• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.61-68
• /
• 2024

In the quest for advancing diabetes diagnosis, this study introduces a novel two-step machine learning approach that synergizes the probabilistic predictions of Logistic Regression with the classification prowess of Random Forest. Diabetes, a pervasive chronic disease impacting millions globally, necessitates precise and early detection to mitigate long-term complications. Traditional diagnostic methods, while effective, often entail invasive testing and may not fully leverage the patterns hidden in patient data. Addressing this gap, our research harnesses the predictive capability of Logistic Regression to estimate the likelihood of diabetes presence, followed by employing Random Forest to classify individuals into diabetic, pre-diabetic or nondiabetic categories based on the computed probabilities. This methodology not only capitalizes on the strengths of both algorithms-Logistic Regression's proficiency in estimating nuanced probabilities and Random Forest's robustness in classification-but also introduces a refined mechanism to enhance diagnostic accuracy. Through the application of this model to a comprehensive diabetes dataset, we demonstrate a marked improvement in diagnostic precision, as evidenced by superior performance metrics when compared to other machine learning approaches. Our findings underscore the potential of integrating diverse machine learning models to improve clinical decision-making processes, offering a promising avenue for the early and accurate diagnosis of diabetes and potentially other complex diseases.

• Korean Journal of Radiology
• /
• v.25 no.1
• /
• pp.86-102
• /
• 2024

Early diagnosis, accurate assessment, and localization of peritoneal metastasis (PM) are essential for the selection of appropriate treatments and surgical guidance. However, available imaging modalities (computed tomography [CT], conventional magnetic resonance imaging [MRI], and 18fluorodeoxyglucose positron emission tomography [PET]/CT) have limitations. The advent of new imaging techniques and novel molecular imaging agents have revealed molecular processes in the tumor microenvironment as an application for the early diagnosis and assessment of PM as well as real-time guided surgical resection, which has changed clinical management. In contrast to clinical imaging, which is purely qualitative and subjective for interpreting macroscopic structures, radiomics and artificial intelligence (AI) capitalize on high-dimensional numerical data from images that may reflect tumor pathophysiology. A predictive model can be used to predict the occurrence, recurrence, and prognosis of PM, thereby avoiding unnecessary exploratory surgeries. This review summarizes the role and status of different imaging techniques, especially new imaging strategies such as spectral photon-counting CT, fibroblast activation protein inhibitor (FAPI) PET/CT, near-infrared fluorescence imaging, and PET/MRI, for early diagnosis, assessment of surgical indications, and recurrence monitoring in patients with PM. The clinical applications, limitations, and solutions for fluorescence imaging, radiomics, and AI are also discussed.

• Journal of Gastric Cancer
• /
• v.9 no.3
• /
• pp.104-109
• /
• 2009

Purpose: The aim of this study is to evaluate the accuracy of surgically diagnosing early gastric cancer (EGC) and lymph node metastasis, and to determine its role for performing limited surgery for EGC. Materials and Methods: We reviewed 369 patients who underwent gastrectomy for primary gastric carcinoma. The surgical diagnosis was evaluated by determining its sensitivity, specificity and accuracy, and this was compared with the preoperative examinations. Results: The sensitivity, specificity, and accuracy of the intraoperative diagnosis for EGC were 74.5%, 95.7% and 83.7%, respectively. The predictive value for EGC according to the intraoperative diagnosis was 95.7%. The surgical diagnosis of EGC showed higher specificity and a higher predictive value than preoperative examinations, which significantly reduced the risk of underestimating advanced gastric cancer (AGC) to EGC. The sensitivity, specificity, and accuracy for lymph node metastasis according to the surgical diagnosis were 73.2%, 78.1% and 76.4%, respectively. For 70 patients with a discrepancy in the diagnosis of EGC between the pre- and intra-operative diagnosis, the surgical diagnosis was correct in 63 (90%) patients, but the preoperative examinations were correct in only 7 (10%) patients. Conclusion: The surgical diagnosis showed better accuracy than the preoperative examinations for detecting EGC and lymph node metastasis. Our results suggest that the decision for conducting limited surgery based on the surgical diagnosis might reduce the risk of under-treatment of AGC to EGC better than the preoperative examinations.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.9
• /
• pp.4567-4570
• /
• 2012

