitrectomy facilities. For many clinicians, the duration of visual symptoms is the most important and first consideration when planning SMH treatment. Very little emphasis is given to the SMH's imaging characteristics. Currently, there are several treatment options for SMH removal. There is a need to develop a simplified treatment algorithm for SMH that is less reliant on the patient's visual complaints, considers heme characteristics on basic retinal imaging, and has the potential to achieve uniform and predictable treatment outcomes in real-world situations. In this short article, we discuss the various factors that can assist clinicians in the management of SMH and present a simplified treatment algorithm based on the SMH's retinal imaging characteristics.

Multiomics-Based Outcome Prediction in Personalized Ultra-Fractionated Stereotactic Adaptive Radiotherapy (PULSAR).

Objectives: This retrospective study aims to develop a multiomics approach that integrates radiomics, dosiomics, and delta features to predict treatment responses in brain metastasis (BM) patients undergoing PULSAR. Methods: A retrospective study encompassing 39 BM patients with 69 lesions treated with PULSAR was undertaken. Radiomics, dosiomics, and delta features were extracted from both pre-treatment and intra-treatment MRI scans alongside dose distributions. Six individual models, alongside an ensemble feature selection (EFS) model, were evaluated. The classification task focused on distinguishing between two lesion groups based on whether they exhibited a volume reduction of more than 20% at follow-up. Performance metrics, including sensitivity, specificity, accuracy, precision, F1 score, and the area under the receiver operating characteristic (ROC) curve (AUC), were assessed. Results: The EFS model integrated the features from pre-treatment radiomics, pre-treatment dosiomics, intra-treatment radiomics, and delta radiomics. It outperformed six individual models, achieving an AUC of 0.979, accuracy of 0.917, and F1 score of 0.821. Among the top nine features of the EFS model, six features came from post-wavelet transformation and three from original images. Conclusions: The study demonstrated the feasibility of employing a data-driven multiomics approach to predict treatment outcomes in BM patients receiving PULSAR treatment. Integrating multiomics with intra-treatment decision support in PULSAR shows promise for optimizing patient management and reducing the risks of under- or over-treatment.

Enhanced tumor control and survival in preclinical models with adoptive cell therapy preceded by low-dose radiotherapy.

Effective infiltration of chimeric antigen receptor T (CAR-T) cells into solid tumors is critical for achieving a robust antitumor response and improving therapeutic outcomes. While CAR-T cell therapies have succeeded in hematologic malignancies, their efficacy in solid tumors remains limited due to poor tumor penetration and an immunosuppressive tumor microenvironment. This study aimed to evaluate the potential of low-dose radiotherapy (LDRT) administered before T-cell therapy to enhance the antitumor effect by promoting CAR-T cell infiltration. We hypothesized that combining LDRT with T-cell therapy would improve tumor control and survival compared to either treatment alone. We investigated this hypothesis using two NSG mouse models bearing GSU or CAPAN-2 solid tumors. The mice were treated with engineered CAR-T cells targeting guanyl cyclase-C (GCC) or mesothelin as monotherapy or in combination with LDRT. Additionally, we extended this approach to a C57BL/6 mouse model implanted with MC38-gp100+ cells, followed by adoptive transfer of pmel+ T cells before and after LDRT. Tumor growth and survival outcomes were monitored in all models. Furthermore, we employed atomic force microscopy (AFM) in a small cohort to assess the effects of radiotherapy on tumor stiffness and plasticity, exploring the role of tumor nanomechanics as a potential biomarker for treatment efficacy. Our results demonstrated enhanced tumor control and prolonged survival in mice treated with LDRT followed by T-cell therapy across all models. The combination of LDRT with CAR-T or pmel+ T-cell therapy led to superior tumor suppression and survival compared to monotherapy, highlighting the synergistic impact of the combined approach. Additionally, AFM analysis revealed significant changes in tumor stiffness and plasticity in response to LDRT, suggesting that the nanomechanical properties of the tumor may be predictive of therapeutic response. The findings of this study highlight the transformative potential of incorporating LDRT as a precursor to adoptive T-cell therapy in solid tumors. By promoting CAR-T and pmel+ T-cell infiltration into the tumor microenvironment, LDRT enhanced tumor control and improved survival outcomes, offering a promising strategy to overcome the challenges associated with CAR-T therapy in solid tumors. Additionally, the changes in tumor nanomechanics observed through AFM suggest that tumor stiffness and plasticity could be biomarkers for predicting treatment outcomes. These results support further investigation into the clinical application of this combined approach to improve the efficacy of cell-based therapies in patients with solid tumors.

