Treatment Planning Process Research Articles

Estimation of heart dose in left breast cancer radiotherapy: Assessment of vDIBH feasibility using the supervised machine learning algorithm.

The volunteer deep inspiration breath hold (vDIBH) technique is used to reduce the heart dose in left breast cancer radiotherapy. Many times, it is faced that despite rigorous exercise and training, not all patients get benefited as expected. The primary objective of this study was to develop a machine learning program for prediction of mean heart dose before left breast radiotherapy under vDIBH. The present work is based on the dosimetric parameters of eighty-two left breast cancer patients, who have undergone modified radical mastectomy, enrolled for their radiation treatment. The trained machine learning algorithm employed linear regression to establish a correlation between Haller Index and heart mean dose (HMD) received during the ca left breast cancer radiotherapy. Subsequently, HMD values were used to model the regression relationship with maximum heart distance (MHD). The method adopted is beneficial in patient selection and assessment for suitability of patients' radiotherapy planning under vDIBH treatment technique. For data from 21 test patients, the mean of HMD obtained from the treatment planning system (TPS) and the mean of predicted HMD by developed program were found to be 468.76 cGy and 464.66 cGy, respectively. The present work facilitates precise HMD prediction in left breast cancer radiation therapy even before starting the treatment planning process. Additionally, this program offers suggestions in terms of modifications in treatment settings for even better results of vDIBH techniques if not matches with the anticipated results.

Enhancing the drug addiction treatment service by introducing a new residential treatment model in the Philippines: A qualitative study

BackgroundThere is an increased demand for quality treatment and rehabilitation services for people who use drugs (PWUDs) in the Philippines. In response, the Philippines Government’s Department of Health (DOH) has established a new residential treatment model, Intensive Treatment and Rehabilitation Program for Residential Treatment and Rehabilitation Centers (INTREPRET), and integrated it into the existing treatment service platform of 21 DOH-owned Treatment and Rehabilitation Centers (TRCs). We conducted a qualitative study to identify the changes engendered by the implementation of this treatment model.MethodsData were collected through individual face-to-face interviews. We interviewed purposefully selected 29 patients and 35 facilitators of INTREPRET group sessions in seven TRCs. We transcribed the interview records and organized the narrative information into key themes using thematic analysis during the coding process.ResultsThe changes perceived by the study participants included the attitude and behavior of patients, attitude and competency of facilitators, relationship between facilitators and patients, treatment planning and review process, efficient and standardized treatment services, and monitoring mechanisms of the patient’s recovery process. Participants also noted challenges in INTREPRET implementation, including family participation in therapy sessions, lack of facilitators, securing a conducive place for conducting sessions, and reproducing workbooks.ConclusionsThe results imply that the introduction of INTREPRET could improve treatment service quality and the effectiveness of treatment, which were primarily associated with behavioral changes in patients, improved relationship between patients and facilitators, and INTREPRET’s alignment with key international treatment standards. However, despite the positive changes perceived by the participants, certain challenges pertaining to family participation in therapy sessions and the lack of resources were identified. These criticisms must be addressed by DOH, along with an integration of INTREPRET into its policy and strategic framework, to ensure the effectiveness and sustainability of the new treatment model.

Multicriteria optimization achieves superior normal tissue sparing in volumetric modulated arc therapy for gastric cancer

ObjectiveTo evaluate the benefits of volumetric modulated arc therapy (VMAT) based on multicriteria optimization (MCO) for gastric cancer patients, particularly the protection of serial organs at risk (OARs) that overlap with the target volume.MethodsMCO and single-criterion optimization (SCO) VMAT plans were conducted among 30 gastric cancer patients, with a prescription dose of 50.4 Gy delivered in 28 fractions. All treatment plans underwent review, and a comparison was made between the active planning time and different dose-volume parameters.ResultsBoth the MCO and SCO VMAT plans achieved the target dose coverage, with no significant difference in the conformity index (CI) for the planning target volume (PTV), at median CI values of 0.887 and 0.891, respectively (P = 0.417). The MCO plans showed a slight but significant increase in the homogeneity index of the PTV, with a median increase of 0.029 (P < 0.001). Additionally, the MCO plans resulted in a lower D2% to the small intestine and duodenum, with reductions of 3.43 Gy and 0.3 Gy, respectively (P < 0.05). Furthermore, the Dmax to the small intestine correlated moderately with the overlapping volume between the small intestine and the target volume (ρ = 0.42, P = 0.023). Except for the mean dose to the liver, the MCO plans performed better in terms of dose indicators for other OARs. Moreover, compared to the SCO plans, the median active planning time in the MCO plans was significantly reduced by 53.2 min (P < 0.0001).ConclusionsMCO can effectively help the physicians to quickly select an optimal treatment plan for patients with gastric cancer. It has been shown that MCO VMAT plans can significantly reduce the dose to OARs and shorten the active planning time, with acceptable target coverage. In addition, these plans take less dosimetric time, thereby streamlining the treatment planning process.

