Clinician Support Research Articles

Self-Guided vs Clinician-Guided Online Cognitive Behavioral Therapy for Atopic Dermatitis: A Randomized Clinical Trial.

Clinician-guided online self-help based on cognitive behavioral therapy (CBT) has been shown to be effective at decreasing symptom severity for people with atopic dermatitis (AD). A brief online self-guided CBT intervention could be more cost-effective and allow for easy implementation and broader outreach compared with more comprehensive clinician-guided interventions. To investigate whether a brief online self-guided CBT intervention is noninferior to a comprehensive online clinician-guided CBT treatment. This single-blind randomized clinical noninferiority trial was conducted at Karolinska Institutet, Stockholm, Sweden. Adult individuals with AD were enrolled from November 2022 to April 2023. The last postintervention data were collected in December 2023. Participants randomized to the self-guided group had access to a self-guided online CBT intervention for 12 weeks without clinician support. Participants randomized to the clinician-guided group received online CBT for 12 weeks. The primary outcome was change in score from baseline to postintervention to 12-week follow-up on the self-reported Patient-Oriented Eczema Measure (POEM). The predefined noninferiority margin was 3 points on POEM. Of 168 randomized participants, 142 (84.5%) were female, and the mean (SD) age was 39 (10.5) years. A total of 86 participants were randomized to the self-guided group and 82 were randomized to the clinician-guided group. A total of 151 (90.0%) completed the main outcome postintervention assessment. Postintervention, the clinician-guided group had improved 4.20 points (95% CI, 1.94-6.05) on POEM and the self-guided group improved 4.60 points (95% CI, 2.57-6.64), corresponding to an estimated mean difference in change of 0.36 points (1-sided 97.5% CI, -∞ to 1.75), which was below the noninferiority margin of 3 points. No serious adverse events were reported. In the clinician-guided group, clinicians spent a mean (SD) of 36.0 (33.3) minutes (95% CI, 29.2-41.7) on treatment guidance and 14.0 (6.0) minutes (95% CI, 12.9-15.6) on assessments compared to 15.8 (6.4) minutes on assessments in the self-guided group. In this randomized clinical noninferiority trial, a brief self-guided CBT intervention was noninferior to clinician-guided CBT. Given the limited clinical resources required to deliver self-guided CBT, this treatment might be a promising means to disseminate evidence-based psychological treatment for patients with AD. ClinicalTrials.gov Identifier: NCT05517850.

Policy Feedback and the Politics of Childhood Vaccine Mandates: Conflict and Change in California, 2012–2019

Context: In 2012, California instituted a new requirement for parents to consult with a clinician before receiving a personal belief exemption (PBE) to its school entry vaccine mandate. In 2015, the state removed this exemption altogether. In 2019, legislators cracked down on medical exemptions to address their misuse by vaccine refusers and supportive clinicians. This article uses “policy feedback theory” to explore these political conflicts, arguing that PBEs informed the emergence and approaches of two coalitions whose conflict reshaped California's vaccination policies. Methods: The authors analyzed legal, policy, academic, and media documents; interviewed 10 key informants; and deductively analyzed transcripts using NVivo 20 transcription software. Findings: California's long-standing vaccination policy inadvertently disseminated two fundamentally incompatible social norms: vaccination is a choice, and vaccination is not a choice. Over time, the culture and number of vaccine refusers grew, at least in part because the state's policy sanctioned the norm of vaccine refusal. Conclusions: The long-term consequences of California's “mandate + PBE” policy—visible, public, and socially sanctioned vaccine refusal—undermined support for it over time, generating well-defined losses for a large group of people (the vaccinating public) and specifically for the provaccine parent activists whose experiences of personal grievance drove their mobilization for change.

A mindfulness-based, cognitive, social, digital relapse-prevention intervention for youth with depression in Australia: study protocol for a randomised controlled trial of Rebound

IntroductionMajor depressive disorder (MDD) causes significant disease burden and functional impairment during adolescence and young adulthood. While most young people recover from their first episode, around two-thirds will experience one...

Integrating Clinical Data and Patient-Reported Outcomes for Analyzing Gender Differences and Progression in Multiple Sclerosis Using Machine Learning.