Objectives: The purposes of this study were to determine the prevalence and predictive value to detect significant neoplasia and invasive lesions, and to evaluate the correlation between clinical and histopathology of women with squamous cell carcinoma (SCCA) on Siriraj liquid-based cervical cytology (Siriraj-LBC). Methods: The computerized database of women who underwent Siriraj-LBC at Siriraj Hospital, Mahidol University from January 2007 to December 2010 were retrieved. The hospital records of women with SCCA cytology were reviewed. Results: The prevalence of SCCA cytology was 0.07%. A total of 86 women, mean age was 58.1 years. Sixty-one women (70.9%) were post-menopausal. Overall significant pathology and invasive gynecologic cancer were detected in 84 women (97.7%) and 71 women (82.5%), respectively. The positive predictive values for detection of significant neoplasia and invasive lesion were 97.7% and 82.6%, respectively. The cervical cancer was diagnosed in 69 women and among these 58 women were SCCA. Thirteen women (15.1%) had cervical intraepithelial neoplasia (CIN) 3 and two women (2.3%) had cervicitis. The sensitivity and specificity of colposcopy for cervical cancer detection in SCCA cytology were 83.3% and 75%, respectively. Median follow up period was 17.6 months and 64 patients were alive without cytologic abnormality. Conclusions: The final histopathology of SCCA cytology in our populations demonstrated a wide variety, from cervicitis to invasive cancer and the most common diagnosis was invasive cervical cancer. Colposcopy with biopsy and/or endocervical curettage and loop electrosurgical excision procedure should be undertaken to achieve histologic diagnosis.

• Journal of The Korean Dental Society of Anesthesiology
• /
• v.12 no.1
• /
• pp.17-23
• /
• 2012

Background: This study evaluated pulp vitality of anterior permanent teeth using pulse oximetry (PO), which is already used for monitoring of patient's $SpO_2$ and pulse rates (PR). Also we compared with ice tests and electric pulp test (EPT). Methods: 9 teeth, endodontic treated, were selected as non-vital teeth group. 17 vital teeth were selected as control group. Our aim is to compare sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of ice test, electric pulp test and pulse oximetry, respectively. Pulse oximetry has two test results, $SpO_2$ and pulse rates. Also we calculated correlation and statistical significances by Pearson's test between EPT and pulse oximetry. Results: Sensitivity, specificity, PPV, NPV were calculated on each tests. Ice test has results of 1.00, 0.89, 0.94 and 1.00, respectively. EPT has results of 0.94, 0.78, 0.89 and 0.88 respectively. $SpO_2$ has results of 0.94, 1.00, 1.00 and 0.90, respectively. PR has results of all 1.00. Conclusions: PO showed relatively accurate, stable and objective results on both $SpO_2$ and PR. Percentage of ability of accurate diagnosis for vital teeth is 94% for ice test, 89% for EPT, 100% for $SpO_2$ and PR. Percentage of ability of accurate diagnosis for non-vital teeth is 100% for ice test, 88% for EPT, 90% for $SpO_2$ and 100% for PR. In additions, PR could be more accurate and significant tests than $SpO_2$.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.15
• /
• pp.6407-6412
• /
• 2015

Purpose: To predict prostatic carcinoma using a logistic regression model on prebiopsy peripheral blood samples. Materials and Methods: Data of a total of 873 patients who consulted Urology Outpatient Clinics of Fatih Sultan Mehmet Training and Research Hospital between February 2008 and April 2014 scheduled for prostate biopsy were screened retrospectively. PSA levels, prostate volumes, prebiopsy whole blood cell counts, neutrophil and platelet counts, neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), biopsy results and Gleason scores in patients who had established diagnosis of prostate cancer (PCa) were evaluated. Results: This study was performed on a total of 873 cases, with an age range 48-76 years, divided into three groups as for biopsy results. with diagnoses of benign prostatic hyperplasia (BPH) (n=304, 34.8 %), PCa (n=265, 30.4 %) and histological prostatitis (n=304; 34.8 %). Intra- and intergroup comparative evaluations were performed. White blood cell and neutrophil counts in the histological prostatitis group were significantly higher than those of the BPH and PCa groups (p=0.001; p=0.004; p<0.01). A statistically significant intergroup difference was found for PLR (p=0.041; p<0.05) but not lymphocyte count (p>0.05). According to pairwise comparisons, PLR were significantly higher in the PCa group relative to BPH group (p=0.018, p<0.05, respectively). Though not statistically significant, higher PLR in cases with PCa in comparison with the prostatitis group was remarkable (p=0.067, and p>0.05, respectively). Conclusions: Meta-analyses showed that in patients with PSA levels over 4 ng/ml, positive predictive value of PSA is only 25 percent. Therefore, novel markers which can both detect clinically significant prostate cancer, and also prevent unnecessary biopsies are needed. Relevant to this issue in addition to PSA density, velocity, and PCA3, various markers have been analyzed. In the present study, PLR were found to be the additional predictor of prostatic carcinoma.