Characterizing the unseen: Clinical and radiographic perspectives on unilateral condylar hyperplasia

ObjectivesUnilateral condylar hyperplasia (UCH), marked by progressive condylar growth, occurs between ages 11–30 with unclear etiology. This retrospective study aims to clarify the clinical, radiographic, and demographic features of UCH to improve its diagnosis and treatment. Material and methodsData for all patients included in this study were retrieved from the archive. Inclusion criteria were the diagnosis of UCH supported by a positive bone scan above 10% of condylar uptake in SPECT/CT, the patient's history of progressive facial asymmetry, symptoms confirmed by the orthodontist during follow-up, and clinical and radiological evaluation. Demographic characteristics, along with volumetric and linear measurements, were statistically evaluated. ResultsForty-one patients were included in this study with 70.73% female predominance. Patients were classified as transverse and vertical type condylar hyperplasia (CH) according to their prominent asymmetry characteristics. Eighteen patients were classified as vertical type CH and 23 patients were classified as transverse type CH. Twenty had left-side condylar overgrowth, and 21 had right-side overgrowth. Condylar volume difference was significantly higher in vertical type CH patients compared to transverse type CH (p = 0.004). No correlation was found between growth rate (bone scan uptake ratio) and condylar volume difference in patients with vertical type and transverse type CH patients (p = 0.205). ConclusionParticularly in cases that exhibit a pronounced vertical growth tendency, volumetric and linear measurements can guide the timing and treatment planning process.

Transformer-Integrated Hybrid Convolutional Neural Network for Dose Prediction in Nasopharyngeal Carcinoma Radiotherapy.

Radiotherapy is recognized as the major treatment of nasopharyngeal carcinoma. Rapid and accurate dose prediction can improve the efficiency of the treatment planning process and the quality of radiotherapy plans. Currently, deep learning-based methods have been widely applied to dose prediction for radiotherapy treatment planning. However, it is important to note that existing models based on Convolutional Neural Networks (CNN) often overlook long-distance information. Although some studies try to use Transformer to solve the problem, it lacks the ability of CNN to process the spatial information inherent in images. Therefore, we propose a novel CNN and Transformer hybrid dose prediction model. To enhance the transmission ability of features between CNN and Transformer, we design a hierarchical dense recurrent encoder with a channel attention mechanism. Additionally, we propose a progressive decoder that preserves richer texture information through layer-wise reconstruction of high-dimensional feature maps. The proposed model also introduces object-driven skip connections, which facilitate the flow of information between the encoder and decoder. Experiments are conducted on in-house datasets, and the results show that the proposed model is superior to baseline methods in most dosimetric criteria. In addition, the image analysis metrics including PSNR, SSIM, and NRMSE demonstrate that the proposed model is consistent with ground truth and produces promising visual effects compared to other advanced methods. The proposed method could be taken as a powerful clinical guidance tool for physicists, significantly enhancing the efficiency of radiotherapy planning. The source code is available at https://github.com/CDUTJ102/THCN-Net .

Removable partial dentures: Part 1.

The provision of removable partial dentures (RPDs) is an important skill for practitioners and it can often be challenging to make a successful prosthesis which the patient finds satisfactory. This three-part series has been designed to provide an overview of the clinical management of patients requiring RPDs. This first part provides a refresher of the aspects of the history and examination that are relevant to RPDs. We describe some key principles that are relevant to challenging denture cases. This will help the reader begin the treatment planning process and understand some of the factors which influence the prognosis of dentures.