Multiple sclerosis (MS) is a complex neurodegenerative disease with a variable prognosis that complicates effective management and treatment. This study leverages machine learning (ML) to enhance the understanding of disease progression and uncover gender-based differences in MS by analyzing clinical data integrated with patient-reported outcomes (PROMs). We conducted a prospective cohort study involving 250 MS patients at a secondary care hospital in Spain over an 18-month period. Using REDCap for data management, we collected comprehensive demographic, clinical, and PROMs data. Our analysis utilized Decision Trees, Random Forest, and Support Vector Machine algorithms to classify patients based on disease evolution and infer Expanded Disability Status Scale (EDSS) levels. Additionally, we employed propensity score matching to analyze gender differences, focusing on clinical outcomes and quality of life measures. The results could indicate that integrating diverse data sets through ML would significantly improve the diagnostic accuracy and serve as a support for clinician's decision making. Our models achieved high accuracy in classifying MS types and predicting disability levels, demonstrating the potential of ML in personalized treatment planning. Furthermore, our findings suggest notable gender differences in disease progression and response to treatment. These insights advocate for a gender-specific approach in MS management and highlight the importance of personalized medicine. This study underscores the transformative potential of ML in enhancing the understanding and management of MS through integrated data analysis.

Evaluation of a New Automated Mono-Test for the Detection of Aspergillus Galactomannan: Comparison of Aspergillus Galactomannan Ag VirCLIA® Mono-Test with PlateliaTMAspergillus Ag ELISA Assay.

The analytical performance of the new Aspergillus Galactomannan Ag VirCLIA® mono-test (Vircell S.L.) was compared to the Platelia™ Aspergillus Ag ELISA assay (Bio-Rad). Prospective serum and bronchoalveolar lavage (BAL) samples from patients at risk of invasive aspergillosis (IA) were tested using both the Aspergillus Galactomannan Ag VirCLIA® mono-test and the Platelia™ Aspergillus Ag ELISA assay. Concordance, sensitivity, specificity, and positive and negative predictive values were calculated using the manufacturer-recommended cutoff levels. Receiver operating characteristic (ROC) analysis and the Youden index were performed to determine the optimal cutoff. A total of 187 serum samples and 73 BAL samples were analyzed with both assays. The concordance between the Aspergillus Galactomannan Ag VirCLIA® mono-test and the Platelia™ Aspergillus Ag ELISA assay was 87.8%, with a Cohen's kappa of 0.75. The sensitivity and specificity of the Aspergillus Galactomannan Ag VirCLIA® mono-test were 78.6% and 96.2%, respectively, with positive and negative predictive values of 94.8% and 83.3%. The ROC curve for the Aspergillus Galactomannan Ag VirCLIA® mono-test demonstrated an area under the curve (AUC) of 0.87, and the Youden index at the manufacturer's established cutoff was 0.73. This new Aspergillus Galactomannan Ag VirCLIA® mono-test exhibited adequate analytical and clinical performance, showing good correlation with the Platelia™ Aspergillus Ag ELISA assay. The single-sample, semi-automated test is user-friendly, allowing small laboratories to perform the test on demand without the need for batch evaluations, providing a useful solution for timely diagnostic support for clinicians.

Virtual support group initiative for mental health professionals in the COVID-19 pandemic.

As a result of the coronavirus pandemic, mental health professionals have faced the challenge of helping their clients cope with pandemic-related distress on top of ongoing therapeutic issues. This article describes a telehealth-delivered peer/mutual support program for mental health professionals during the pandemic and the key themes identified by participants. An interdivisional American Psychological Association task force formed a working group to identify practical ways to provide mental health professionals with direct support during the pandemic. A mutual support program, the Clinician Support Collaborative, was initiated using virtual video technology. This article describes the program and themes that emerged, including the challenges and benefits of using virtual video technology to host mutual support meetings. Mutual support meetings were conducted on a weekly basis in 2020 and 2021, with mental health professionals and trainees in the Americas, Australasia, and India participating. Key themes identified included the logistical, therapeutic, and privacy concerns participants faced when shifting to telehealth, professional isolation, compassion fatigue, moral injury, burnout, stigma, disparities, and the intersection of personal/family stressors and work stressors. Recommendations for future use of virtual video technology to provide mutual support by and for mental health professionals are provided. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

