Actual Treatments Research Articles

P1022 ChatGPT in the management of Inflammatory Bowel Disease, a future or a present reality?

Abstract Background The management of inflammatory bowel disease (IBD) involves complex clinical scenarios, especially when complications arise. Traditionally guided by clinical expertise and established guidelines, artificial intelligence (AI) is now being explored as an adjunct in medical care. This study assesses ChatGPT’s ability to provide IBD management recommendations in both initial and complex cases. By comparing ChatGPT’s responses to both, real-world decisions and medical treatment in European Crohn’s and Colitis Organisation (ECCO) guidelines, the study aims to evaluate AI’s alignment, reliability, and potential in IBD management. Methods A retrospective analysis was conducted of the electronic medical records of IBD patients in both initial and complicated phases. Management recommendations for 19 cases were generated using ChatGPT-4o and then compared with actual treatments and the ECCO guidelines. A gastroenterologist certified by the Mexican Association of Gastroenterology oversaw evaluations across 7 categories: 5-ASA, steroids, antibiotics, thiopurines, anti-TNF agents, anti-integrins, and anti-IL23. Cohen’s Kappa test was used to assess agreement. Results ChatGPT showed perfect agreement (Kappa = 1.000) with healthcare providers and ECCO guidelines for antibiotics, diagnostic workups, symptom management, surgical consultations, monitoring, and anti-IL-23 recommendations. Substantial agreement (Kappa ~0.6–0.8) was observed for 5-ASA and steroids, with minor variations but overall strong alignment. Moderate to fair agreement (Kappa ~0.3–0.5) was noted for anti-TNF and anti-integrins, reflecting variability in complex cases. For thiopurines, agreement was minimal, suggesting differences due to varying thresholds or interpretations (Figure 1). Conclusion ChatGPT displayed a perfect agreement with providers and guidelines in areas such as antibiotics, diagnostic workups, symptom management, surgical consultations, monitoring, and anti-IL-23 therapies, indicating its potential for standardising IBD care. However, discrepancies arise in complex cases involving anti-TNF and anti-integrins, possibly due to the inclusion of newer treatments not yet covered by ECCO guidelines. This underscores the necessity for AI systems to evolve alongside advancing treatment modalities. Differences in thiopurine recommendations highlight the enduring importance of clinical judgement. Notably, there is currently no standardisation in the management of IBD. This study illustrates ChatGPT’s promise as a decision-support tool for standardising IBD care. Future efforts should focus on validating AI to further apply it as an adjuvant in clinical decision-making and tailoring recommendations to individual patients.

Individualized treatment recommendations for patients with locally advanced head and neck squamous cell carcinoma utilizing deep learning.

The conventional treatment for locally advanced head and neck squamous cell carcinoma (LA-HNSCC) is surgery; however, the efficacy of definitive chemoradiotherapy (CRT) remains controversial. This study aimed to evaluate the ability of deep learning (DL) models to identify patients with LA-HNSCC who can achieve organ preservation through definitive CRT and provide individualized adjuvant treatment recommendations for patients who are better suited for surgery. Five models were developed for treatment recommendations. Their performance was assessed by comparing the difference in overall survival rates between patients whose actual treatments aligned with the model recommendations and those whose treatments did not. Inverse probability treatment weighting (IPTW) was employed to reduce bias. The effect of the characteristics on treatment plan selection was quantified through causal inference. A total of 7,376 patients with LA-HNSCC were enrolled. Balanced Individual Treatment Effect for Survival data (BITES) demonstrated superior performance in both the CRT recommendation (IPTW-adjusted hazard ratio (HR): 0.84, 95% confidence interval (CI), 0.72-0.98) and the adjuvant therapy recommendation (IPTW-adjusted HR: 0.77, 95% CI, 0.61-0.85), outperforming other models and the National Comprehensive Cancer Network guidelines (IPTW-adjusted HR: 0.87, 95% CI, 0.73-0.96). BITES can identify the most suitable treatment option for an individual patient from the three most common treatment options. DL models facilitate the establishment of a valid and reliable treatment recommendation system supported by quantitative evidence.

