Immune checkpoint status and oncogenic mutation profiling of rectal cancer after neoadjuvant chemotherapy (KSCC1301-A2).

Aim: Immune checkpoint inhibitors (ICIs) are less effective in mismatch repair (MMR)-proficient (pMMR) colorectal cancers (CRCs) than in MMR-deficient CRCs. Here, we investigated changes in the tumor microenvironment after neoadjuvant chemotherapy (NAC) without radiotherapy in locally advanced rectal cancer (LARC) and the potential of ICIs as therapeutic agents for pMMR CRCs. Methods: This was an ad hoc analysis of a KSCC1301 randomized phase II trial in which patients with untreated resectable LARC were randomly assigned to receive S-1 and oxaliplatin or folinic acid, 5-fluorouracil, and oxaliplatin as NAC. Forty-nine patients were studied in this ad hoc analysis. As a reference cohort, we assessed 25 rectal cancer patients who underwent surgery without NAC outside the randomized trial. Immune checkpoint molecules (ICMs; PD-1, PD-L1, CTLA-4, LAG3), tumor-infiltrating lymphocytes (TILs; CD8, FOXP3), and other related proteins were evaluated by immunohistochemistry. Next-generation sequencing (NGS) using Oncomine™ Comprehensive Assay version 3 was conducted in 23 patients. Results: The expression levels of PD-1, CTLA-4, and LAG3 in the NAC group were significantly higher than in reference patients (p < 0.001). Additionally, the infiltration of CD8+ and FOXP3+ T cells, and the CD8/FOXP3 ratio were significantly higher in the NAC group than in reference patients (p < 0.0001). NGS analysis revealed no specific gene alteration related to TILs or ICMs. Conclusion: We demonstrated changes in the tumor immune microenvironment after NAC in pMMR rectal cancer. NAC was associated with increased expression of ICMs and TILs. Rectal cancer could be susceptible to combined immunotherapy with chemotherapy.

Advances in cancer DNA methylation analysis with methPLIER: use of non-negative matrix factorization and knowledge-based constraints to enhance biological interpretability.

DNA methylation is an epigenetic modification that results in dynamic changes during ontogenesis and cell differentiation. DNA methylation patterns regulate gene expression and have been widely researched. While tools for DNA methylation analysis have been developed, most of them have focused on intergroup comparative analysis within a dataset; therefore, it is difficult to conduct cross-dataset studies, such as rare disease studies or cross-institutional studies. This study describes a novel method for DNA methylation analysis, namely, methPLIER, which enables interdataset comparative analyses. methPLIER combines Pathway Level Information Extractor (PLIER), which is a non-negative matrix factorization (NMF) method, with regularization by a knowledge matrix and transfer learning. methPLIER can be used to perform intersample and interdataset comparative analysis based on latent feature matrices, which are obtained via matrix factorization of large-scale data, and factor-loading matrices, which are obtained through matrix factorization of the data to be analyzed. We used methPLIER to analyze a lung cancer dataset and confirmed that the data decomposition reflected sample characteristics for recurrence-free survival. Moreover, methPLIER can analyze data obtained via different preprocessing methods, thereby reducing distributional bias among datasets due to preprocessing. Furthermore, methPLIER can be employed for comparative analyses of methylation data obtained from different platforms, thereby reducing bias in data distribution due to platform differences. methPLIER is expected to facilitate cross-sectional DNA methylation data analysis and enhance DNA methylation data resources.

Deep neural operator-driven real-time inference to enable digital twin solutions for nuclear energy systems.

This paper focuses on the feasibility of deep neural operator network (DeepONet) as a robust surrogate modeling method within the context of digital twin (DT) enabling technology for nuclear energy systems. Machine learning (ML)-based prediction algorithms that need extensive retraining for new reactor operational conditions may prohibit real-time inference for DT across varying scenarios. In this study, DeepONet is trained with possible operational conditions and that relaxes the requirement of continuous retraining - making it suitable for online and real-time prediction components for DT. Through benchmarking and evaluation, DeepONet exhibits remarkable prediction accuracy and speed, outperforming traditional ML methods, making it a suitable algorithm for real-time DT inference in solving a challenging particle transport problem. DeepONet also exhibits generalizability and computational efficiency as an efficient surrogate tool for DT component. However, the application of DeepONet reveals challenges related to optimal sensor placement and model evaluation, critical aspects of real-world DT implementation. Addressing these challenges will further enhance the method's practicality and reliability. Overall, this study marks an important step towards harnessing the power of DeepONet surrogate modeling for real-time inference capability within the context of DT enabling technology for nuclear systems.