The Multiple Facets of Cow’s Milk Allergy

Cow’s milk allergy (CMA) is one of the most common food allergies in early childhood. CMA has varied presentations and multiple facets. A detailed clinical history is key for classification. In IgE-mediated CMA skin prick testing and serum specific IgE testing are useful in the diagnosis, but an oral food challenge (OFC) may still be necessary if there is doubt or to assess tolerance. Non-IgE-mediated CMA presentations include food protein-induced allergic proctocolitis (FPIAP), food protein-induced enterocolitis syndrome (FPIES), and eosinophilic esophagitis (EoE). The diagnosis of FPIAP and FPIES is based on the clinical history. An esophageal biopsy is required for the diagnosis of EoE. Atopy patch testing, IgG or IgG4 testing are not helpful in any CMA evaluation. Children with CMA (except those with FPIAP) are at risk for poor growth and a nutritional evaluation should be part of routine care. Extensively hydrolyzed formulas are the recommended first choice alternative formula for CMA. For IgE-mediated CMA, alternative approaches to traditional strict avoidance include oral immunotherapy (OIT) and omalizumab (both as monotherapy and as an adjunct to OIT). Multiple international guidelines have addressed evaluation and management of CMA providing key information, support and guidance for clinicians in daily practice.

Expanding access to addictions care: Implementation of a 24-hour healthcare provider support line in British Columbia, Canada

BackgroundMorbidity and mortality related to substance use have risen to catastrophic levels in North America, and treatment services are often difficult to access. In response, the province of British Columbia (BC), Canada, launched a province-wide addiction medicine support phone line that offers clinicians immediate access to phone consultation with an addictions medicine expert. The service operates 24/7 is accessible to any clinician in the province seeking assistance with an addiction-related question. We describe an evaluation of the reach and perceived impact of the service over its first two years.MethodsThe 24/7 Addiction Medicine Clinician Support Line was evaluated prospectively from June 2020 to April 2022. All provider-to-provider encounters were included. Data was collected from two primary sources: health provider demographic information collected at the time of consultation, and optional clinician surveys conducted after the consultation was complete. Descriptive data are presented as numerical values and percentages.ResultsOver the 22-month evaluation period, 1,279 consultations were requested by 631 distinct care providers across British Columbia. The service averaged 15 calls per week across the province, and 51.5% of calls were made outside of business hours. Physicians made the majority of calls to the service (n = 865, 67.6%), followed by nurse practitioners (n = 162, 12.7%). Among those who completed a follow-up survey (n = 258 calls, 20.2% total calls), 81.8% (n = 211) were “very” or “extremely” satisfied with the consultation. Of these respondents, 65.5% (n = 169) reported that the consultation led to the provision of better care for their patient, with 58.1% (n = 150) initiating a new prescription and 22.1% (n = 57) reporting expedited treatment for their patient. The consultation area of focus was most commonly opioid use (n = 417; 59.6%), followed by polysubstance use (n = 98; 14.0%).ConclusionsThe impact of the 24/7 Addiction Clinician Support Line was widespread, and the service increased accessibility to evidence-based addictions treatment across a range of care settings. Clinicians expressed a high degree of satisfaction with the service. To our knowledge, this province-wide program is the first of its kind in North America, offering a scalable and adaptable model to support access to evidence-based addictions care in under-resourced settings.

Clinician and Practice Characteristics Associated With Support of Office-Based Methadone: Findings From a National Survey.

Alternative models for methadone delivery outside of federal and state-regulated opioid treatment programs may improve access. We determined factors associated with clinician support for continuing office-based methadone. We used data from the electronic Opioid Use Disorder Provider COVID-19 Survey conducted among X-waivered clinicians who were providing outpatient, longitudinal treatment of opioid use disorder (OUD) from July 2020 to August 2020. The outcome variable was selecting "The opportunity for patients to receive office-based methadone" when asked "Which pandemic-related policy changes or new policy changes would you like to be continued or started after the pandemic?" Using sequential multivariable logistic regression modeling, we estimated the association between clinician and practice characteristics and support for office-based methadone. Of 1900 respondents, 728 met the inclusion criteria. Twenty-eight percent indicated support for office-based methadone. Clinician characteristics associated with support for office-based methadone were being Black or African American versus White (adjusted odds ratio [AOR] [95% confidence interval (CI)], 2.88 [1.19-6.98]), having provided medications for OUD (MOUD) for >15 years versus ≤15 years (AOR [95% CI], 1.66 [1.02-2.68]), treating 51 to 100 patients with MOUD monthly versus <25 patients (AOR [95% CI], 1.79 [1.04-3.09]), providing methadone (AOR [95% CI], 1.71 [1.03-2.85]) versus not providing MOUD previously, and working in an academic medical center versus other settings (AOR [95% CI], 1.88 [1.11-3.16]). A minority of surveyed X-waivered clinicians supported office-based methadone. Efforts to expand access to methadone via office-based settings should address implementation barriers.

