Clinical analysis and artificial intelligence survival prediction of serous ovarian cancer based on preoperative circulating leukocytes

Low Back Pain Among Health Sciences Undergraduates: Results Obtained from a Machine-Learning Analysis

Background and objective. Low back pain (LBP) is considered the most common and challenging disorder in health care. Although its incidence increases with age, a student's sedentary behavior could contribute to this risk. Through machine learning (ML), advanced algorithms can analyze complex patterns in health data, enabling accurate prediction and targeted prevention of medical conditions such as LBP. This study aims to detect the factors associated with LBP among health sciences students. Methods. A self-administered modified version of the Standardized Nordic Questionnaire was completed by 222 freshman health sciences students from May to June 2022. A supervised random forest algorithm was utilized to analyze data and prioritize the importance of variables related to LBP. The model's predictive capability was further visualized using a decision tree to identify high-risk patterns and associations. Results. A total of 197/222 (88.7%) students participated in this study, most of whom (75%) were female. Their mean age and body mass index were 23 ± 3.8 and 23 ± 3.5, respectively. In this group, 46% (n = 90) of the students reported having experienced LBP in the last month, 15% (n = 30) were smokers, and 60% (n = 119) were involved in prolonged sitting (more than 3 h per day). The decision tree of ML revealed that a history of pain (score = 1), as well as disability (score= 0.34) and physical activity (score = 0.21), were significantly associated with LBP. Conclusions. Approximately 46% of the health science students reported LBP in the last month, and a machine-learning approach highlighted a history of pain as the most significant factor related to LBP.

Comparing the Effectiveness of Artificial Intelligence Models in Predicting Ovarian Cancer Survival: A Systematic Review

BACKGROUND

This systematic review investigates the use of machine learning (ML) algorithms in predicting survival outcomes for ovarian cancer (OC) patients. Key prognostic endpoints, including overall survival (OS), recurrence-free survival (RFS), progression-free survival (PFS), and treatment response prediction (TRP), are examined to evaluate the effectiveness of these algorithms and identify significant features that influence predictive accuracy.

RECENT FINDINGS

A thorough search of four major databases-PubMed, Scopus, Web of Science, and Cochrane-resulted in 2400 articles published within the last decade, with 32 studies meeting the inclusion criteria. Notably, most publications emerged after 2021. Commonly used algorithms for survival prediction included random forest, support vector machines, logistic regression, XGBoost, and various deep learning models. Evaluation metrics such as area under the curve (AUC) (18 studies), concordance index (C-index) (11 studies), and accuracy (11 studies) were frequently employed. Age at diagnosis, tumor stage, CA-125 levels, and treatment-related factors were consistently highlighted as significant predictors, emphasizing their relevance in OC prognosis.

CONCLUSION

ML models demonstrate considerable potential for predicting OC survival outcomes; however, challenges persist regarding model accuracy and interpretability. Incorporating diverse data types-such as clinical, imaging, and molecular datasets-holds promise for enhancing predictive capabilities. Future advancements will depend on integrating heterogeneous data sources with multimodal ML approaches, which are crucial for improving prognostic precision in OC.

Diagnostic accuracy of artificial intelligence algorithms to predict remove all macroscopic disease and survival rate after complete surgical cytoreduction in patients with ovarian cancer: a systematic review and meta-analysis

BACKGROUND

Complete Cytoreduction (CC) in ovarian cancer (OC) has been associated with better outcomes. Outcomes after CC have a multifactorial and interrelated cause that may not be predictable by conventional statistical methods. Artificial intelligence (AI) may be more accurate in predicting outcomes. This systematic review aimed to determine the accuracy of AI compared to traditional statistics in predicting outcomes after CC in OC.

METHODS

PubMed, Scopus, Google Scholar, Embase, and Web of Science databases were searched with Mesh terms to find studies that investigated the role of AI in predicting outcomes after CC in EOC from the beginning of 2015 to February 2024. The outcomes included overall survival (OS), removal of all macroscopic disease (R0), length of hospital stay (LOS), and intensive care unit (ICU) admission. This systematic review was conducted based on the PRISMA guidelines. Heterogeneity between studies was evaluated using the I2 test. Egger's test was used to check publication bias.