Validity and reliability of the osteoporotic fracture treatment score (OF score) and outcomes across various treatments in osteoporosis vertebral compression fracture patients

BackgroundOsteoporotic vertebral compression fractures (OVF) are prevalent and substantially impact healthcare systems and patients’ quality of life. The osteoporotic fracture treatment score (OF score), developed by the German Society of Orthopedics and Trauma (DGOU), guides surgical decisions, but its reliability and validity are underexplored. This study assessed the OF score’s inter- and intraobserver reliability, validated its treatment recommendations, and investigated intermediate outcomes of different DGOU-recommended surgical strategies for OVF.MethodsA retrospective cohort study was conducted. Inter- and intraobserver reliability of the OF score and its subcomponents were analyzed using clinical and radiographic data. Validity was assessed by comparing the OF score’s recommended treatments with actual treatments received. Outcomes at the final follow-up were back pain visual analog scale, Oswestry Disability Index, EQ-VAS, EQ-5D-5 L, adjacent fracture incidence, local kyphotic angle, and reoperation rates. Patients with at least 1-year follow-up were included.ResultsA total of 157 patients (84.7% female; mean age 74.2 ± 10.5 years) were evaluated. The most frequent osteoporotic fracture (OF) types were OF4 (49.0%) and OF3 (40.8%). The OF score demonstrated good interobserver reliability (ICC = 0.77, 95% CI: 0.65–0.86) and intraobserver reliability (ICC = 0.83, 95% CI: 0.72–0.90). Kappa values for subcomponents ranged from 0.57 to 0.89. Excluding patients with indeterminate recommendations (OF score = 6), 82.9% received treatments concordant with OF score recommendations. Receiver operating characteristic curve analysis showed an area under the curve of 0.77 (95% CI: 0.67–0.86); an OF score cutoff > 6.5 predicted actual treatment with 87.9% sensitivity and 61.0% specificity. All surgical treatments showed comparable improvements in clinical outcomes. However, patients treated with stand-alone cement augmentation (CA) had less local kyphotic angle correction (P = 0.004) and greater postoperative kyphotic progression (P < 0.001) than those undergoing short-segment (SS-PI) or long-segment instrumentation (LS-PI). No significant differences in adjacent fractures or complications were observed.ConclusionsThe OF score is a reliable and valid system with good discriminative ability for surgical decision-making in OVF patients. CA, SS-PI, and LS-PI are viable options with comparable functional outcomes. However, in OF3 or OF4 fractures, caution is advised due to lesser kyphosis correction and greater kyphotic progression with CA compared to SS-PI or LS-PI, as recommended by the DGOU.

Assessment of Professional Practices in the Care Pathway of Patients with Upper Aerodigestive Tract Cancer in a University Hospital.

The main objective of this study was to evaluate the alignment between treatment decisions made during multidisciplinary team meetings (MTMs) and the treatments received by patients with upper aerodigestive tract cancers. The secondary objective was to identify factors influencing potential discrepancies. This retrospective, single-center study was conducted at a tertiary referral center and included 147 patients diagnosed with squamous cell carcinoma of the upper aerodigestive tract. Patients were divided into two groups based on the match between MTM-decided and actual treatments. Multivariate analysis was performed to assess factors independently associated with discrepancies. Out of 147 patients, 28 (19%) received treatment that did not align with MTM decisions. Among these, eight died before treatment, one patient refused care, five received supportive care, five patients underwent surgery, three received radiotherapy alone, one patient underwent surgery and adjuvant radiochemotherapy, one patient underwent surgery and adjuvant radiotherapy alone, three patients received radiochemotherapy, and one patient received palliative chemotherapy. Independent significant factors associated with non-concordance included poor performance status (PS) and treatment not received at a tertiary reference center. Treatment shifts mainly involved downgrading from curative to palliative care. This study highlights the importance of patient health status in determining deviations from MTM decisions. Further efforts should focus on improving the integration of patient comorbidities and health status into MTM decision-making to optimize care delivery.

Reliability and validity of the Paprosky classification for acetabular bone loss based on level of orthopedic training.