Sketch-based semantic retrieval of medical images.

The volume of medical images stored in hospitals is rapidly increasing; however, the utilization of these accumulated medical images remains limited. Existing content-based medical image retrieval (CBMIR) systems typically require example images, leading to practical limitations, such as the lack of customizable, fine-grained image retrieval, the inability to search without example images, and difficulty in retrieving rare cases. In this paper, we introduce a sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without the need for example images. The key concept is feature decomposition of medical images, which allows the entire feature of a medical image to be decomposed into and reconstructed from normal and abnormal features. Building on this concept, our SBMIR system provides an easy-to-use two-step graphical user interface: users first select a template image to specify a normal feature and then draw a semantic sketch of the disease on the template image to represent an abnormal feature. The system integrates both types of input to construct a query vector and retrieves reference images. For evaluation, ten healthcare professionals participated in a user test using two datasets. Consequently, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for rare cases. Our SBMIR system provides on-demand, customizable medical image retrieval, thereby expanding the utility of medical image databases.

Magnetic resonance-based imaging biopsy with signatures including topological Betti number features for prediction of primary brain metastatic sites.

This study incorporated topology Betti number (BN) features into the prediction of primary sites of brain metastases and the construction of magnetic resonance-based imaging biopsy (MRB) models. The significant features of the MRB model were selected from those obtained from gray-scale and three-dimensional wavelet-filtered images, BN and inverted BN (iBN) maps, and clinical variables (age and gender). The primary sites were predicted as either lung cancer or other cancers using MRB models, which were built using seven machine learning methods with significant features chosen by three feature selection methods followed by a combination strategy. Our study dealt with a dataset with relatively smaller brain metastases, which included effective diameters greater than 2 mm, with metastases ranging from 2 to 9 mm accounting for 17% of the dataset. The MRB models were trained by T1-weighted contrast-enhanced images of 494 metastases chosen from 247 patients and applied to 115 metastases from 62 test patients. The most feasible model attained an area under the receiver operating characteristic curve (AUC) of 0.763 for the test patients when using a signature including features of BN and iBN maps, gray-scale and wavelet-filtered images, and clinical variables. The AUCs of the model were 0.744 for non-small cell lung cancer and 0.861 for small cell lung cancer. The results suggest that the BN signature boosted the performance of MRB for the identification of primary sites of brain metastases including small tumors.

Association of quantitative analysis of intratumoral reduced E-cadherin expression with lymph node metastasis and prognosis in patients with breast cancer.

Loss of E-cadherin expression is a poor prognostic factor in patients with breast cancer. Breast cancer cells co-cultured with adipocytes reportedly promote E-cadherin attenuation and tumor progression. The current study aimed to investigate the association of reduced E-cadherin expression with adipose tissue invasion (ATI) and prognosis in breast cancer. Surgical specimens were collected from 188 women with invasive ductal carcinoma of the breast who had undergone surgery without neoadjuvant treatment. We compared E-cadherin expression in ATI and invasive front (IF) using immunohistochemistry with ImageJ. Reduced E-cadherin expression was detected not only in the ATI area but also in the IF, and the degree of reduced E-cadherin expression was positively correlated with both areas. In patients with lymph node metastasis compared to those without, E-cadherin expression was reduced and this reduction was associated with poor recurrence-free survival. We concluded that E-cadherin expression is reduced not only at the ATI area but also at the IF of the tumor. Reduced E-cadherin expression is a clear prognostic factor for breast cancer. Hence, future research is warranted for establishing an objective and quantitative E-cadherin staining assay that will allow clinical use of E-cadherin as a prognostic factor.

Endoscopic mucosal ischemic index for predicting anastomotic complications after esophagectomy: a prospective cohort study.