Pre-Transplant Dual-Energy X-ray Absorptiometry (DXA)-Derived Body Composition Measures as Predictors of Treatment Outcomes and Early Post-Transplant Complications in Patients with Multiple Myeloma (MM) Treated with Autologous Hematopoietic Stem Cell Transplantation (AutoHSCT).

Background/Objectives: Changes in muscle mass and bone density are common in multiple myeloma (MM) patients. Dual-energy X-ray absorptiometry (DXA) offers precise, non-invasive insights into a patient's physical condition before autologous stem cell transplantation (autoHSCT). This study examines how pre-transplant body composition impacts treatment outcomes and early complications in MM patients undergoing autoHSCT. Methods: This study is a single-center, retrospective analysis of patients with MM who were treated with first or second autoHSCT and underwent DXA pre-transplant between 11 August 2019 and 12 June 2024. Results: We conducted a study of pre-transplant body composition in 127 patients with MM. Among them, 108 (85%) qualified for first autoHSCT, while 19 (15%) qualified for a second. The median age of the patients was 64 years (range 50-73). In the Cox proportional hazards regression conducted in the group of women, Total Body %Fat was a statistically significant predictor for progression-free survival (PFS) (HR = 0.07, 95% CI = 0.01,0.6, p = 0.0157). In the Mann-Whitney U test conducted on males, Lean Mass/Height2 and Appen. Lean Height2 were statistically significant predictors of early infections after autoHSCT (Z = 1.98, p = 0.0473 and Z = 2.32, p = 0.0204, respectively). In males, Fat Mass/Height2 was a significant predictor of non-infectious toxicity related to treatment (Z = -1.98, p = 0.0476). Conclusions: In women, higher levels of adipose tissue initially appear to exert a protective effect; however, this benefit diminishes over time, with greater fat mass eventually correlating with an increased risk of disease progression. In men, muscle mass has been identified as a significant predictor of early infection risk post-autoHSCT. Furthermore, our findings indicate that an increased amount of adipose tissue in men is statistically associated with a higher risk of non-infectious treatment-related toxicity. These conclusions highlight the critical need for further investigation into the role of body composition.

A study on music therapy aimed at psychological trauma recovery for bereaved families driven by artificial intelligence.

This study explores the effectiveness of music therapy in repairing psychological trauma in bereaved families, aiming to provide a comprehensive understanding of its potential therapeutic impact. It begins with an analysis of the current situation faced by bereaved families, identifying the psychological challenges they experience. The research design included the recruitment of participants from bereaved families, who were then divided into an experimental group and a control group. An optimized Long Short-Term Memory (LSTM) network model was constructed to analyze music therapy data, tailored specifically to capture the nuances of this therapeutic process. The experimental procedure detailed the specific operations involved in the music therapy sessions and established a clear comparison framework between the two groups. The performance of the proposed LSTM model demonstrated high accuracy (0.85), precision (0.86), recall (0.84), and F 1-score (0.85), indicating its effectiveness in predicting treatment outcomes. When compared to the Self-Reporting Inventory-90 (SCL-90) scale, the model captured the trend of treatment effects with a high level of accuracy and reliability. Notably, participants numbered 2, 6, and 8 in the experimental group showed substantial improvement rates of 67.21%, 71.45%, and 75.67%, respectively, in their psychological health issues. The comparative analysis between the experimental and control groups confirmed that the music therapy approach, as guided by the proposed LSTM model, led to a more significant improvement in psychological health issues for bereaved families. This suggests that the model offers a promising avenue for enhancing the effectiveness of music therapy in this context.