Reliability and validity of the Paprosky classification for acetabular bone loss have been debated. Additionally, the relationship between surgeon training level and Paprosky classification accuracy/treatment selection is poorly defined. This study aimed to: (1) evaluate the validity of preoperative Paprosky classification/treatment selection compared to intraoperative classification/treatment selection and (2) evaluate the relationship between training level and intra-rater and inter-rater reliability of preoperative classification and treatment choice. Seventy-four patients with intraoperative Paprosky types [I (N = 24), II (N = 27), III (N = 23)] were selected. Six raters (Residents (N = 2), Fellows (N = 2), Attendings (N = 2)) independently provided Paprosky classification and treatment using preoperative radiographs. Graders reviewed images twice, 14 days apart. Cohen's Kappa was calculated for (1) inter-rater agreement of Paprosky classification/treatment by training level (2), intra-rater reliability, (3) preoperative and intraoperative classification agreement, and (4) preoperative treatment selection and actual treatment performed. Inter-rater agreement between raters of the same training level was moderate (K range = 0.42-0.50), and mostly poor for treatment selection (K range = 0.02-0.44). Intra-rater agreement ranged from fair to good (K range = 0.40-0.73). Agreement between preoperative and intraoperative classifications was fair (K range = 0.25-0.36). Agreement between preoperative treatment selections and actual treatments was fair (K range = 0.21-0.39). Inter-rater reliability of Paprosky classification was poor to moderate for all training levels. Preoperative Paprosky classification showed fair agreement with intraoperative Paprosky grading. Treatment selections based on preoperative radiographs had fair agreement with actual treatments. Further research should investigate the role of advanced imaging and alternative classifications in evaluation of acetabular bone loss.

Natural compounds combined with imatinib as promising antileukemic therapy: An updated review

Natural products (NP) have been an alternative therapy for several diseases for centuries, and they also serve as an essential source of bioactive molecules, enhancing our drug discovery capacity. Among these NP, some phytochemicals have shown multiple biological effects, including anticancer activity, with higher effectiveness and less toxicity than actual treatments, suggesting their possible use on resilient human malignancies such as leukemia. Imatinib mesylate (Im) is a selective tyrosine kinase inhibitor widely used as an anticancer drug, the gold standard to attend chronic myeloid leukemia (CML). Nevertheless, resistance to this drug in patients with CML renders it insufficient to eliminate cells with Philadelphia chromosome (BCR/ABL+). Moreover, recent studies show that imatinib can induce genotoxic and chromosomic damage in some in vitro and in vivo models. These facts urge finding new therapeutic alternatives to increase the effectiveness of antileukemic treatment. Recent research has shown that the combined effects of phytochemicals with imatinib can improve the cytotoxicity or resensitized the resistant cells to this drug in diverse leukemia cell lines. Independent mechanisms of action among phytochemicals and imatinib include BCR/ABL regulation, downregulation of transcription factors, inhibition of anti-apoptotic and activation of pro-apoptotic proteins, apoptosis induction dependent- and independent of ROS-overproduction, membrane functions disruption, induction of cell cycle arrest, and cell death. This review summarizes and discusses the synergic effect of some phytochemicals combined with imatinib on leukemia cells and the mechanism of action proposed for these combinations, looking to contribute to developing new effective alternatives for leukemia treatment.

DNA G-quadruplexes in the genome of Trypanosoma cruzi as potential therapeutic targets for Chagas disease: Dithienylethene ligands as effective antiparasitic agents

Chagas disease is caused by the parasite Trypanosoma cruzi and affects over 7 million people worldwide. The two actual treatments, Benznidazole (Bzn) and Nifurtimox, cause serious side effects due to their high toxicity leading to treatment abandonment by the patients. In this work, we propose DNA G-quadruplexes (G4) as potential therapeutic targets for this infectious disease. We have found 174 PQS per 100,000 nucleotides in the genome of T. cruzi and confirmed G4 formation of three frequent motifs. We synthesized a family of 14 quadruplex ligands based in the dithienylethene (DTE) scaffold and demonstrated their binding to these identified G4 sequences. Several DTE derivatives exhibited micromolar activity against epimastigotes of four different strains of T. cruzi, in the same concentration range as Bzn. Compounds L3 and L4 presented remarkable activity against trypomastigotes, the active form in blood, of T. cruzi SOL strain (IC50 = 1.5–3.3 μM, SI = 25–40.9), being around 40 times more active than Bzn and displaying much better selectivity indexes.