DPDCD: The Intelligent Prediction Strategy for the Course Development of Diabetic Kidney Disease

Diabetic nephropathy (DKD) is a severe diabetes complication and a leading cause of mortality. While urine microalbuminuria and eGFR are common markers, some advanced cases may exhibit normal values. The progression from microalbuminuria to overt proteinuria in DKD is gradual and requires comprehensive physiological tests for diagnosis. This study employs deep reinforcement learning to predict DKD progression based on patients’ physiological data, aiming to assist clinical diagnosis and treatment. A multivariate logistic regression algorithm is used to describe the DKD prediction probability. An optimized DKD progression prediction algorithm (DPDCD) based on deep reinforcement learning determines the best model coefficients, enabling accurate prediction of DKD progression using routine clinical data. Experimental results demonstrate that DPDCD outperforms other algorithms in predicting DKD progression, providing valuable support for clinicians.

Women’s perspectives on the acceptability of risk-based cervical cancer screening

BackgroundThe increased knowledge of cervical cancer (CC) risk factors and suboptimal performance of present screening programs has generated interest in shifting from a universal screening approach to one based on individual risk assessment. To inform the future development of risk-based CC screening programs, it is crucial to gain insight into the factors influencing the acceptability of such approach among screening target group women. The aim of this study was to prospectively investigate the acceptability of risk-based CC screening and to identify potential barriers.MethodsIn this qualitative study, one-to-one semi-structured interviews were conducted with a purposeful sample including women aged 30–65 years to explore women’s perspectives on the acceptability of risk-based CC screening. The study was conducted in Estonia, and interviews were conducted from March to September 2023. Potential participants were approached in person by a member of the study team or by their healthcare providers at primary care or gynaecology clinics. The interview guides were developed based on the concept of acceptability of healthcare interventions.ResultsTwenty participants (mean age 44.5, SD = 8.6) with diverse backgrounds were interviewed. The seven components of acceptability (affective attitude, burden, ethicality, opportunity costs, perceived effectiveness, self-efficacy, and intervention coherence) were explored as key themes. Generally, women supported risk-based screening. However, we identified several factors that may compromise the acceptability of risk-based screening. The participants were reluctant to accept less intense screening for low-risk women and anticipated that if risk-based approach was implemented, more frequent testing would remain an option. Providing in-person clinician support was expected, requiring additional healthcare resources. Knowledge gaps in CC prevention highlighted the need for accessible information and education. Most women were unworried about sensitive data inclusion in risk score calculations. However, some participants were concerned about potential confidentiality breaches by healthcare workers.ConclusionThis study indicates that risk-based CC screening is acceptable, except for testing low-risk women less frequently. Our findings underscore the necessity for comprehensive understanding of the needs and concerns of the target group women for program development. Healthcare organizations are required to proactively address these needs by implementing comprehensive information dissemination and efficient communication approaches.

Feasibility of Emergency Department-Initiated HIV Pre-Exposure Prophylaxis.

Pre-exposure prophylaxis (PrEP) for HIV-using antiretroviral medication in non-infected individuals to prevent HIV-has immense potential to slow the spread of the virus. However, uptake has been insufficient, and stark racial disparities exist in both HIV acquisition and PrEP usage, making PrEP access a health equity issue. A promising venue to engage high-risk populations in PrEP care is the emergency department (ED); however, existing ED PrEP initiatives have been costly or have had limited success. We hypothesize that two strategies could overcome these barriers: prescribing PrEP during an ED visit and providing patients with an initial supply of PrEP medication in the ED. Here, we describe the results of a qualitative study exploring multidisciplinary emergency clinicians and HIV clinicians' needs and views about the feasibility of such an initiative. We conducted 22 semi-structured interviews with multidisciplinary clinicians from an urban, safety-net medical center in the ED and the on-site HIV clinic that provides PrEP services. We performed thematic analysis to summarize challenges and potential solutions described by participants. Participants' responses fell into three thematic categories: operational challenges; patient-level considerations; and potential impacts. Operational challenges highlighted the difficulty of PrEP initiation in a busy ED and clinician support needs. Patient-level considerations included the complex psychosocial needs of ED patients who could benefit from PrEP. Finally, participants anticipated that an ED-based PrEP initiation program could positively impact both individual patients and public health. Interviews with emergency department and HIV clinic staff revealed important considerations and potential solutions for ED-initiated PrEP workflows. Clinicians in both specialties were enthusiastic about such an initiative, which could facilitate its success. This study lays the groundwork for the future design of an efficient and innovative workflow to leverage the ED as an essential entry point into HIV prevention services.