The role of 3D cinematic rendering in the evaluation of upper extremity trauma.

Traumatic upper extremity injuries are a common cause of emergency department visits, comprising between 10-30% of traumatic injury visits. Timely and accurate evaluation is important to prevent severe complications such as permanent deformities, ischemia, or even death. Computed tomography (CT) and CT angiography (CTA) are the favored non-invasive imaging techniques for assessing upper extremity trauma, playing a crucial role in both the treatment planning and decision-making processes for such injuries. In CT postprocessing, a novel 3D rendering method, cinematic rendering (CR), employs sophisticated lighting models that simulate the interaction of multiple photons with the volumetric dataset. This technique produces images with realistic shadows and improved surface detail, surpassing the capabilities of volume rendering (VR) or maximal intensity projection (MIP). Considering the benefits of CR, we demonstrate its use and ability to achieve photorealistic anatomic visualization in a series of 11 cases where patients presented with traumatic upper extremity injuries, including bone, vascular, and skin/soft tissue injuries, adding to diagnostic confidence and intervention planning.

The Efficacy of Diagnostic Plaster Models in Orthodontic Diagnosis and Treatment Planning.

The growing integration of digital technologies in orthodontics is shifting the orthodontic diagnosis and recordkeeping paradigm, replacing conventional plaster models with intraoral scanning and 3D photography. This study investigated the impact of orthodontic plaster models on orthodontic diagnosis and treatment planning decisions by orthodontists. Thirty-three orthodontists assessed six patients' records with different malocclusion cases. Each case was assessed twice by each orthodontist evaluating a case: the first evaluation with digital records without diagnostic casts and the second evaluation with the added diagnostic orthodontic plaster model. Diagnostic and treatment plan decisions for each malocclusion case were compared with and without the aid of the diagnostic orthodontic plaster models to assess the plaster model's impact on the treatment plan's soundness. Statistically insignificant differences were found for the diagnoses and treatment plans with or without the aid of orthodontic plaster models. Intraclass correlation coefficients revealed agreement among orthodontists for both evaluated situations (0.685; p < 0.0001). Plaster models were found to significantly influence orthodontists' decisions about the need for surgical intervention (p = 0.026), but they did not significantly impact the overall malocclusion diagnostic classification nor the decision regarding the extent of treatment, whether comprehensive or limited (p = 0.146) and extraction versus non-extraction approaches (p = 0.266). These findings support the idea that digital record alternatives may be viable for orthodontic recordkeeping purposes. Within the limitations of this study, it can be concluded that the presence or absence of orthodontic plaster models does not significantly impact the orthodontic diagnosis or treatment planning process.

Computational modeling of tumor invasion from limited and diverse data in Glioblastoma

For diseases with high morbidity rates such as Glioblastoma Multiforme, the prognostic and treatment planning pipeline requires a comprehensive analysis of imaging, clinical, and molecular data. Many mutations have been shown to correlate strongly with the median survival rate and response to therapy of patients. Studies have demonstrated that these mutations manifest as specific visual biomarkers in tumor imaging modalities such as MRI. To minimize the number of invasive procedures on a patient and for the overall resource optimization for the prognostic and treatment planning process, the correlation of imaging and molecular features has garnered much interest. While the tumor mass is the most significant feature, the impacted tissue surrounding the tumor is also a significant biomarker contributing to the visual manifestation of mutations — which has not been studied as extensively. The pattern of tumor growth impacts the surrounding tissue accordingly, which is a reflection of tumor properties as well. Modeling how the tumor growth impacts the surrounding tissue can reveal important information about the patterns of tumor enhancement, which in turn has significant diagnostic and prognostic value. This paper presents the first work to automate the computational modeling of the impacted tissue surrounding the tumor using generative deep learning. The paper isolates and quantifies the impact of the Tumor Invasion (TI) on surrounding tissue based on change in mutation status, subsequently assessing its prognostic value. Furthermore, a TI Generative Adversarial Network (TI-GAN) is proposed to model the tumor invasion properties. Extensive qualitative and quantitative analyses, cross-dataset testing, and radiologist blind tests are carried out to demonstrate that TI-GAN can realistically model the tumor invasion under practical challenges of medical datasets such as limited data and high intra-class heterogeneity.