Estimated compared with actual plans of paediatric dental treatment performed under deep sedation: A retrospective cohort study

AbstractBackgroundPlanning the extent of paediatric dental treatment under deep sedation is highly important, as the duration of the sedation should be limited to approximately 1 h, and the amount of local anesthesia is limited by the children's body weight.AimTo compare treatment plans estimated at initial examinations with actual dental treatments under intravenous deep sedation. We examined factors that could affect the differences.DesignFor this retrospective cohort study, data were collected from the medical records of all the children younger than 18 years who underwent dental treatment under intravenous deep sedation during 2019–2021 at the Department of Pediatric Dentistry.ResultsIn total, 108 children were included. During the actual versus the estimated treatment under deep sedation, more teeth were treated (p &lt; .001), and the treatment was more complex (p &lt; .001). A longer waiting period for dental treatment was found to be correlated with a greater number of treated teeth than was estimated (p = .003) and with greater complexity of the actual than the estimated treatment (p = .003).ConclusionActual compared with estimated dental treatment under deep sedation involved more teeth and was of greater complexity. This suggests that referrals should include children with limited estimated treatment plans.

Pediatric femoral shaft fractures: the American Academy of Orthopaedic Surgeons clinical practice guidelines versus actual management in a teaching hospital.

In 2009, the clinical practice guidelines (CPG) were released by the American Academy of Orthopaedic Surgeons (AAOS), which outline an age-based approach for treating pediatric femoral shaft fractures (PFSF), both nonoperatively and operatively. The aim of the current study was to investigate potential disparities between the recommended treatments for PFSF based on the AAOS-CPG and the actual treatments administered in The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University. A retrospective review was conducted on the medical charts and radiographs of all PFSF treated at The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University from January 2014 to January 2022. We identified 445 children who met our inclusion criteria and evaluated their treatments according to the AAOS-CPG. Actual treatments were then compared with the treatments recommended by the AAOS-CPG. Binomial and multivariate logistic regression was used to examine whether different factors could predict the choice between operative and nonoperative management. Operative treatments were undertaken in 102 of 215 (47.4%) fractures in children younger than 6 years, in 102 of 122 (83.6%) fractures in those between 6 and 12 years of age, and in 107 of 108 (99.1%) fractures in those older than 12 years. Nonoperative management was conducted in 113 of 215 (52.6%) fractures in children younger than 6 years, in 20 of 122 (16.4%) fractures in those between 6 and 12 years of age, and in 1 of 108 (0.9%) fractures in those older than 12 years of age. Surgeon decisions for non-surgery were in agreement with the CPG 52.6% of the time, whereas agreement reached 90.9% for surgical choices. Predictors of actual operative management were age (P=0.01), patient weight (P<0.001), fracture pattern (P<0.001), presence of other orthopedic injuries requiring surgery (P=0.002), and polytrauma (P=0.02). There was limited concordance between actual treatments and CPG recommendations, particularly for the nonoperative management of fractures in children under 6 years old. Age, patient weight, fracture pattern, presence of other orthopedic injuries requiring surgery, and polytrauma were the main predictors of our operative decision-making process.

Inhibition of Shikimate Kinase from Methicillin-Resistant Staphylococcus aureus by Benzimidazole Derivatives. Kinetic, Computational, Toxicological, and Biological Activity Studies.