Nurses' Experiences With Virtual Consultations and Home-Monitoring in Patients With Cardiac Disease: A Systematic Review and Qualitative Meta-Synthesis ofResults.

To explore how nurses experience facilitators and barriers to the use of video-consultations for home-monitoring of patients with cardiac disease. A systematic literature search in PubMed, CINAHL, Scopus, and Web of Science was undertaken, inclusion criteria were qualitative data published between 2013 and 2023 written in English, Norwegian, Swedish, or Danish. Ten studies were included in the qualitative synthesis conducted as described by Braun and Clarke. From the synthesis, a main theme emerged: Nurses' uncertainty toward telemedicine is a risk toward the use of video-consultations and home-monitoring. The essence of the findings range from nurses' positive experiences to their frustration concerning the implementation process and the lack of technical support for clinicians and patients. Nurses often felt frustration and uncertainty about the quality of delivered care through virtual consultations. Working with technology in caring for patients with cardiac disease, including video-consultations and home-monitoring, nurses experienced a sense of insecurity. Insecurity was identified as a lack of technological knowledge, nurses' feelings of apathy, poorer observation through a video-consultation, and the lack of organizational support.

Coming of age in a warming world: A self‐determination theory perspective

AbstractToday's youth are growing up in a world threatened by climate change. Facing an uncertain future, young people—and especially adolescents—tend to be concerned about climate change, even more so than other age groups. How can socializing agents (e.g., educators, policymakers, clinicians) support and engage adolescents as they come of age in a warming world? In this article, we review studies on climate change and youth development from the perspective of self‐determination theory (SDT). SDT provides a framework for understanding a nascent body of literature on adolescents' responses to climate change. In particular, SDT offers insights into the factors that can facilitate or undermine adolescents' internalization of climate science, engagement in pro‐environmental behavior, and capacity for resilience and well‐being. We discuss SDT's potential to inform efforts to encourage positive youth development amid climate change, and we identify priorities for investigation.

Supporting clinicians post exposure to potentially traumatic events: Emergency department peer support program evaluation.

Workers in EDs are regularly exposed to potentially traumatic events. Since the COVID-19 pandemic, there has been exponential interest in peer support programs (PSPs) in a range of settings. We describe a PSP implemented in 2017 at University Hospital Geelong (UHG) ED together with results of a survey. To describe the program such that others can replicate it in their settings in addition to feedback evaluation. Method involved a survey emailed to the ED doctors. Thirty responses from 96 emails with a range of feedback. ED Doctors place high value on the PSP.

An integrative predictive model for orthokeratology lens decentration based on diverse metrics.

To develop a predictive model for orthokeratology (Ortho-K) lens decentration 1 month after wear. This study included myopic children who were fitted with Ortho-K lenses at Fujian Provincial Hospital between December 2022 and May 2024. Corneal topography parameters and other relevant metrics were collected pre- and post-treatment. Feature selection was conducted using univariate logistic regression and Lasso regression analysis. A machine learning approach was used to develop multiple predictive models, including Decision Tree, Logistic Regression, Multilayer Perceptron, Random Forest, and Support Vector Machine. Model performance was evaluated using accuracy, sensitivity, specificity, ROC curves, DCA curves, and calibration curves. SHAP values were employed to interpret the models. The Logistic Regression model demonstrated the best predictive performance, with an AUC of 0.82 (95% CI: 0.69-0.95), accuracy of 77.59%, sensitivity of 85%, and specificity of 61.11%. The most significant predictors identified were age, 8 mm sag height difference, 5 mm Kx1, and 7 mm Kx2. SHAP analysis confirmed the importance of these features, particularly the 8 mm sag height difference. The Logistic Regression model successfully predicted the risk of Ortho-K lens decentration using key corneal morphological metrics and age. This model provides valuable support for clinicians in optimizing Ortho-K lens fitting strategies, potentially reducing the risk of adverse outcomes and improving the quality of vision for patients. Further validation in clinical settings is recommended.