Deep learning-based prediction of the dose-volume histograms for volumetric modulated arc therapy of left-sided breast cancer.

The advancements in artificial intelligence and computational power have made deep learning an attractive tool for radiotherapy treatment planning. Deep learning has the potential to significantly simplify the trial-and-error process involved in inverse planning required by modern treatment techniques such as volumetric modulated arc therapy (VMAT). In this study, we explore the ability of deep learning to predict organ-at-risk (OAR) dose-volume histograms (DVHs) of left-sided breast cancer patients undergoing VMAT treatment based solely on their anatomical characteristics. The predicted DVHs could be used to derive patient-specific dose constraints and dose objectives, streamlining the treatment planning process, standardizing the quality of the plans, and personalizing the treatment planning. This study aimed to develop a deep learning-based framework for the prediction of organ-specific dose-volume histograms (DVH) based on structures delineated for left-sided breast cancer treatment. We used a dataset of 249 left-sided breast cancer patients treated with tangential VMAT fields. We extracted delineated structures and dose distributions for each patient and derived slice-by-slice DVHs for planning target volume (PTV) and organs-at-risk. The patients were divided into training (70%, n=174), validation (10%, n=24), and test (20%, n=51) sets. Collected data were used to train a deep learning model for the prediction of the DVHs based on the delineated structures. The developed deep learning model comprised a modified DenseNet architecture followed by a recurrent neural network. In the independent test set (n=51), the point-wise differences in the slice-by-slice DVHs between the clinical and predicted DVHs were small; the mean squared errors were 3.53, 1.58, 2.28, 3.37, and 1.44 [×10-4] for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. With the derived cumulative DVHs, the mean absolute difference±standard deviation of mean doses between the clinical and the predicted DVH were 0.08± 0.04Gy, 0.24± 0.22Gy, 0.73± 0.46Gy, 0.07± 0.06Gy, and 0.14± 0.14Gy for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. The deep learning-based approach enabled automatic and reliable prediction of the DVH based on delineated structures. The predicted DVHs could potentially serve as patient-specific clinical goals used to aid treatment planning and avoid suboptimal plans or to derive optimization objectives and constraints for automated treatment planning.

Ensuring High Quality Treatment Plans with a Plan Quality Review Checklist

Treatment plan quality is a crucial component for a successful outcome of radiation therapy treatments. As the complexity of radiation therapy planning and delivery techniques increases, the role of the medical physicist in assessing treatment plan quality becomes more critical. Integrating plan quality review throughout the treatment planning process allows improvements without delaying treatment or rushing to produce changes at the last minute. In this work, we aim to provide practical check items for physicists to reference when assessing treatment plan quality with a critical eye, asking questions such as “is this the best dose distribution feasible for this patient?,” “could we change any planning parameters to improve plan quality?,” and “could we change the planning strategy for this particular patient or for future patients?”; and to work with planners and physicians to create a multidisciplinary collaborative culture that achieves the best plan feasible for every patient. We tabulate the features that affect plan quality in each process step and check details for individual items. This report is aimed at medical physicists, planners, radiation oncologists, and other professionals who are involved in treatment planning.

Feasibility of interdisciplinary evaluation in non-arthritic hip pain: A randomized trial

BackgroundPhysical therapy and orthopaedic surgery are two common treatments for non-arthritic hip pain. Interdisciplinary evaluation across these disciplines may produce a more supportive treatment-planning process; however, the feasibility of such an evaluation remains unknown. Hypothesis ObjectiveTo assess the feasibility of an interdisciplinary evaluation with an orthopaedic surgeon and physical therapist for non-arthritic hip pain. Study designObservational feasibility study of a randomized controlled trial. MethodsParticipants were randomized to an interdisciplinary (surgeon + physical therapist) or standard (surgeon) evaluation in a hip preservation clinic. Recruitment rate was recorded. Retention rate was calculated for all variables of interest. Enrollment and refusal reasons were recorded as patient quotes and categorized by a single grader. Time spent in clinic was compared across groups using Mann Whitney U tests (P ≤ 0.05). Study clinicians were interviewed, and responses were categorized based on pre-determined themes. ResultsEighty-one percent of eligible patients enrolled over a 15-month recruitment period. Willingness(n = 16), urgency to resolve pain(n = 10), financial compensation(n = 1), interest in research(n = 42), physical therapy(n = 6), or multiple-provider care(n = 15) were participants’ enrollment reasons; reason was not recorded for 22 participants. Time(n = 11), preference for single-provider care(n = 6), current physical therapy treatment(n = 1), and disinterest in physical therapy(n = 7) or research(n = 2) were refusal reasons of patients who did not enroll. Retention for primary variables of interest was 100% in both groups. Participants spent, on average, 23.5 min more time in clinic for the interdisciplinary evaluation compared to the standard (P < 0.001). ConclusionsAn interdisciplinary evaluation for patients with non-arthritic hip pain that included a physical therapist and orthopaedic surgeon in a hip preservation clinic was feasible and may better inform the treatment planning process.