RESULTS

Ten studies (3460 participants) were included. The pooled estimate of 3 studies showed that the accuracy of AI for predicting OS was (Mean: 69.64%, CI 95%:66.50, 72.78%, I2:0%). The pooled estimate of 4 studies showed that the accuracy of AI for predicting R0 was (Mean: 80.5%, CI 95%:71.46, 89.6%, I2:47.9%). The use of AI in predicting outcomes, including ICU admission, urinary tract infection (UTI), and LOS was investigated in one study, and the AUC of AI for predicting all three outcomes was approximately 90%.

CONCLUSION

AI may accurately predict the outcomes after CC in OC patients. Most studies agree that Artificial Neural Networks (ANN) and Machine Learning (ML) models outperform conventional statistics in predicting postoperative outcomes.

Predicting survival in patients with SARS-CoV-2 based on cytokines and soluble immune checkpoint regulators

Background

Coronavirus disease 2019 (COVID-19) has been widespread for over four years and has progressed to an endemic stage. Accordingly, the evaluation of host immunity in infected patients and the development of markers for prognostic prediction in the early stages have been emphasized. Soluble immune checkpoints (sICs), which regulate T cell activity, have been reported as promising biomarkers of viral infections.

Methods

In this study, quantitative values of 17 sICs and 16 cytokines (CKs) were measured using the Luminex multiplex assay. A total of 148 serum samples from 100 patients with COVID-19 were collected and the levels were compared between survivors vs. non-survivors and pneumonic vs. non-pneumonic conditions groups. The impact of these markers on overall survival were analyzed using a machine learning algorithm.

Results

sICs, including sCD27, sCD40, herpes virus entry mediator (sHVEM), T-cell immunoglobulin and mucin-domain containing-3 (sTIM-3), and Toll-like receptor 2 (sTLR-2) and CKs, including chemokine CC motif ligand 2 (CCL2), interleukin-6 (IL-6), IL-8, IL-10, IL-13, granulocyte-macrophage colony-stimulating factor (GM-CSF), and tumor necrosis factor-α (TNF- α), were statistically significantly increased in the non-survivors compared to those of in the survivors. IL-6 showed the highest area under the receiver-operating curve (0.844, 95% CI = 0.751-0.913) to discriminate non-survival, with a sensitivity of 78.9% and specificity of 82.4%. In Kaplan-Meier analysis, patients with procalcitonin over 0.25 ng/mL, C-reactive protein (CRP) over 41.0 mg/dL, neutrophil-to-lymphocyte ratio over 18.97, sCD27 over 3828.8 pg/mL, sCD40 over 1283.6 pg/mL, and IL-6 over 21.6 pg/mL showed poor survival (log-rank test). In the decision tree analysis, IL-6, sTIM-3, and sCD40 levels had a strong impact on survival. Moreover, IL-6, CD40, and CRP levels were important to predict the probability of 90-d mortality using the SHapley Additive exPlanations method.

Conclusion

sICs and CKs, especially IL-6, sCD27, sCD40, and sTIM-3 are expected to be useful in predicting patient outcomes when used in combination with existing markers.

Comprehensive machine learning-based preoperative blood features predict the prognosis for ovarian cancer

PURPOSE

Significant advancements in improving ovarian cancer (OC) outcomes have been limited over the past decade. To predict prognosis and improve outcomes of OC, we plan to develop and validate a robust prognosis signature based on blood features.

METHODS

We screened age and 33 blood features from 331 OC patients. Using ten machine learning algorithms, 88 combinations were generated, from which one was selected to construct a blood risk score (BRS) according to the highest C-index in the test dataset.

RESULTS

Stepcox (both) and Enet (alpha = 0.7) performed the best in the test dataset with a C-index of 0.711. Meanwhile, the low RBS group possessed observably prolonged survival in this model. Compared to traditional prognostic-related features such as age, stage, grade, and CA125, our combined model had the highest AUC values at 3, 5, and 7 years. According to the results of the model, BRS can provide accurate predictions of OC prognosis. BRS was also capable of identifying various prognostic stratifications in different stages and grades. Importantly, developing the nomogram may improve performance by combining BRS and stage.

CONCLUSION

This study provides a valuable combined machine-learning model that can be used for predicting the individualized prognosis of OC patients.