Neuroimaging studies of resting-state functional magnetic resonance imaging in eating disorders

Eating disorders (EDs), including anorexia nervosa (AN), bulimia nervosa (BN), binge-eating disorder (BED), and pica, are psychobehavioral conditions characterized by abnormal eating behaviors and an excessive preoccupation with weight and body shape. This review examines changes in brain regions and functional connectivity in ED patients over the past decade (2013–2023) using resting-state functional magnetic resonance imaging (rs-fMRI). Key findings highlight alterations in brain networks such as the default mode network (DMN), central executive network (CEN), and emotion regulation network (ERN). In individuals with AN, there is reduced functional connectivity in areas associated with facial information processing and social cognition, alongside increased connectivity in regions linked to sensory stimulation, aesthetic judgment, and social anxiety. Conversely, BED patients show diminished connectivity in the dorsal anterior cingulate cortex within the salience network and increased connectivity in the posterior cingulate cortex and medial prefrontal cortex within the DMN. These findings suggest that rs-fMRI could serve as a valuable biomarker for assessing brain function and predicting treatment outcomes in EDs, paving the way for personalized therapeutic strategies.

A neural network model for predicting the effectiveness of treatment in patients with neovascular glaucoma associated with diabetes mellitus.

The study hypothesizes that neural networks can be an effective tool for predicting treatment outcomes in patients with diabetic neovascular glaucoma (NVG), considering not only baseline intraocular pressure (IOP) values but also inflammation and intraocular microcirculation indicators. To investigate the diagnostic significance of inflammation and intraocular blood circulation indicators in a neural network model predicting the effectiveness of transscleral cyclophotocoagulation (TSC CPC) treatment in patients with NVG of diabetic origin. This retrospective cohort study included 127 patients (127 eyes; aged Me 65.0 years) with painful diabetic NVG and 20 healthy individuals (aged Me 61.5 years) as an immunological control. All patients underwent TSC CPC with a diode laser. Treatment success was defined as achieving an IOP level of ≤ 21 mmHg and maintaining or improving best-corrected visual acuity (BCVA) after 12 months of observation. Preoperative systemic immune-inflammation index (SII = platelets × [neutrophils/lymphocytes]) and systemic inflammation response index (SIRI = neutrophils × [monocytes/lymphocytes]) were calculated. We assessed the values of volumetric pulse blood filling, determined by the rheographic coefficient (RQ, 0/00), using the rheoophthalmography (ROG) method. Multiple regression analysis was used to conclude the significance of treatment efficacy based on initial clinical and laboratory indicators, followed by constructing a prediction model in the neural network. The development of the neural network model identified the most significant "input" parameters: SIRI (100%), RQ (85.7%), and SII (80.7%), which significantly influenced treatment success. The sensitivity of the neural network model was 100%, specificity was 30%, and the percentage of correctly predicted events during testing on the control group was 92.9%. Neural network-based prediction of transscleral cyclophotocoagulation effectiveness for patients with diabetic neovascular glaucoma allows for a sufficiently accurate forecast of treatment success with a probability of 92.9%. We believe the in-time correction of systemic inflammation and intraocular blood circulation can significantly reduce intraocular pressure, preserve visual acuity, and improve the quality of life in patients with diabetic NVG after TSC CPC. Further research is required to support these findings.

Programmatic forecasting of treatment and diagnostic measures for congenital cleft lip and/or palate

Relevance. The documentation processes in medical organizations across the DPR are being restructured, particularly in relation to providing therapeutic and rehabilitative care for children with congenital maxillofacial anomalies. Significant changes have been made to both the requirements for medical documentation and the speed at which it is processed, thanks to advancements in information technology and the introduction of individual electronic medical records. In this era of medical digitalization, it is crucial to simplify data collection and improve the forecasting of the effectiveness of therapeutic and rehabilitative measures conducted at the Pediatric Maxillofacial Surgery Center in Donetsk.Materials and methods. To evaluate the effectiveness of forecasting therapeutic and rehabilitative measures using the "Outpatient Monitoring" software, a previously developed model for predicting treatment outcomes was used. This model is based on an analysis of factors and indicators that reflect different aspects of the treatment and rehabilitation process for children with cleft lip and/or palate.Results. The study led to the implementation of a methodology for forecasting the effectiveness of therapeutic and rehabilitative measures at the Pediatric Maxillofacial Surgery Center in Donetsk, utilizing the " Outpatient Monitoring " computer-based accounting and analytical software, which facilitates both practical and scientific tasks related to the monitoring, treatment, and rehabilitation of children with cleft lip and/or palate.Conclusion. The developed forecasting model will greatly simplify the work of specialists at the Pediatric Maxillofacial Surgery Center.