The Accuracy of Digital Impressions versus Conventional Impressions in Neonates with Cleft Lip and/or Palate: A Laboratory-Based Study.

Cleft lip and palate (CL/P) are a common congenital craniofacial anomaly requiring precise impressions for effective treatment. Conventional impressions (CIs) pose challenges in neonates with CL/P due to their delicate oral anatomy. While digital impressions (DIs) are increasingly recognised for their potential benefits over conventional methods in dentistry, their accuracy and application in neonates with cleft lip and palate (CL/P) remain underexplored. This study aimed to assess the accuracy of DIs compared to CIs in neonates with CL/P, using alginate and putty materials as references. A laboratory-based case-control study was conducted, utilising soft acrylic models resembling neonatal mouths with CL/P. Alginate and putty impressions were obtained conventionally, while digital impressions were captured using an intraoral scanner (IOS). A total of 42 models were analysed, divided evenly into three groups, with each group comprising 14 models. Superimposition and surface discrepancy analyses were performed to evaluate impression accuracy. The results revealed no statistically significant differences between the digital and conventional impressions in their intra-arch measurements and surface discrepancies. The mean measurement values did not significantly differ among groups, with p values indicating no significant variations (p > 0.05), confirmed by an analysis of variance. High intra-examiner reliability with Intra Class Coefficient (ICC) values close to 1 indicated consistent measurements over time. The current study demonstrates that DIs are equally accurate as conventional alginate and putty impressions in neonates with cleft lip and palate, offering a viable and less invasive alternative for clinical practise. This advancement holds promise for improving the treatment planning process and enhancing patient comfort, particularly in vulnerable neonatal populations. Further research is warranted to explore the clinical implications and factors affecting DI accuracy in this population.

The rehabilitation of a combined mid-facial defect using a magnetretained intra- and extra-oral prosthesis: a case report

There are several treatment options available to restore function and appearance in patients with combined mid-facial defects. Owing to the size of the defect and the associated size and weight of the prostheses, adequate retention can be challenging to achieve. Retention of a facial prosthesis can be improved using several techniques, such as medical grade adhesives, attachments, or osseo-integrated implants. For patients with a history of radiotherapy, surgical rehabilitation may be less favourable than non-surgical approaches owing to the risk of osteoradionecrosis and a reduced blood supply in the surgical fields. This clinical case report highlights the conservative rehabilitation of a combined mid-facial defect using a magnet-retained intra-oral and extra-oral prosthesis. CPD/Clinical Relevance: A thorough medical and clinical assessment will highlight factors that will influence the treatment planning process when managing a combined mid-facial defect.

A randomized controlled trial of shared decision-making treatment planning process to enhance shared decision-making in patients with MBC