Antimicrobial resistance (AMR) is one of the biggest threats in modern times. It was estimated that in 2019, 1.27 million deaths occurred around the globe due to AMR. Methicillin-resistant Staphylococcus aureus (MRSA) strains, a pathogen considered of high priority by the World Health Organization, have proven to be resistant to most of the actual antimicrobial treatments. Therefore, new treatments are required to be able to manage this increasing threat. Under this perspective, an important metabolic pathway for MRSA survival, and absent in mammals, is the shikimate pathway, which is involved in the biosynthesis of chorismate, an intermediate for the synthesis of aromatic amino acids, folates, and ubiquinone. Therefore, the enzymes of this route have been considered good targets to design novel antibiotics. The fifth step of the route is performed by shikimate kinase (SK). In this study, an in-house chemical library of 170 benzimidazole derivatives was screened against MRSA shikimate kinase (SaSK). This effort led to the identification of the first SaSK inhibitors, and the two inhibitors with the greatest inhibition activity (C1 and C2) were characterized. Kinetic studies showed that both compounds were competitive inhibitors with respect to ATP and non-competitive for shikimate. Structural analysis through molecular docking and molecular dynamics simulations indicated that both inhibitors interacted with ARG113, an important residue involved in ATP binding, and formed stable complexes during the simulation period. Biological activity evaluation showed that both compounds were able to inhibit the growth of a MRSA strain. Mitochondrial assays showed that both compounds modify the activity of electron transport chain complexes. Finally, ADMETox predictions suggested that, in general, C1 and C2 can be considered as potential drug candidates. Therefore, the benzimidazole derivatives reported here are the first SaSK inhibitors, representing a promising scaffold and a guide to design new drugs against MRSA.

Determining individual suitability for neoadjuvant systemic therapy in breast cancer patients through deep learning.

The survival advantage of neoadjuvant systemic therapy (NST) for breast cancer patients remains controversial, especially when considering the heterogeneous characteristics of individual patients. To discern the variability in responses to breast cancer treatment at the individual level and propose personalized treatment recommendations utilizing deep learning (DL). Six models were developed to offer individualized treatment suggestions. Outcomes for patients whose actual treatments aligned with model recommendations were compared to those whose did not. The influence of certain baseline features of patients on NST selection was visualized and quantified by multivariate logistic regression and Poisson regression analyses. Our study included 94,487 female breast cancer patients. The Balanced Individual Treatment Effect for Survival data (BITES) model outperformed other models in performance, showing a statistically significant protective effect with inverse probability treatment weighting (IPTW)-adjusted baseline features [IPTW-adjusted hazard ratio: 0.51, 95% confidence interval (CI), 0.41-0.64; IPTW-adjusted risk difference: 21.46, 95% CI 18.90-24.01; IPTW-adjusted difference in restricted mean survival time: 21.51, 95% CI 19.37-23.80]. Adherence to BITES recommendations is associated with reduced breast cancer mortality and fewer adverse effects. BITES suggests that patients with TNM stage IIB, IIIB, triple-negative subtype, a higher number of positive axillary lymph nodes, and larger tumors are most likely to benefit from NST. Our results demonstrated the potential of BITES to aid in clinical treatment decisions and offer quantitative treatment insights. In our further research, these models should be validated in clinical settings and additional patient features as well as outcome measures should be studied in depth.

Potential utility of pretreatment serum miRNAs for optimal treatment selection in advanced high-grade serous ovarian cancer.

The primary treatment of patients with advanced ovarian cancer is selected from whether primary debulking surgery or neoadjuvant chemotherapy. We investigated whether pretreatment serum microRNA profiles are useful for selecting patients with advanced high-grade serous ovarian cancer who obtain better outcomes from undergoing primary debulking surgery or neoadjuvant chemotherapy. Consecutive patients with clinical stage IIIB-IVB and serum microRNA data were selected. Patients who underwent primary debulking surgery or neoadjuvant chemotherapy were subjected to 1:1 propensity score matching before comparing their progression-free survival using Cox modelling. Progression-free probabilities for the selected microRNA profiles were calculated, and the estimated progression-free survival with the recommended primary treatment was determined and compared with the actual progression-free survival of the patients. Of the 108 patients with stage IIIB-IVB disease, the data of 24 who underwent primary debulking surgery or neoadjuvant chemotherapy were compared. Eleven and three microRNAs were independent predictors of progression-free survival in patients who underwent primary debulking surgery and neoadjuvant chemotherapy, respectively. Two microRNAs correlated significantly with complete resection of the tumours in primary debulking surgery. No differences were found between the actual and estimated progression-free survival in the primary debulking surgery and neoadjuvant chemotherapy groups (P>0.05). The recommended and actual primary treatments were identical in 27 (56.3%) of the 48 patients. The median improved survival times between recommended and actual treatment were 11.7 and 32.6months for patients with actual primary debulking surgery and neoadjuvant chemotherapy, respectively. Pretreatment microRNA profiles could be used to select subgroups of patients who benefited more from primary debulking surgery or neoadjuvant chemotherapy and might contribute to selecting the optimal primary treatment modality in advanced high-grade serous ovarian cancer patients.