BACKGROUND: Postoperative complications related to gastric conduit reconstruction are still common issues after McKeown esophagectomy. A novel endoscopic mucosal ischemic index is desired to predict anastomotic complications after McKeown esophagectomy. AIMS AND METHODS: The purpose of this study was to prospectively evaluate the safety and efficacy of endoscopic examinations of the anastomotic region in the acute period after esophagectomy. Endoscopic examinations were performed on postoperative days (PODs) 1 and 8. The severity of ischemia was prospectively validated according to the endoscopic mucosal ischemic index (EMII). RESULTS: A total of 58 patients were included after evaluating the safety and feasibility of the endoscopic examination on POD 1 in 10 patients. Anastomotic leakage occurred in 6 patients. Stricture occurred in 13 patients. A greater than 67% circumference and lesion length greater than 20 mm of anastomotic ischemic area (AIA) on POD 1 were associated with developing anastomotic leakage after esophagectomy (OR: 14.5; 95% CI: 1.8-306.5; P = 0.03, OR: 19.4; 95% CI: 1.7-536.8; P = 0.03). More than 67% circumferential ischemic mucosa and ischemic mucosal lengths greater than 20 mm of AIA on POD 1 were associated with developing anastomotic strictures after esophagectomy (OR: 6.4; 95% CI: 1.4-31.7; P = 0.02, OR: 5.9; 95% CI: 1.2-33.1; P = 0.03). Patients with either more than 67% circumferential ischemic mucosa or ischemic mucosal lengths greater than 20 mm of AIA on POD 1 were defined as EMII-positive patients. The sensitivity, specificity, and positive and negative predictive values of EMII positivity on POD 1 for leakage were 100%, 78.8%, 35.3%, and 100%, respectively. The sensitivity, specificity, and positive and negative predictive values of the EMII positivity on POD 1 for strictures were 69.2%, 82.2%, 52.9%, and 90.2%, respectively. CONCLUSIONS: The application of an endoscopic classification system to mucosal ischemia after McKeown esophagectomy is both appropriate and satisfactory in predicting anastomotic complications. TRIAL REGISTRATION: Clinical Trial.gov Registry, ID: NCT02937389, Registration date: Oct 17, 2015.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information.

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.

Application of non-negative matrix factorization in oncology: one approach for establishing precision medicine.

The increase in the expectations of artificial intelligence (AI) technology has led to machine learning technology being actively used in the medical field. Non-negative matrix factorization (NMF) is a machine learning technique used for image analysis, speech recognition, and language processing; recently, it is being applied to medical research. Precision medicine, wherein important information is extracted from large-scale medical data to provide optimal medical care for every individual, is considered important in medical policies globally, and the application of machine learning techniques to this end is being handled in several ways. NMF is also introduced differently because of the characteristics of its algorithms. In this review, the importance of NMF in the field of medicine, with a focus on the field of oncology, is described by explaining the mathematical science of NMF and the characteristics of the algorithm, providing examples of how NMF can be used to establish precision medicine, and presenting the challenges of NMF. Finally, the direction regarding the effective use of NMF in the field of oncology is also discussed.

[Congenital Pulmonary Airway Malformation Diagnosed in Adulthood].

Congenital pulmonary airway malformation diagnosed in adulthood is very rare. A 54-year-old woman was admitted to our hospital with complaints of abnormal chest shadow. Computed tomography( CT) demonstrated multiple cysts, mass lesions, and consolidation in left lower lobe. Bronchofiber scopy could not establish the diagnose. Left lower lobectomy was performed for diagnosis and treatment. Pathologically the lesion was diagnosed as congenital pulmonary airway malformation.

Prognostic Impact of Relative Dose Intensity of Adjuvant Chemotherapy With S-1 on Pancreatic Ductal Adenocarcinoma.