Immune-reactive tumor organoids system to determine the effects of microbial metabolites on cancer immunity and immunotherapies

Immunotherapies are a revolutionary approach to treating cancer by utilizing the body’s immune system to target and combat cancer cells. This approach offers promising alternatives to traditional chemotherapies. Its potential to induce long-lasting remissions and specificity for cancer cells, which minimizes side effects, makes it a cutting-edge treatment with tremendous potential. With the increase of the clinical usage of immunotherapy, evidence emerges of the microbiome’s impact on both tumor growth and response to immunotherapy. The proposed involvement of the microbiome can change treatment efficacy by altering drug metabolism and reshaping the immune system response. Understanding the specific interactions between tumor cells, immune cells, and the microbiome is a critical step in the advancement of immunotherapy. To study the complex interaction between cancer immunity and the microbiome, various preclinical in vivo and in vitro models have been developed. We have recently described the use of an ex vivo preclinical model for anti-cancer treatment outcome prediction –tumor tissue equivalents (organoids). Specifically, immune-reactive tumor organoids are proposed as a novel tool for understanding how the microbiome influences cancer immunity and immunotherapy. More importantly, this platform can utilize patient samples to dissect patient-specific elements regulating cancer immune response and microbiome influence. This review presents the rationale for using the immune-reactive tumor organoids model to study the interactions between the microbiome and cancer immunotherapy. It will discuss available components of the model and analyze their interplay, summarize relevant experimental data, and assess their validity. Additionally, it explores the potential of immune-reactive organoids for personalized treatment approaches. Understanding the microbiome’s role in immunotherapy outcomes will lead to transformative cancer treatment via a simple change of diet or other microbiome manipulations. Ongoing research on microbiome-cancer interactions utilizing the described model systems will lead to innovative treatment strategies and improved patient outcomes.

Imaging in malignant peritoneal neoplasms.

Peritoneal malignancies encompass a diverse range of tumors originating within the peritoneum, including primary tumors such as mesothelioma and primary serous peritoneal carcinoma or secondary tumors resulting from the spread of cancers from gastrointestinal, gynecological, and extra-abdominal sources. The traditional approach of palliative care for these malignancies is being replaced by a multimodal strategies that integrates surgery with systemic or intraperitoneal chemotherapy. Notably, cytoreductive surgery combined with hyperthermic intraperitoneal chemotherapy has shown significant improvements in survival rates. Imaging is crucial in the multidisciplinary management of these tumors, aiding in diagnosis, staging, restaging, and monitoring therapy response. It is also vital for appropriate patient selection, using the acronym "PAUSE", which involves assessing tumor burden via the peritoneal carcinomatosis index, evaluating patients pre- and post-therapy, detecting complications following therapy, and predicting treatment outcomes. This review explores the imaging manifestations of peritoneal malignancies, distinguishing them from various mimics, and underscores the importance of imaging modalities such as CT, MRI, PET/CT, and PET/MRI in effective decision-making and management.

AI in Surgery: Navigating Trends and Managerial Implications Through Bibliometric and Text Mining Odyssey.

Background:This research employs bibliometric and text-mining analysis to explore artificial intelligence (AI) advancements within surgical procedures. The growing significance of AI in healthcare underscores the need for healthcare managers to prioritize investments in this technology. Purpose:To assess the increasing impact of AI on surgical practices through a comprehensive analysis of scientific literature, providing insights that can guide managerial decision-making in adopting AI solutions.Research Design:The study analyzes over 6000 scientific articles published since 1990 to evaluate trends and contributions in the field, informing managers about the current landscape of AI in surgery.Study Sample:The research focuses on publications from various influential publishers across North America, Northern Asia, and Eastern & Western Europe, highlighting key markets for AI implementation in surgical settings.Data Collection and Analysis:A bibliometric approach was utilized to identify key contributors and influential journals. At the same time, text-mining techniques highlighted significant keywords related to AI in surgery, aiding managers in recognizing essential areas for further exploration and investment.Results:The year 2022 marked a significant upsurge in publications, indicating widespread AI integration in healthcare. The U.S. emerged as the foremost contributor, followed by China, the UK, Germany, Italy, the Netherlands, and India. Key journals, such as Annals of Surgery and Spine Journal, play a crucial role in disseminating research findings, serving as valuable resources for managers seeking to stay informed.Conclusions:The findings underscore AI's pivotal role in enhancing diagnostic precision, predicting treatment outcomes, and improving operational efficiency in surgical practices. This progress represents a significant milestone in modern medical science, paving the way for intelligent healthcare solutions and further advancements in the field. Healthcare managers should leverage these insights to foster innovation and improve patient care standards.