PurposeOpportunities exist for patients with metastatic breast cancer (MBC) to engage in shared decision-making (SDM). Presenting patient-reported data, including patient treatment preferences, to oncologists before or during a treatment plan decision may improve patient engagement in treatment decisions.MethodsThis randomized controlled trial evaluated the standard-of-care treatment planning process vs. a novel treatment planning process focused on SDM, which included oncologist review of patient-reported treatment preferences, prior to or during treatment decisions among women with MBC. The primary outcome was patient perception of shared decision-making. Secondary outcomes included patient activation, treatment satisfaction, physician perception of treatment decision-making, and use of treatment plans.ResultsAmong the 109 evaluable patients from December 2018 to June 2022, 28% were Black and 12% lived in a highly disadvantaged neighborhood. Although not reaching statistical significance, patients in the intervention arm perceived SDM more often than patients in the control arm (63% vs. 59%; Cramer’s V = 0.05; OR 1.19; 95% CI 0.55–2.57). Among patients in the intervention arm, 31% were at the highest level of patient activation compared to 19% of those in the control arm (V = 0.18). In 82% of decisions, the oncologist agreed that the patient-reported data helped them engage in SDM. In 45% of decision, they reported changing management due to patient-reported data.ConclusionsOncologist engagement in the treatment planning process, with oncologist review of patient-reported data, is a promising approach to improve patient participation in treatment decisions which should be tested in larger studies.Trial registrationNCT03806738.

The effect of antitumor therapy on the reproductive system, the possibility of preserving female fertility

The influence of malignant neoplasms and their treatment methods on the reproductive function of women is one of the significant problems of oncogynecology. The mechanisms of ovarian follicle loss caused by chemotherapy have their own characteristics depending on the characteristics of the cytotoxic agent and act differently on different populations of ovarian cells. The toxic effect on fertility of the main groups of antitumor drugs is considered. Reproductive dysfunction has negative consequences for a woman’s physical and mental health. The use of methods that reduce the effect of cytotoxic agents on the ovary helps to prevent premature ovarian insufficiency, leading to infertility. The article discusses modern methods of fertility preservation using assisted reproductive technologies. All cancer patients of reproductive age should receive full oncofertility counseling as early as possible, during the treatment planning process, regardless of the type and stage of the disease.

The Impact Use of Anatomical Region Templates on the Quality of Planning Radiation Therapy

Relevance: This article reviews a study that evaluates the effect of using anatomical region templates at the delineation stage on the quality of exposure plans. We compare two groups of plans: with and without the use of anatomical region templates. The study aims to optimize planning processes and compliance with standards. It is hypothesized that the use of anatomical region templates at the delineation stage may influence the efficiency and accuracy of radiation therapy planning. Conclusions: the use of anatomical region templates greatly simplifies and speeds up the treatment planning process, allowing for increased productivity and more patients to be treated without sacrificing quality of care, as well as reducing the likelihood of missing structures, thereby ensuring safe treatment. The creation of anatomical region templates allows standardized procedures and dosage parameters to be established, thereby improving the quality and uniformity of radiation therapy. However, anatomical region templates can limit individualized treatment because they are based on standardized templates and may not take into account the unique characteristics of patients. These results highlight the significant advantages of using anatomical region templates in radiotherapy planning, but also highlight the limitations of this method in individualizing treatment.

Design and implementation of automated notification systems and an electronic whiteboard for radiation therapy planning monitoring.

Radiotherapy (RT) treatment and treatment planning is a complex process prepared and delivered by a multidisciplinary team of specialists. Efficient communication and notification systems among different team members are therefore essential to ensure the safe, timely delivery of treatments to patients. To address this issue, we developed and implemented automated notification systems and an electronic whiteboard to track every CT simulation, contouring task, the new-start schedule, and physician's appointments and tasks, and notify team members of overdue and missing tasks and appointments. The electronic whiteboard was developed to have a straightforward view of current patients' planning workflow and to help different team members coordinate with each other. The systems were implemented and have been used at our center to monitor the progress of treatment-planning tasks for over 2 years. The last-minute plans were relatively reduced by about 40% in 2023 compared to 2021 and 2022 with a p-value<0.05. The overdue contouring tasks of more than 1 day decreased from 46.8% in 2019 and 33.6% in 2020 to 20%-26.4% in 2021-2023 with a p-value<0.05 after the implementation of the notification system. The rate of plans with 1-3 day planning time decreased by 20.31%, 39.32%, and 24.08% with a p-value<0.05 and the rate of plans with 1-3 day planning time due to the contouring task overdue more than 1 day decreased by 49.49%, 56.89%, and 46.52% with a p-value<0.05 after the implementation. The rate of outstanding appointments that are overdue by more than 7 days decreased by more than 5% with a p-value<0.05 following the implementation of the system. Our experience shows that this system requires minimal human intervention, improves the treatment planning workflow and process by reducing errors and delays in the treatment planning process, positively impacts on-time treatment plan completion, and reduces the need for compressed or rushed treatment planning timelines.