BACKGROUND/AIM: Although adjuvant chemotherapy (AC) with S-1 is currently the standard treatment for pancreatic ductal adenocarcinoma (PDAC) in Japan, the associations between its relative dose intensity (RDI) and survival outcomes remain unclear. PATIENTS AND METHODS: We reviewed 310 patients with PDAC who had undergone pancreatectomy from January 2014 to June 2020 at three institutions. Of these, patients who had received adjuvant S-1 monotherapy were analyzed. Patients who had died or developed recurrences within 6 months, or received neoadjuvant chemotherapy, were excluded from the analyses. Possible predictors of overall survival (OS), including RDI, were analyzed using Cox regression. The cutoff value for RDI was determined by receiver operating characteristic analysis. RESULTS: Ninety-four patients with a median age of 69 years (range=39-84 years) were analyzed. In the high-RDI group (RDI≥72.3%, n=74), the OS rates were 98.5% and 80.8% at 1 and 3 years, respectively, whereas in the low-RDI group (RDI <72.3%, n=20) they were 88.9% and 51.6%, respectively (p=0.001). By multivariate analysis, lymph node metastasis [hazard ratio (HR)=3.06; p=0.020], low RDI (HR=2.95; p=0.020), and time interval from surgery to initiation of AC > 51 days (HR=2.50; p=0.046) were independently associated with inferior OS. The combination of the latter two factors clearly stratified both OS and recurrence-free survival (p<0.001 and p=0.017, respectively). CONCLUSION: Early initiation and maintenance of RDI of S-1 monotherapy after pancreatectomy may improve the OS of PDAC patients.

Impact of chronological age on efficacy and safety of fluoropyrimidine plus bevacizumab in older non-frail patients with metastatic colorectal cancer: a combined analysis of individual data from two phase II studies of patients aged >75 years.

OBJECTIVE: Many clinical trials for older patients with metastatic colorectal cancer have been conducted, and fluoropyrimidine and bevacizumab are standard treatments. However, the relationship between age and the efficacy and safety of this treatment is unclear in older metastatic colorectal cancer patients. METHODS: Individual data from two phase II studies on older (≥75 years), non-frail patients with metastatic colorectal cancer treated with uracil-tegafur/leucovorin or S-1 combined with bevacizumab were collected. Patient characteristics were evaluated with multiple regression analyses for survival outcomes, using the Cox proportional hazard model and linear regression analyses for the worst grade of adverse events. RESULTS: We enrolled 102 patients with a median age of 80 years (range, 75-88 years). Of the 70 patients who died, seven (10%) died of causes unrelated to disease or treatment. The study treatment was discontinued due to adverse events in 19 patients (18.6%), with 63% aged ≥85 years. The adverse event that most commonly resulted in treatment discontinuation was grade 2 fatigue (21%). Chronological age was not associated with progression-free survival (Hazard ratio, 1.03; P = 0.40) or overall survival (Hazard ratio, 1.02; P = 0.65). Age was weakly associated with non-hematologic adverse events (regression coefficient [R], 0.27; P = 0.007), especially fatigue (R, 0.23; P = 0.02) and nausea (R, 0.19; P = 0.06), but not with hematologic (R, 0.05; P = 0.43) or bevacizumab-related (R, -0.06; P = 0.56) adverse events. CONCLUSIONS: The efficacy of fluoropyrimidine plus bevacizumab was age-independent in patients with metastatic colorectal cancer aged ≥75 years, and attention should be paid to non-hematologic adverse events as age increases.

[Surgical Treatment for Lung Cancer Associated with Hypertrophic Pulmonary Osteoarthropathy].

Hypertrophic pulmonary osteoarthropathy( HPO) is a rare paraneoplastic manifestation of lung cancer that causes joint pain, joint swelling, and limited range of motion. Two surgical cases of lung cancer with HPO are presented. Case1:A 43-year-old female was referred to our department with a diagnosis of cStage ⅡB left hilar lung cancer. She had difficulty in walking due to arthralgia caused by HPO. Left pneumonectomy was performed and the arthralgia disappeared on the first postoperative day. The patient is being well after surgery without relapse of joint symptoms. Case2:The patient was a 65-year-old male with cStage ⅡA right lung cancer. The symptoms of HPO appeared after he was found to have lung cancer. After right upper lobectomy, the arthralgia disappeared on the first postoperative day. Currently, he is receiving adjuvant chemotherapy, without relapse of joint symptoms.

Bilateral Inflammatory Breast Cancer That Developed Two Years after Treatment for Triple-negative Breast Cancer.