Validation of an Artificial Intelligence-Based Prediction Model Using 5 External PET/CT Datasets of Diffuse Large B-Cell Lymphoma.

The aim of this study was to validate a previously developed deep learning model in 5 independent clinical trials. The predictive performance of this model was compared with the international prognostic index (IPI) and 2 models incorporating radiomic PET/CT features (clinical PET and PET models). Methods: In total, 1,132 diffuse large B-cell lymphoma patients were included: 296 for training and 836 for external validation. The primary outcome was 2-y time to progression. The deep learning model was trained on maximum-intensity projections from PET/CT scans. The clinical PET model included metabolic tumor volume, maximum distance from the bulkiest lesion to another lesion, SUVpeak, age, and performance status. The PET model included metabolic tumor volume, maximum distance from the bulkiest lesion to another lesion, and SUVpeak Model performance was assessed using the area under the curve (AUC) and Kaplan-Meier curves. Results: The IPI yielded an AUC of 0.60 on all external data. The deep learning model yielded a significantly higher AUC of 0.66 (P < 0.01). For each individual clinical trial, the model was consistently better than IPI. Radiomic model AUCs remained higher for all clinical trials. The deep learning and clinical PET models showed equivalent performance (AUC, 0.69; P > 0.05). The PET model yielded the highest AUC of all models (AUC, 0.71; P < 0.05). Conclusion: The deep learning model predicted outcome in all trials with a higher performance than IPI and better survival curve separation. This model can predict treatment outcome in diffuse large B-cell lymphoma without tumor delineation but at the cost of a lower prognostic performance than with radiomics.

Applications of artificial intelligence in interventional oncology: An up-to-date review of the literature.

Interventional oncology provides image-guided therapies, including transarterial tumor embolization and percutaneous tumor ablation, for malignant tumors in a minimally invasive manner. As in other medical fields, the application of artificial intelligence (AI) in interventional oncology has garnered significant attention. This narrative review describes the current state of AI applications in interventional oncology based on recent literature. A literature search revealed a rapid increase in the number of studies relevant to this topic recently. Investigators have attempted to use AI for various tasks, including automatic segmentation of organs, tumors, and treatment areas; treatment simulation; improvement of intraprocedural image quality; prediction of treatment outcomes; and detection of post-treatment recurrence. Among these, the AI-based prediction of treatment outcomes has been the most studied. Various deep and conventional machine learning algorithms have been proposed for these tasks. Radiomics has often been incorporated into prediction and detection models. Current literature suggests that AI is potentially useful in various aspects of interventional oncology, from treatment planning to post-treatment follow-up. However, most AI-based methods discussed in this review are still at the research stage, and few have been implemented in clinical practice. To achieve widespread adoption of AI technologies in interventional oncology procedures, further research on their reliability and clinical utility is necessary. Nevertheless, considering the rapid research progress in this field, various AI technologies will be integrated into interventional oncology practices in the near future.

Assessing factors of adherence and efficacy: A randomized controlled trial of a fully automated self-help A-EBT website.

Treatment for trichotillomania is notably limited, preventing suffering individuals from having access to treatment. To address this need, researchers have developed and tested asynchronous online interventions for adults with trichotillomania. A factor that may impact the efficacy of these programs is the use of phone check-ins (or similar coaching support) to improve treatment adherence in website treatment delivery. In the current study we evaluated the role of check-ins on treatment adherence and efficacy of a website delivering acceptance and commitment therapy-enhanced behavior therapy (A-EBT). A sample of 101 adults with trichotillomania were randomly assigned to an A-EBT web-based intervention with or without phone check-in support. Adherence to the web-based program was not significantly improved by check-ins and treatment outcomes did not vary by condition (with or without check-ins). However, adherence to the program across conditions, did predict treatment outcomes. The program was found to be effective at decreasing trichotillomania symptom severity and improving trichotillomania specific psychological inflexibility over time across check-in conditions. Our findings suggest that check-ins did not improve adherence to or efficacy of the program, thus supporting recent literature suggesting that check-ins do not necessarily improve program adherence.

Optimising outcomes for frail patients with oesophagogastric (OG) cancers: The impact of dose reduction and comprehensive geriatric assessment.