• The Korean Journal of Cytopathology
• /
• v.10 no.1
• /
• pp.13-19
• /
• 1999

The authors analysed 2,653 cases of transthoracic fine needle aspiration cytology of the lung to evaluate the diagnostic accuracy and its limitation. A comparison was made between the original cytologic and the final histologic diagnoses on 1,149 cases from 1,074 patients. A diagnosis of malignancy was established in 38.3% benign in 48.1%, atypical lesion in 2.3%, and inadequate one in 11.9% of the cases. Statistical data on cytologic diagnoses were as follows; specificity 98.9%: sensitivity of procedure, 76.8%: sensitivity of diagnosis, 95.5%: false positive 5 cases: false negative 18 cases: predictive value for malignancy, 98.8%: predictive value for benign lesion, 79.5%: overall diagnostic efficiency, 87.5%: typing accuracy in malignant tumor, 80%.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.15
• /
• pp.6053-6057
• /
• 2014

Aim: To determine utility of the frozen section (FS) in the operative management of endometrial pre-malignant lesions. Materials and Methods: We retrospectively analyzed patients who underwent abdominal hysterectomy with preoperative diagnosis of complex atypical endometrial hyperplasia (CAEH) and simple endometrial hyperplasia (SEH) between May 2007 and December 2013. Frozen and paraffin section (PS) results were compared. Sensitivity, specificity, the positive predictive value (PPV), the negative predictive value (NPV) and the accuracy in predicting EC on FS were evaluated with 95% confidence intervals (CIs) for each parameter. The correlation between FS and PS was calculated as an ${\kappa}$ coefficient. Results: Among 143 preoperatively diagnosed CAEH cases, 60 (42%) were malignant and 83 (58%) were benign in PS; and among 60 malignant cases diagnosed in PS, 43 (71%) were "malignant" in FS. Sensitivity, specificity, PPV and NPV for FS were 76%, 100%, 100% and 87.5%, respectively. Conclusions: We found that FS is reliable and applicable in the management of endometrial hyperplasias. It is important that the pathologist should be experienced because FS for endometrial pre-malignant lesions has significant inter-observer variability. The other conclusion is that patients with the diagnosis of EH, especially those who are postmenopausal, should undergo surgery where FS investigation is available.

• Journal of Yeungnam Medical Science
• /
• v.24 no.2
• /
• pp.179-185
• /
• 2007

Backgroud : Urinary tract infection (UTI) is common in children. The available gold standard methods for diagnosis, Tc-99m dimercaptosuccinic acid (DMSA) scan and computed tomography (CT) are invasive and expensive. This study was performed to assess the role of power Doppler ultrasound (PDU) for diagnosis of acute pyelonephritis (APN). Materials and Methods : A prospective study was conducted in 25 children with aged 2 weeks to 5 years who were hospitalized with the first episode of febrile UTI suggesting acute pyelonephritis. All children were examined in the first 3-5 days of admission by PDU and Tc-99m DMSA scan. The comparison between PDU and DMSA scan was performed on the basis of patients. Results : The sensitivity and specificity of PDU for the detection of affected kidneys were 38.1% and 50.0%, and the positive predictive value and negative predictive value were 61.9% and 50.0%, respectively. Vesicoureteral refluxes (VUR) were identified in 11 patients (44.4%) and 18 kidneys (36%). The PDU and DMSA scan showed a matching perfusion defect in 23.8% and 50.0% respectively. Conclusion : These data indicate the PDU has a relatively low sensitivity and specificity for differentiating APN from lower UTI but may be a complement tool to DMSA scan for the prediction of VUR in infants and children.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.5
• /
• pp.3289-3292
• /
• 2013

Introduction: The purpose of this study was to identify clinical profiles of patients with low risk of having bone metastases, for which bone scanning could be safely eliminated. Materials and Methods: This retrospective cross sectional study looked at prostate cancer patients seen in the Urology Departments in 2 tertiary centres over the 11 year period starting from January 2000 to May 2011. Patient demographic data, levels of PSA at diagnosis, Gleason score for the biopsy core, T-staging as well as the lymph node status were recorded and analysed. Results: 258 men were included. The mean age of those 90 men (34.9%) with bone metastasis was $69.2{\pm}7.3$ years. Logistic regression found that PSA level (P=0.000) at diagnosis and patient's nodal-stage (P=0.02) were the only two independent variables able to predict the probability of bone metastasis among the newly diagnosed prostate cancer patients. Among thowse with a low PSA level less than 20ng/ml, and less than 10ng/ml, bone metastasis were detected in 10.3% (12 out of 117) and 9.7% (7 out of 72), respectively. However, by combining PSA level of 10ng/ml or lower, and nodal negative as the two criteria to predict negative bone scan, a relatively high negative predictive value of 93.8% was obtained. The probability of bone metastasis in prostate cancer can be calculated with this formula: -1.069+0.007(PSA value, ng/ml)+1.021(Nodal status, 0 or 1)=x Probability of bone metastasis=$2.718^x/1+2.718^x$. Conclusion: Newly diagnosed prostate cancer patients with a PSA level of 10ng/ml or lower and negative nodes have a very low risk of bone metastasis (negative predictive value 93.8%) and therefore bone scans may not be necessary.