Development and evaluation of an online education module to improve clinician knowledge and management of eating disorders in the peripartum: a pre-post survey study

ObjectiveEating disorders (EDs) comprise a range of illnesses characterised by disordered eating, distressing thoughts, and changes in weight. EDs in the perinatal period are a growing concern. Maternity staff receive little training in this area and often report feeling ill-equipped to recognise or respond to presentations of ED during this time. The study aimed to develop and evaluate an online educational module for clinicians and support workers to improve knowledge of EDs in the perinatal period.MethodEducation modules were developed using a co-design process with consumer advocates, peer support workers, clinicians, and experts. Consumer perspectives, evidence-based videos, activities, and text relating to screening, management, monitoring and referral of perinatal individuals with EDs were included in the module. Quantitative and qualitative data from pre- and post- surveys were used to evaluate changes in knowledge and confidence before and after completing the module, and to assess staff satisfaction, usability, and obtain feedback for improvement.ResultsUse of the online education module significantly increased staff knowledge of EDs in the perinatal period. Participants also felt more confident in discussing the topic with patients, screening, supporting, and referring a person with ED in the perinatal period. Participants also reported the module was engaging and easy-to-use.ConclusionsFindings indicate that the ED online education module is an engaging and easy-to-use tool for improving the knowledge and skills of the healthcare workforce, thereby improving patient care and health outcomes. The development of additional online resources for clinicians would be beneficial for increasing staff capability and improving patient services.

Nutraceuticals in osteoporosis prevention.

Nutraceuticals are gaining popularity as they can contribute to bone health by delaying the onset or slowing down the progression of pathological bone loss. Osteoporosis's bone loss is a concern for older adults and a crucial aspect of aging. Maintaining healthy bones is the key to living a full and active life. Our review explores the current knowledge on the role of nutraceuticals in preventing osteoporosis by focusing on three main aspects. First, we provide an overview of osteoporosis. Second, we discuss the latest findings on natural nutraceuticals and their efficacy in reducing bone loss, emphasizing clinical trials. Third, we conduct a structured analysis to evaluate nutraceuticals' pros and cons and identify translational gaps. In conclusion, we must address several challenges to consolidate our knowledge, better support clinicians in their prescriptions, and provide people with more reliable nutritional recommendations to help them lead healthier lives.

What I was thinking/what I would do differently: Technology-enabled traumatic stress support.

At the 39th meeting of the International Society of Traumatic Stress Studies, three leading researchers and clinicians in technology-enabled traumatic stress support were invited to reflect on their careers and contributions to the field. Dr. Brian P. Marx has led the development of large-scale technologies to screen, assess, and treat traumatic stress pathology across diverse etiologies and needs. Dr. Barbara O. Rothbaum, a pioneer in the development of virtual reality for exposure therapy, has demonstrated the efficacy and scalability of digital treatment for traumatic stress. Retired Col. Dr. Eric Vermetten has worked extensively on the intersection of basic mechanisms, novel psychological and biological treatment, and technology for scalable assessment and treatment, primarily in military and mass casualty contexts. The panelists were asked to reflect on their initial ambitions, concerns, unexpected challenges, and the influence of their work on new research trajectories. Their insights provide valuable lessons about the process and content of their work, and their pioneering efforts have significantly advanced the field of technology-enabled traumatic stress support.

Machine learning model predicting factors for incisional infection following right hemicolectomy for colon cancer

Background and aimColorectal cancer is a prevalent malignancy worldwide, and right hemicolectomy is a common surgical procedure for its treatment. However, postoperative incisional infections remain a significant complication, leading to prolonged hospital stays, increased healthcare costs, and patient discomfort. Therefore, this study aims to utilize machine learning models, including random forest, support vector machine, deep learning models, and traditional logistic regression, to predict factors associated with incisional infection following right hemicolectomy for colon cancer.MethodsClinical data were collected from 322 patients undergoing right hemicolectomy for colon cancer, including demographic information, preoperative chemotherapy status, body mass index (BMI), operative time, and other relevant variables. These data are divided into training and testing sets in a ratio of 7:3. Machine learning models, including random forest, support vector machine, and deep learning, were trained using the training set and evaluated using the testing set.ResultsThe deep learning model exhibited the highest performance in predicting incisional infection, followed by random forest and logistic regression models. Specifically, the deep learning model demonstrated higher area under the receiver operating characteristic curve (ROC-AUC) and F1 score compared to other models. These findings suggest the efficacy of machine learning models in predicting risk factors for incisional infection following right hemicolectomy for colon cancer.ConclusionsMachine learning models, particularly deep learning models, offer a promising approach for predicting the risk of incisional infection following right hemicolectomy for colon cancer. These models can provide valuable decision support for clinicians, facilitating personalized treatment strategies and improving patient outcomes.