303 Background: Delivery of appropriate management of elderly patients with OG malignancies in the palliative setting remains challenging and unpredictable. Incidence of OG cancers increases markedly with age, and there are growing numbers of elderly, frail and medically complex patients referred to oncology services for treatment. An adaptive approach to their management is required, tailored to their complex medical needs. The GO2 study sought to optimise chemotherapy delivery in this cohort and demonstrated that upfront dose reductions do not reduce progression-free survival in OG cancers. We analysed the treatment and outcome of elderly patients undergoing first-line palliative chemotherapy at our centre, with or without comprehensive geriatric assessment (CGA). Methods: We retrospectively analysed the records of patients over the age of 75 treated at our centre between May 2011 and March 2023. Progression-free survival (PFS) was calculated from the date of treatment initiation to date of radiological progression, or 19 th March 2024 if patients had not progressed. Overall survival (OS) was calculated from treatment initiation to date of death per the electronic health record, or 19 th March 2024 if patients had not died. Grade 3 (G3) toxicities and dose reductions (DRs) were identified from medical records. Statistical analyses were performed using R v4.3.3. Results: 82 patients were included in the analysis. Overall median PFS was 6.5 months (1-107 months) and median OS was 10 months (1-107 months). Patients who qualified for chemotherapy with immunotherapy had improved PFS (median 16 months, range 2-27 months) and OS (median 16 months, range 10-27 months). G3 toxicities were increased in patients without upfront DR (44% vs. 30%). The most significant predictor for survival in multivariate analysis was performance status (PS), which was associated with worse PFS (hazard ratio 2.66, range 1.35–5.35, p = 0.004), and OS (hazard ratio 6.13, range 2.79–13.44, p &lt; 0.001). Age was not associated with survival. Consistent with the GO2 trial, there was no association between upfront DR and PFS (p = 0.13) or OS (p = 0.72). 38% of patients underwent CGA as part of their workup for chemotherapy. These patients were more likely to have upfront DR (61% vs. 47%). In this cohort, G3 toxicity rates were comparable in patients with PS 0-1 who underwent CGA (39% vs. 35%). In patients with PS ≥ 2, G3 toxicity rates were higher in those who did not undergo CGA (67% vs. 30%). Conclusions: Upfront DR in elderly patients is safe and does not impact survival but does reduce the burden of toxicity. PS, rather than age, is a better predictor of survival and treatment outcome. CGA may help mitigate toxicity burden in patients with poor performance status.

Reply to Editorial Comment on “External Validation Demonstrates Machine Learning Models Outperform Human Experts in Prediction of Objective and Patient-reported Overactive Bladder Treatment Outcomes”

Reply to Editorial Comment on “External Validation Demonstrates Machine Learning Models Outperform Human Experts in Prediction of Objective and Patient-reported Overactive Bladder Treatment Outcomes”

Pharmacogenomic augmented machine learning in electronic health record alerts: A health system-wide usability survey of clinicians.

Pharmacogenomic (PGx) biomarkers integrated using machine learning can be embedded within the electronic health record (EHR) to provide clinicians with individualized predictions of drug treatment outcomes. Currently, however, drug alerts in the EHR are largely generic (not patient-specific) and contribute to increased clinician stress and burnout. Improving the usability of PGx alerts is an urgent need. Therefore, this work aimed to identify principles for optimal PGx alert design through a health-system-wide, mixed-methods study. Clinicians representing multiple practices and care settings (N = 1062) in urban, rural, and underserved regions were invited to complete an electronic survey comparing the usability of three drug alerts for citalopram, as a case study. Alert 1 contained a generic warning of pharmacogenomic effects on citalopram metabolism. Alerts 2 and 3 provided patient-specific predictions of citalopram efficacy with varying depth of information. Primary outcomes included the System's Usability Scale score (0-100 points) of each alert, the perceived impact of each alert on stress and decision-making, and clinicians' suggestions for alert improvement. Secondary outcomes included the assessment of alert preference by clinician age, practice type, and geographic setting. Qualitative information was captured to provide context to quantitative information. The final cohort comprised 305 geographically and clinically diverse clinicians. A simplified, individualized alert (Alert 2) was perceived as beneficial for decision-making and stress compared with a more detailed version (Alert 3) and the generic alert (Alert 1) regardless of age, practice type, or geographic setting. Findings emphasize the need for clinician-guided design of PGx alerts in the era of digital medicine.