Abstract 3960: Establishment of humanized mouse models engrafted with luciferase-expressing acute myeloid leukemia cell lines

Abstract Introduction: Because acute myeloid leukemia (AML) is a very aggressive and quickly developing cancer, for which actual treatments are either inefficient, poorly tolerated, or leading to resistance, there is a strong need for an effective platform to evaluate novel therapies. Our aim is to provide a relevant humanized mouse model as a precious tool to evaluate innovated treatments to cure AML. Methods: Mice were humanized with CD34+ hematopoietic stem cells to reconstitute a complete human immune system. Three AML cell lines, namely OCI-AML2, OCI-AML3 and MOLM-14, all expressing mCherry and luciferase, were intravenously engrafted at different doses in non-humanized and CD34-humanized mice. Tumor proliferation was monitored by bioluminescence imaging (BLI) thanks to luciferase expression on tumor cells. Their expression of mCherry was also exploited to determine the presence of tumor cells in blood and tissues using flow cytometry. Results: All AML cell lines engrafted in mice, but we observed different growth kinetics and homogeneity depending on the humanization of mice and the dose injected. Indeed, tumor grew more slowly and heterogeneously in humanized mice, which underlines the role of human immune cells reconstituted in mice. This was improved by increasing the number of tumor cells injected. Tumor cells were found in femurs, spleen, kidneys, ovary, lungs, and uterus depending on the cell line. Mice survival was also highly affected by the tumor cell line engrafted. We observed that MOLM14 was the most aggressive model, while OCI-AML3 reached a steady state and were tolerated by mice over a long period. Conclusion: We established 3 different AML cell lines in a model of humanized mice which nicely recapitulates the growth of tumor cells in target organs. These 3 models behave differently in terms of growth kinetic, tolerability by mice, and organs infiltrated, which gives plenty of opportunities to evaluate novel therapies designed to cure AML. Citation Format: Emilie Bayon, Arije Mersni, Audrey Wetzel, Jade Villé, Kiave Yune Ho Wang Yin. Establishment of humanized mouse models engrafted with luciferase-expressing acute myeloid leukemia cell lines [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3960.

Using the right design controls for acupuncture trials: Methodological rigor and validity in research

Acupuncture treatment can be defined as a medical procedure with an acupuncture needle at acupoints. Establishing suitable control settings is essential, based on the target elements of the acupuncture therapy. In order to properly design a clinical trial or an experiment, a control group must be established. Here, we overview the significance of the control group and its limitations in acupuncture research. Clinical trials have employed a variety of study designs and controls for acupuncture treatment in order to compare the effects of actual treatments with control groups that include no treatment or treatment as usual, sham acupuncture at true acupoints, real acupuncture at non-acupoints, and sham acupuncture at non-acupoints. In order to determine the point-specificity of acupuncture, real acupuncture at non-acupoints should be taken into consideration, whereas sham acupuncture at the same true acupoints should be used to determine the needling-specific effect of acupuncture. It is crucial to choose the optimum control for acupuncture treatments depending on the study's main goal and to interpret the results in accordance with the research design.