Deep learning diagnostic performance and visual insights in differentiating benign and malignant thyroid nodules on ultrasound images

This study aims to construct and evaluate a deep learning model, utilizing ultrasound images, to accurately differentiate benign and malignant thyroid nodules. The objective includes visualizing the model's process for interpretability and comparing its diagnostic precision with a cohort of 80 radiologists. We employed ResNet as the classification backbone for thyroid nodule prediction. The model was trained using 2096 ultrasound images of 655 distinct thyroid nodules. For performance evaluation, an independent test set comprising 100 cases of thyroid nodules was curated. In addition, to demonstrate the superiority of the artificial intelligence (AI) model over radiologists, a Turing test was conducted with 80 radiologists of varying clinical experience. This was meant to assess which group of radiologists' conclusions were in closer alignment with AI predictions. Furthermore, to highlight the interpretability of the AI model, gradient-weighted class activation mapping (Grad-CAM) was employed to visualize the model's areas of focus during its prediction process. In this cohort, AI diagnostics demonstrated a sensitivity of 81.67%, a specificity of 60%, and an overall diagnostic accuracy of 73%. In comparison, the panel of radiologists on average exhibited a diagnostic accuracy of 62.9%. The AI's diagnostic process was significantly faster than that of the radiologists. The generated heat-maps highlighted the model's focus on areas characterized by calcification, solid echo and higher echo intensity, suggesting these areas might be indicative of malignant thyroid nodules. Our study supports the notion that deep learning can be a valuable diagnostic tool with comparable accuracy to experienced senior radiologists in the diagnosis of malignant thyroid nodules. The interpretability of the AI model's process suggests that it could be clinically meaningful. Further studies are necessary to improve diagnostic accuracy and support auxiliary diagnoses in primary care settings.

Exploring the efficacy of artificial neural networks in predicting lung cancer recurrence: a retrospective study based on patient records

Background

Lung cancer remains a significant public health concern, accounting for a considerable number of cancer-related deaths worldwide. Neural networks have emerged as a promising tool that can aid in the diagnosis and treatment of various cancers. Consequently, there has been a growing interest in exploring the potential of artificial intelligence (AI) methods in medicine. The present study aimed to evaluate the effectiveness of a neural network in predicting lung cancer recurrence.

Methods

The study employed retrospective data from 2,296 medical records of patients diagnosed with lung cancer and admitted to the Warmińsko-Mazurskie Center for Lung Diseases in Olsztyn, Poland. The statistical software STATISTICA 7.1, equipped with the Neural Networks module (StatSoft Inc., Tulsa, USA), was utilized to analyze the data. The neural network model was trained using patient information regarding gender, treatment, smoking status, family history, and symptoms of cancer.

Results

The study employed a multilayer perceptron neural network with a two-phase learning process. The network demonstrated high predictive ability, as indicated by the percentage of correct classifications, which amounted to 87.5%, 89.1%, and 89.9% for the training, validation, and test sets, respectively.

Conclusions

The findings of this study support the potential usefulness of a neural network-based predictive model in assessing the risk of lung cancer recurrence. Further research is warranted to validate these findings and to explore AI's broader implications in cancer diagnosis and treatment.

Prognostic Role of Neutrophil, Monocyte and Platelet to Lymphocyte Ratios in Advanced Ovarian Cancer According to the Time of Debulking Surgery

Despite a multimodal radical treatment, mortality of advanced epithelial ovarian cancer (AEOC) remains high. Host-related factors, such as systemic inflammatory response and its interplay with the immune system, remain underexplored. We hypothesized that the prognostic impact of this response could vary between patients undergoing primary debulking surgery (PDS) and those undergoing interval debulking surgery (IDS). Therefore, we evaluated the outcomes of two surgical groups of newly diagnosed AEOC patients according to the neutrophil, monocyte and platelet to lymphocyte ratios (NLR, MLR, PLR), taking median ratio values as cutoffs. In the PDS group (n = 61), low NLR and PLR subgroups showed significantly better overall survival (not reached (NR) vs. 72.7 months, 95% confidence interval [CI]: 40.9-95.2, p = 0.019; and NR vs. 56.1 months, 95% CI: 40.9-95.2, p = 0.004, respectively) than those with high values. Similar results were observed in progression free survival. NLR and PLR-high values resulted in negative prognostic factors, adjusting for residual disease, BRCA1/2 status and stage (HR 2.48, 95% CI: 1.03-5.99, p = 0.043, and HR 2.91, 95% CI: 1.11-7.64, p = 0.03, respectively). In the IDS group (n = 85), ratios were not significant prognostic factors. We conclude that NLR and PLR may have prognostic value in the PDS setting, but none in IDS, suggesting that time of surgery can modulate the prognostic impact of baseline complete blood count (CBC).