A 66-year-old woman underwent partial mastectomy and a sentinel lymph node biopsy for left breast cancer; the pathological diagnosis was invasive ductal carcinoma (pT1aN0, pStage I, triple-negative subtype). Postoperative radiotherapy was performed. Two years later, she developed redness and induration at both breasts. The diagnosis was bilateral inflammatory breast cancer. After four cycles of dose-dense epirubicin and cyclophosphamide followed by 12 weekly paclitaxel cycles, bilateral total mastectomy and axillary lymph node dissection were performed. At the one-year follow-up after undergoing operation and radiotherapy, she remained alive without recurrence. Dose-dense treatment regimens may help patients achieve complete resection without short-term recurrence.

Comparison of Dasatinib- and Imatinib-Related Cardiotoxic Adverse Events in Japanese Patients With Chronic Myeloid Leukemia and Gastrointestinal Stromal Tumor.

Background: Despite the beneficial effects of BCR-ABL1 tyrosine kinase inhibitors (TKIs) in the treatment of chronic myeloid leukemia (CML), they may also cause adverse events (AEs), especially cardiovascular toxicity. The incidence of TKI-induced AEs may vary among ethnic groups, and there is little specific information for Japanese patients. Methods and Results: Sixty-nine consecutive patients who were started on treatment with dasatinib (n=25) or imatinib (n=44) for CML or gastrointestinal stromal tumor (GIST) between December 2008 and December 2019 were retrospectively recruited to the study. We determined the prevalence of AEs through October 2020 and compared the incidence of AEs between the 2 drugs. Baseline characteristics were comparable between the 2 groups. However, compared with the imatinib-treated group, the dasatinib-treated group had a higher incidence of congestive heart failure (CHF; 20.0% vs. 2.3%; P=0.04), pleural effusion (48% vs. 20.5%; P=0.03), pericardial effusion (24% vs. 4.6%; P=0.02), QT prolongation (4 vs. 0 patients; P=0.02), and pulmonary hypertension (3 vs. 0 patients; P=0.04). In the dasatinib-treated group, CHF tended to be associated with tricuspid valve regurgitation pressure gradient, and pleural effusion was observed in all patients. All-cause mortality and other cardiovascular events did not differ significantly between the 2 groups. Conclusions: Cardiotoxic AEs occurred more frequently in Japanese patients with CML and GIST treated with dasatinib than imatinib.

Vasohibin-1 and -2 in pulmonary lymphangioleiomyomatosis (LAM) cells associated with angiogenic and prognostic factors.

Lymphangioleiomyomatosis (LAM) is a rare pulmonary neoplasm, clinically associated with dyspnea and respiratory failure. Current therapeutic modalities do not necessarily reach satisfactory outcome and novel therapeutic approaches are currently warranted. Therefore, in this study, we focused on vasohibin-1 (VASH1) and -2 (VASH2); VASH1 terminated and VASH2 promoted angiogenesis. In addition, both VASH1/2 were reported to influence the progression of various human malignancies. We first performed hierarchical clustering analysis to attempt to classify 36 LAM cases into three different clusters according to immunoreactivity of VASH1/2 and other angiogenic and prognostic factors of LAM; VEGFR1/2/3, p-mTOR, p-S6, p-4EBP, ERα, PgR, MMP2, and MMP9. The cluster harboring higher angiogenic factors had higher VASH1/2 status. VASH1 was significantly positively correlated with VEGFR2, MMP9, and p-mTOR (p-value <0.05), and VASH2 with both angiogenic and prognostic factors including VEGFR1, PgR, MMP9, p-mTOR, p-S6, and p-4EBP (p-value <0.05). Subsequent PCR array of angiogenic genes demonstrated that high VASH1 mRNA was significantly positively associated with the status of SPHK1 and TYPM, lower EGF and EFNB2 (p-value <0.05), and high VASH2 mRNA negatively with MMP2 (p-value <0.05). VASH1 was considered to be up-regulated by activation of angiogenesis, whereas VASH2 could influence the angiogenesis and progression of LAM.

Phase II study of S-1 and oxaliplatin as neoadjuvant chemotherapy for locally advanced adenocarcinoma of the gastric or esophagogastric junction: KSCC1601.