Effect of high frequency repetitive transcranial magnetic stimulation (rTMS) on the balance and the white matter integrity in patients with relapsing-remitting multiple sclerosis: A long-term follow-up study

ObjectivesRepetitive Transcranial Magnetic Stimulation (rTMS) is considered as a safe and non-invasive developing technique used as a therapeutic method for patients with Relapsing-Remitting Multiple Sclerosis (RRMS) who suffer from disturbances in gait and balance. The aim of our study is to evaluate the long-term effect of high frequency rTMS as a therapeutic option for truncal ataxia in RRMS patients and to assess its impact on the integrity of the white matter (WMI), measured in the form of anisotropy metrics using diffusion tensor imaging (DTI). MethodsThe study was conducted in two phases: phase I; a randomized, single-blind, sham-controlled phase and phase II was a 12 months longitudinal open-label prospective phase. Phase I of the trial involved the randomization of 43 patients with RRMS and truncal ataxia to either real (n = 20) or sham (n = 19) rTMS (2 participants from each treatment group were excluded from the study; one developed a relapse before treatment, 2 declined to participate, and one did not show up). Phase II involved providing 12 actual treatments cycles to all patients; each cycle length is 4 weeks, repeated four times on a trimonthly basis, forming a total of 48 sessions. DTI was used for assessment of the WMI. All patients performed DTI 3 times: Imaging sessions were conducted at the screening visit, at the end of phase I, and after the last session in phase II for the first, second and third sessions respectively. A figure-of-8-shape coil, employing rTMS protocol and located over the cerebellum, was used. rTMS protocol is formed of 20 trains formed of 50 stimuli with 20 s apart (5 Hz of 80 % of resting Motor Threshold “MT”). The Berg Balance Scale (BBS), Time up and go (TUG) test, and 10-m walk test (10MWT) were first evaluated at the start of each cycle and just after the final rTMS session. ResultsThe genuine rTMS group's 10MWT, TUG, and BBS showed substantial improvement (p < 0.01), which is continued to be improved throughout the study Timeline, with a significant difference observed following the final rTMS session (P< 0.001). A longitudinal increase in FA was observed in both the Cerebello-Thalamo-Cortical (CTC) and Cortico-Ponto-Cerebellar (CPC) bilateral, as indicated by means of Fractional Anisotropy (FA) measures (p < 0.05). ConclusionIn ataxic RRMS patients, high frequency rTMS over the cerebellum has a long-term beneficial impact on both balance and WMI.

Analysis of Individualized Silicone Rubber Bolus Using Fan Beam Computed Tomography in Postmastectomy Radiotherapy: A Dosimetric Evaluation and Skin Acute Radiation Dermatitis Survey.

Objective: To investigate the dosimetric effects of using individualized silicone rubber (SR) bolus on the target area and organs at risk (OARs) during postmastectomy radiotherapy (PMRT), as well as evaluate skin acute radiation dermatitis (ARD). Methods: A retrospective study was performed on 30 patients with breast cancer. Each patient was prepared with an individualized SR bolus of 3 mm thickness. Fan-beam computed tomography (FBCT) was performed at the first and second fractions, and then once a week for a total of 5 times. Dosimetric metrics such as homogeneity index (HI), conformity index (CI), skin dose (SD), and OARs including the heart, lungs, and spinal cord were compared between the original plan and the FBCTs. The acute side effects were recorded. Results: In targets' dosimetric metrics, there were no significant differences in Dmean and V105% between planning computed tomography (CT) and actual treatments (P > .05), while the differences in D95%, V95%, HI, and CI were statistically significant (P < .05). In OARs, there were no significant differences between the Dmean, V5, and V20 of the affected lung, V5 of the heart and Dmax of the spinal cord (P > .05) except the V30 of affected lung, which was slightly lower than the planning CT (P < .05). In SD, both Dmax and Dmean in actual treatments were increased than plan A, and the difference was statistically significant (P < .05), while the skin-V20 and skin-V30 has no difference. Among the 30 patients, only one patient had no skin ARD, and 5 patients developed ARD of grade 2, while the remaining 24 patients were grade 1. Conclusion: The OR bolus showed good anastomoses and high interfraction reproducibility with the chest wall, and did not cause deformation during irradiation. It ensured accurate dose delivery of the target and OARs during the treatment, which may increase SD by over 101%. In this study, no cases of grade 3 skin ARD were observed. However, the potential of using OR bolus to reduce grade 1 and 2 skin ARD warrants further investigation with a larger sample size.

Deep learning to optimize radiotherapy decisions for elderly patients with early-stage breast cancer: a novel approach for personalized treatment.