The potential of high-order features of routine blood test in predicting the prognosis of non-small cell lung cancer

BACKGROUND

Numerous studies have demonstrated that the high-order features (HOFs) of blood test data can be used to predict the prognosis of patients with different types of cancer. Although the majority of blood HOFs can be divided into inflammatory or nutritional markers, there are still numerous that have not been classified correctly, with the same feature being named differently. It is an urgent need to reclassify the blood HOFs and comprehensively assess their potential for cancer prognosis.

METHODS

Initially, a review of existing literature was conducted to identify the high-order features (HOFs) and classify them based on their calculation method. Subsequently, a cohort of patients diagnosed with non-small cell lung cancer (NSCLC) was established, and their clinical information prior to treatment was collected, including low-order features (LOFs) obtained from routine blood tests. The HOFs were then computed and their associations with clinical features were examined. Using the LOF and HOF data sets, a deep learning algorithm called DeepSurv was utilized to predict the prognostic risk values. The effectiveness of each data set's prediction was evaluated using the decision curve analysis (DCA). Finally, a prognostic model in the form of a nomogram was developed, and its accuracy was assessed using the calibration curve.

RESULTS

From 1210 documents, over 160 blood HOFs were obtained, arranged into 110, and divided into three distinct categories: 76 proportional features, 6 composition features, and 28 scoring features. Correlation analysis did not reveal a strong association between blood features and clinical features; however, the risk value predicted by the DeepSurv LOF- and HOF-models is significantly linked to the stage. Results from DCA showed that the HOF model was superior to the LOF model in terms of prediction, and that the risk value predicted by the blood data model could be employed as a complementary factor to enhance the prognosis of patients. A nomograph was created with a C-index value of 0.74, which is capable of providing a reasonably accurate prediction of 1-year and 3-year overall survival for patients.

CONCLUSIONS

This research initially explored the categorization and nomenclature of blood HOF, and proved its potential in lung cancer prognosis.

Gynecological cancer prognosis using machine learning techniques: A systematic review of last three decades (1990–2022)

OBJECTIVE

Many Computer Aided Prognostic (CAP) systems based on machine learning techniques have been proposed in the field of oncology. The objective of this systematic review was to assess and critically appraise the methodologies and approaches used in predicting the prognosis of gynecological cancers using CAPs.

METHODS

Electronic databases were used to systematically search for studies utilizing machine learning methods in gynecological cancers. Study risk of bias (ROB) and applicability were assessed using the PROBAST tool. 139 studies met the inclusion criteria, of which 71 predicted outcomes for ovarian cancer patients, 41 predicted outcomes for cervical cancer patients, 28 predicted outcomes for uterine cancer patients, and 2 predicted outcomes for gynecological malignancies broadly.

RESULTS

Random forest (22.30 %) and support vector machine (21.58 %) classifiers were used most commonly. Use of clinicopathological, genomic and radiomic data as predictors was observed in 48.20 %, 51.08 % and 17.27 % of studies, respectively, with some studies using multiple modalities. 21.58 % of studies were externally validated. Twenty-three individual studies compared ML and non-ML methods. Study quality was highly variable and methodologies, statistical reporting and outcome measures were inconsistent, preventing generalized commentary or meta-analysis of performance outcomes.

CONCLUSION

There is significant variability in model development when prognosticating gynecological malignancies with respect to variable selection, machine learning (ML) methods and endpoint selection. This heterogeneity prevents meta-analysis and conclusions regarding the superiority of ML methods. Furthermore, PROBAST-mediated ROB and applicability analysis demonstrates concern for the translatability of existing models. This review identifies ways that this can be improved upon in future works to develop robust, clinically translatable models within this promising field.

The Use of Artificial Intelligence for Complete Cytoreduction Prediction in Epithelial Ovarian Cancer: A Narrative Review

INTRODUCTION

In patients affected by epithelial ovarian cancer (EOC) complete cytoreduction (CC) has been associated with higher survival outcomes. Artificial intelligence (AI) systems have proved clinical benefice in different areas of healthcare.

OBJECTIVE

To systematically assemble and analyze the available literature on the use of AI in patients affected by EOC to evaluate its applicability to predict CC compared to traditional statistics.

