Background: The complexity of systemic variables and comorbidities makes it difficult to determine the best treatment for patients with hepatocellular carcinoma (HCC). It is impossible to perform a multidimensional evaluation of every patient, but the development of guidelines based on analyses of said complexities would be the next best option. Whereas conventional statistics are often inadequate for developing multivariate predictive models, data mining has proven more capable. Patients, methods and findings: Clinical profiles and treatment responses of 537 patients diagnosed with Barcelona Clinic Liver Cancer stages B and C from 2009 to 2019 were retrospectively analyzed using 4 decision tree algorithms. A combination of 19 treatments, 7 biomarkers, and 4 states of hepatitis was tested to determine which combinations would result in survival times greater than a year in duration. Just 2 of the algorithms produced complete models through single trees, which made them only the ones suitable for clinical judgement. A combination of alpha fetoprotein ≤210.5 mcg/L, glutamic oxaloacetic transaminase ≤1.13 µkat/L, and total bilirubin ≤ 0.0283 mmol/L was shown to be a good predictor of survival >1 year, and the most effective treatments for such patients were radio-frequency ablation (RFA) and transarterial chemoembolization (TACE) with radiation therapy (RT). In patients without this combination, the best treatments were RFA, TACE with RT and targeted drug therapy, and TACE with targeted drug therapy and immunotherapy. The main limitation of this study was its small sample. With a small sample size, we may have developed a less reliable model system, failing to produce any clinically important results or outcomes. Conclusion: Data mining can produce models to help clinicians predict survival time at the time of initial HCC diagnosis and then choose the most suitable treatment.
Background and objective: Local advanced rectal cancer (LARC) poses significant treatment challenges due to its location and high recurrence rates. Accurate early detection is vital for treatment planning. With magnetic resonance imaging (MRI) being resource-intensive, this study explores using artificial intelligence (AI) to interpret computed tomography (CT) scans as an alternative, providing a quicker, more accessible diagnostic tool for LARC. Methods: In this retrospective study, CT images of 1070 T3–4 rectal cancer patients from 2010 to 2022 were analyzed. AI models, trained on 739 cases, were validated using two test sets of 134 and 197 cases. By utilizing techniques such as nonlocal mean filtering, dynamic histogram equalization, and the EfficientNetB0 algorithm, we identified images featuring characteristics of a positive circumferential resection margin (CRM) for the diagnosis of locally advanced rectal cancer (LARC). Importantly, this study employs an innovative approach by using both hard and soft voting systems in the second stage to ascertain the LARC status of cases, thus emphasizing the novelty of the soft voting system for improved case identification accuracy. The local recurrence rates and overall survival of the cases predicted by our model were assessed to underscore its clinical value. Results: The AI model exhibited high accuracy in identifying CRM-positive images, achieving an area under the curve (AUC) of 0.89 in the first test set and 0.86 in the second. In a patient-based analysis, the model reached AUCs of 0.84 and 0.79 using a hard voting system. Employing a soft voting system, the model attained AUCs of 0.93 and 0.88, respectively. Notably, AI-identified LARC cases exhibited a significantly higher five-year local recurrence rate and displayed a trend towards increased mortality across various thresholds. Furthermore, the model’s capability to predict adverse clinical outcomes was superior to those of traditional assessments. Conclusion: AI can precisely identify CRM-positive LARC cases from CT images, signaling an increased local recurrence and mortality rate. Our study presents a swifter and more reliable method for detecting LARC compared to traditional CT or MRI techniques.