The use of routine adjuvant radiotherapy (RT) after breast-conserving surgery (BCS) is controversial in elderly patients with early-stage breast cancer (EBC). This study aimed to evaluate the efficacy of adjuvant RT for elderly EBC patients using deep learning (DL) to personalize treatment plans. Five distinct DL models were developed to generate personalized treatment recommendations. Patients whose actual treatments aligned with the DL model suggestions were classified into the Consistent group, while those with divergent treatments were placed in the Inconsistent group. The efficacy of these models was assessed by comparing outcomes between the two groups. Multivariate logistic regression and Poisson regression analyses were used to visualize and quantify the influence of various features on adjuvant RT selection. In a cohort of 8,047 elderly EBC patients, treatment following the Deep Survival Regression with Mixture Effects (DSME) model's recommendations significantly improved survival, with inverse probability of treatment weighting (IPTW)-adjusted benefits, including a hazard ratio of 0.70 (95% CI, 0.58-0.86), a risk difference of 4.63% (95% CI, 1.59-7.66), and an extended mean survival time of 8.96 months (95% CI, 6.85-10.97), outperforming other models and the National Comprehensive Cancer Network (NCCN) guidelines. The DSME model identified elderly patients with larger tumors and more advanced disease stages as ideal candidates for adjuvant RT, though no benefit was seen in patients not recommended for it. This study introduces a novel DL-guided approach for selecting adjuvant RT in elderly EBC patients, enhancing treatment precision and potentially improving survival outcomes while minimizing unnecessary interventions.

EE320 Impact of NASH Disease Model Adjustment to New Literature Findings: Assessing Cost-Effectiveness of Actual and Theoretical Treatments

EE320 Impact of NASH Disease Model Adjustment to New Literature Findings: Assessing Cost-Effectiveness of Actual and Theoretical Treatments

Exploring Healthcare Applications of the Internet of Things: A Comprehensive Survey

The Internet of Things (IoT) is transforming healthcare by revolutionizing patient care through enhanced diagnostics, real-time examinations, and preventive as well as actual treatments. IoT in healthcare involves smart devices equipped with sensors that accurately collect data for further analysis and action. These devices leverage realtime data to enable monitoring, tracking, and management, thereby improving healthcare outcomes. The efficiency of IoT leads to better decision-making and reduces the risk of errors. Additionally, IoT can be used to prevent machine failures, improving the reliability and quality of patient supply chain responsiveness. This paper provides a comparative survey of IoT applications in the healthcare system.

Inferring actual treatment pathways from patient records

Objective:Treatment pathways are step-by-step plans outlining the recommended medical care for specific diseases; they get revised when different treatments are found to improve patient outcomes. Examining health records is an important part of this revision process, but inferring patients’ actual treatments from health data is challenging due to complex event-coding schemes and the absence of pathway-related annotations. The objective of this study is to develop a method for inferring actual treatment steps for a particular patient group from administrative health records — a common form of tabular healthcare data — and address several technique- and methodology-based gaps in treatment pathway-inference research. Methods:We introduce Defrag, a method for examining health records to infer the real-world treatment steps for a particular patient group. Defrag learns the semantic and temporal meaning of healthcare event sequences, allowing it to reliably infer treatment steps from complex healthcare data. To our knowledge, Defrag is the first pathway-inference method to utilise a neural network (NN), an approach made possible by a novel, self-supervised learning objective. We also developed a testing and validation framework for pathway inference, which we use to characterise and evaluate Defrag’s pathway inference ability, establish benchmarks, and compare against baselines. Results:We demonstrate Defrag’s effectiveness by identifying best-practice pathway fragments for breast cancer, lung cancer, and melanoma in public healthcare records. Additionally, we use synthetic data experiments to demonstrate the characteristics of the Defrag inference method, and to compare Defrag to several baselines, where it significantly outperforms non-NN-based methods. Conclusions:Defrag offers an innovative and effective approach for inferring treatment pathways from complex health data. Defrag significantly outperforms several existing pathway-inference methods, but computationally-derived treatment pathways are still difficult to compare against clinical guidelines. Furthermore, the open-source code for Defrag and the testing framework are provided to encourage further research in this area.