MATERIAL AND METHODS

Data search was carried out through PubMed, Scopus, Ovid MEDLINE, Cochrane Library, EMBASE, international congresses and clinical trials. The main search terms were: Artificial Intelligence AND surgery/cytoreduction AND ovarian cancer. Two authors independently performed the search by October 2022 and evaluated the eligibility criteria. Studies were included when data about Artificial Intelligence and methodological data were detailed.

RESULTS

A total of 1899 cases were analyzed. Survival data were reported in 2 articles: 92% of 5-years overall survival (OS) and 73% of 2-years OS. The median area under the curve (AUC) resulted 0,62. The model accuracy for surgical resection reported in two articles reported was 77,7% and 65,8% respectively while the median AUC was 0,81. On average 8 variables were inserted in the algorithms. The most used parameters were age and Ca125.

DISCUSSION

AI revealed greater accuracy compared against the logistic regression models data. Survival predictive accuracy and AUC were lower for advanced ovarian cancers. One study analyzed the importance of factors predicting CC in recurrent epithelial ovarian cancer and disease free interval, retroperitoneal recurrence, residual disease at primary surgery and stage represented the main influencing factors. Surgical Complexity Scores resulted to be more useful in the algorithms than pre-operating imaging.

CONCLUSION

AI showed better prognostic accuracy if compared to conventional algorithms. However further studies are needed to compare the impact of different AI methods and variables and to provide survival informations.

Artificial Intelligence in Surgical Learning

(1) Background: Artificial Intelligence (AI) is transforming healthcare on all levels. While AI shows immense potential, the clinical implementation is lagging. We present a concise review of AI in surgical learning; (2) Methods: A non-systematic review of AI in surgical learning of the literature in English is provided; (3) Results: AI shows utility for all components of surgical competence within surgical learning. AI presents with great potential within robotic surgery specifically (4) Conclusions: Technology will evolve in ways currently unimaginable, presenting us with novel applications of AI and derivatives thereof. Surgeons must be open to new modes of learning to be able to implement all evidence-based applications of AI in the future. Systematic analyses of AI in surgical learning are needed.

Lymphocyte-to-monocyte ratio after primary surgery is an independent prognostic factor for patients with epithelial ovarian cancer: A propensity score matching analysis

Background

The aim of this study was to elucidate the prognostic value of preoperative lymphocyte-to-monocyte ratio (LMR) after primary surgery in epithelial ovarian cancer (EOC) patients using a propensity score matching (PSM) analysis.

Methods

We retrospectively reviewed consecutive EOC patients who underwent primary surgery between January 2008 and December 2019. Patients were divided into two groups according to the optimal cutoff value of preoperative LMR. PSM (1:1) was conducted to eliminate confounding factors. A Cox proportional hazards model and the Kaplan-Meier estimator were employed to investigate the potential prognostic factors.

Results

A total of 368 EOC patients were included in this study. The optimal cutoff value of LMR was identified as 4.65. Low preoperative LMR was significantly correlated with low albumin, high CA125 level, more blood loss, a high likelihood of ascites, advanced FIGO stage, and poor differentiation (all p < 0.05). After matching, Kaplan-Meier curves showed that the group with LMR < 4.65 experienced significantly shorter OS (p = 0.015). Multivariate Cox analysis revealed that low LMR (HR = 1.49, p = 0.041), advanced FIGO stage (HR = 5.25, p < 0.001), and undefined residual disease (HR = 3.77, p = 0.002) were independent factors in predicting poor OS. A forest plot revealed that LMR had better prognostic value in younger EOC patients, patients with BMI ≥ 25 kg/m² and albumin ≥ 35 g/L, CA125 ≥ 35 U/L, patients who had undergone optimal surgery, and those who had completed chemotherapy. Additionally, low-LMR patients who had undergone incomplete chemotherapy had a shorter median OS compared with those who completed chemotherapy treatment (48.5 vs. 105.9 months, p = 0.026).

Conclusions

LMR could be used as an independent prognostic factor for EOC patients after primary surgery; a noticeable negative effect of LMR was observed among EOC patients with age < 65, good preoperative nutritional status, and more aggressive tumor biology, and among those who underwent optimal surgery. Completing adjuvant chemotherapy is essential to improve survival outcomes among EOC patients with LMR < 4.65 after surgery.