Demonstrating the utility of Instrumented Gait Analysis in the treatment of children with cerebral palsy.

Instrumented gait analysis (IGA) has been around for a long time but has never been shown to be useful for improving patient outcomes. In this study we demonstrate the potential utility of IGA by showing that machine learning models are better able to estimate treatment outcomes when they include both IGA and clinical (CLI) features compared to when they include CLI features alone. We carried out a retrospective analysis of data from ambulatory children diagnosed with cerebral palsy who were seen at least twice at our gait analysis center. Individuals underwent a variety of treatments (including no treatment) between sequential gait analyses. We fit Bayesian Additive Regression Tree (BART) models that estimated outcomes for mean stance foot progression to demonstrate the approach. We built two models: one using CLI features only, and one using CLI and IGA features. We then compared the models' performance in detail. We performed similar, but less detailed, analyses for a number of other outcomes. All results were based on independent test data from a 70%/30% training/testing split. The IGA model was more accurate than the CLI model for mean stance-phase foot progression outcomes (RMSEIGA = 11∘, RMSECLI = 13∘) and explained more than 1.5 × as much of the variance (R2IGA = .45, R2CLI = .28). The IGA model outperformed the CLI model for every level of treatment complexity, as measured by number of simultaneous surgeries. The IGA model also exhibited superior performance for estimating outcomes of mean stance-phase knee flexion, mean stance-phase ankle dorsiflexion, maximum swing-phase knee flexion, gait deviation index (GDI), and dimensionless speed. The results show that IGA has the potential to be useful in the treatment planning process for ambulatory children diagnosed with cerebral palsy. We propose that the results of machine learning outcome estimators-including estimates of uncertainty-become the primary IGA tool utilized in the clinical process, complementing the standard medical practice of conducting a through patient history and physical exam, eliciting patient goals, reviewing relevant imaging data, and so on.

Robustness of carbon-ion radiotherapy against DNA damage repair associated radiosensitivity variation based on a biophysical model.

Interpatient variation of tumor radiosensitivity is rarely considered during the treatment planning process despite its known significance for the therapeutic outcome. To apply our mechanistic biophysical model to investigate the biological robustness of carbon ion radiotherapy (CIRT) against DNA damage repair interference (DDRi) associated patient-to-patient variability in radiosensitivity and its potential clinical advantages against conventional radiotherapy approaches. The "UNIfied and VERSatile bio response Engine" (UNIVERSE) was extended by carbon ions and its predictions were compared to a panel of in vitro and in vivo data including various endpoints and DDRi settings within clinically relevant dose and linear energy transfer (LET) ranges. The implications of UNIVERSE predictions were then assessed in a clinical patient scenario considering DDRi variance. UNIVERSE tests well against the applied benchmarks. While in vitro survival curves were predicted with an R2>0.92, deviations from in vivo RBE data were less than 5.6% The conducted paradigmatic patient plan study implies a markedly reduced significance of DDRi based radiosensitivity variability in CIRT (13% change of in target) compared to conventional radiotherapy (62%) and that boosting the LET within the target further amplifies this robustness of CIRT (8%). In the case of heightened tumor radiosensitivity, a dose de-escalation strategy for photons allows a reduction of the maximum effective dose within the normal tissue (NT) from a of 2.65 to 1.64Gy, which lies below the level found for CIRT ( =2.41Gy) for the analyzed plan and parameters. However, even after de-escalation, the integral effective dose in the NT is found to be substantially higher for conventional radiotherapy in comparison to CIRT ( of 0.75, 0.46, and 0.24Gy for the conventional plan, its de-escalation and CIRT, respectively). The framework offers adequate predictions of in vitro and in vivo radiation effects of CIRT while allowing the consideration of DRRi based solely on parameters derived from photon data. The results of the patient planning study underline the potential of CIRT to minimize important sources of interpatient divergence in therapy outcome, especially when combined with techniques that allow to maximize the LET within the tumor. Despite the potential of de-escalation strategies for conventional radiotherapy to reduce the maximum effective dose in the NT, CIRT appears to remain a more favorable option due to its ability to reduce the integral effective dose within the NT.