Background: For hepatocellular carcinoma (“HCC”), the current standard of treatment is hepatic artery embolization, generally through trans-catheter arterial chemoembolization (“TACE”). There are two types: traditional (“conventional” or “cTACE”) and microsphere (“DC bead TACE”). Unfortunately, the literature comparing the relative effectiveness of cTACE versus DC bead TACE is inconclusive, partially due to the complexity of HCC and its response to treatment. Data mining is an excellent method to extract meaning from complex data sets. Purpose: Through the application of data mining techniques, to compare the relative effectiveness of cTACE and DC bead TACE using a large patient database and to use said comparison to establish usable guidelines for developing treatment plans for HCC patients. Materials and Methods: The data of 372 HCC patients who underwent TACE in Taichung Veterans General Hospital were analyzed. The chi-square test was used to compare the difference in the effectiveness of the two therapies was compared. Logistic regression was used to calculate the odds ratios. Furthermore, using the C4.5 decision tree, the two therapies were classified into applicable fields. Chi-square test, the t-test, and logistic regression were used to verify the classification results. Results: In Barcelona Clinic Stages A and B cancers, cTACE was found to be 22.7% more effective than DC bead TACE. By using the decision tree C4.5 as a classifier, the effectiveness of either treatment for small tumors was 8.475 times than that for large tumors. DC bead TACE was 3.39 times more successful in treating patients with a single tumor than with multiple tumors. For patients with a single tumor, the chi-square test showed that 100–300 μm microspheres were significantly more effective than 300–500 μm. While these findings provide a reference for the selection of an appropriate TACE approach, we noted that overall accuracy was somewhat low, possibly due to the limited population. Conclusions: We found that data mining could be applied to develop clear guidelines for physician and researcher use in the case of complex pathologies such as HCC. However, some of our results contradicted those elsewhere in the literature, possibly due to a relatively small sample size. Significantly larger data sets with appropriate levels of granularity could produce more accurate results.
Contrast-medium-associated kidney injury is caused by the infusion of contrast media. Small vessel disease is significantly associated with various diseases, including simultaneous conditions of the kidney and brain, which are highly vulnerable to similar vascular damage and microvascular pathologies. Data to investigate the adverse effect of contrast media on the brain remain extremely lacking. In this study, 11,332,616 NHI enrollees were selected and divided into two groups, exposed and not exposed to a contrast medium during the observation period, from which 1,461,684 pairs were selected for analyses through matching in terms of age, sex, comorbidities, and frequency of outpatient visits during the previous year. In total, 1,461,684 patients exposed to a contrast medium and 1,461,684 controls not exposed to one were enrolled. In multivariable Cox proportional hazard models, patients exposed to a contrast medium had an overall 2.09-fold higher risk of dementia. In multivariable-stratified analyses, the risk of Alzheimer’s disease was remarkably high in younger patients without any underlying comorbidity. This study is the first to discover that exposure to contrast media is significantly associated with the risk of dementia. A four-fold increased risk of vascular dementia was observed after exposure to a contrast medium. Further studies on the influence of exposure to contrast media on the brain are warranted.
14 May 2026 in Journal of Imaging Informatics in Medicine
Background: The complexity of systemic variables and comorbidities make it difficult to determine the best treatment for patients with hepatocellular carcinoma (HCC). It is impossible to perform a multidimensional evaluation of every patient, but guidelines based on analyses of said complexities would be the next best option. Traditional statistics are inadequate for developing predictive models with many variables; however, data mining is well-suited to the task. Patients and Methods and finding: The clinical profiles and data of a total of 537 patients diagnosed with Barcelona Clinic Liver Cancer stages B and C from 2009 to 2019 were retrospectively analyzed using 4 decision-tree algorithms. 19 treatments, 7 biomarkers, and 4 states of hepatitis were tested to see which combinations would result in survival times greater than a year. 2 of the algorithms produced complete models through single trees, which made only them suitable for clinical judgement. A combination of alpha fetoprotein ≤ 210.5 mcg/L, glutamic oxaloacetic transaminase ≤ 1.13 µkat/L, and total bilirubin ≤ 0.0283 mmol/L was shown to be a good predictor of survival > 1 year, and the most effective treatments for such patients were radio-frequency ablation (RFA) and transarterial chemoembolization (TACE) with radiation therapy (RT). In patients without this combination, the best treatments were RFA, TACE with RT and targeted drug therapy, and TACE with targeted drug therapy and immunotherapy. The main limitation of this study was small sample. With small sample size, we may developed a less reliable model system, failing to produce any clinically important results or outcomes Conclusion: Data mining can produce models to help clinicians predict survival time at the time of initial HCC diagnosis and then choose the most suitable treatment.