BACKGROUND: Perioperative chemotherapy is the standard of care for locally advanced gastric cancer (LAGC). This phase II study investigated the efficacy and safety of S-1 and oxaliplatin (SOX) as neoadjuvant chemotherapy (NAC) for LAGC and esophagogastric junction cancer (EGJC). METHODS: Patients completed up to three cycles of SOX130 (oxaliplatin 130 mg/m2 on day 1, oral S-1 40-60 mg twice daily for 2 weeks every 3 weeks), followed by gastrectomy and D2 lymphadenectomy. The primary endpoint was the pathological response rate (pRR). The anastomosis leakage rate was the secondary endpoint in patients with EGJC, and other secondary endpoints were the R0 resection, overall survival (OS), and relapse-free survival (RFS) rates. RESULTS: Between April 2016 and July 2017, 47 patients (24 EGJC, 23 LAGC) were enrolled in this study. Forty-two patients (89.4%, 95% confidence interval [CI] = 76.9-96.5) underwent surgery, and R0 resection was achieved in 41 patients. The pRR was 59.5% (90% CI = 45.7-72.3). The major grade 3 or 4 toxicities were appetite loss in six patients (12.8%), thrombocytopenia in five patients (10.6%), and neutropenia and diarrhea in three patients (6.4%) each. The rate of severe anastomotic leakage (Clavien-Dindo classification grade III or higher) in 20 EGJC was 25.0% (90% CI = 10.4-45.6). The 3-year OS and RFS rate were 62.9% (95% CI = 47.2-75.1) and 53.2% (95% CI = 38.1-66.2), respectively. CONCLUSION: SOX130 demonstrated substantial benefit for LAGC and EGJC. However, special attention should be paid to anastomotic leakage during surgery for EGJC.

Long-term peritoneal dialysate exposure modulates expression of membrane complement regulators in human peritoneal mesothelial cells.

The membrane complement regulators (CRegs) CD46, CD55, and CD59 are highly expressed on human peritoneal mesothelial cells. However, how mesothelial CRegs change according to the peritoneal dialysis (PD) history of patients has remained unclear. We therefore examined longitudinal changes in CRegs in primary cultured mesothelial cells from PD patients (human peritoneal mesothelial cells; HPMCs) and examined which components of PD fluid (PDF) affect CRegs in vitro. We measured levels of soluble C5b-9 in overnight-dwelling PDF in PD patients and also evaluated changes in CRegs expression on HPMCs collected from PDF using flow cytometry and polymerase chain reaction at a 1-year interval of PD therapy. We also evaluated changes in CReg expressions with stimulation by each component of PDF (glucose, lactic acid and pH) using the Met5A human mesothelial cell line. Levels of sC5b-9 in PDF decreased significantly during 1 year, while expressions of CD46 and CD59 proteins and mRNAs increased significantly in HPMCs during 1 year. Analyzing Met-5A cells, we observed that expressions of the three CRegs were increased by glucose and lactic acid in a concentration-dependent manner, but conversely that expressions of CRegs were decreased by lower pH stimulation. History of PD might influence expression of CRegs by HPMCs through properties of PDF such as glucose, lactic acid, and pH. These results suggest that mesothelial cells may alter expression of CRegs for the purpose of protecting the peritoneum and the presence of PDF might affect peritoneal homeostasis associated with the complement system.

Single-Cell Analysis Using Machine Learning Techniques and Its Application to Medical Research.

In recent years, the diversity of cancer cells in tumor tissues as a result of intratumor heterogeneity has attracted attention. In particular, the development of single-cell analysis technology has made a significant contribution to the field; technologies that are centered on single-cell RNA sequencing (scRNA-seq) have been reported to analyze cancer constituent cells, identify cell groups responsible for therapeutic resistance, and analyze gene signatures of resistant cell groups. However, although single-cell analysis is a powerful tool, various issues have been reported, including batch effects and transcriptional noise due to gene expression variation and mRNA degradation. To overcome these issues, machine learning techniques are currently being introduced for single-cell analysis, and promising results are being reported. In addition, machine learning has also been used in various ways for single-cell analysis, such as single-cell assay of transposase accessible chromatin sequencing (ATAC-seq), chromatin immunoprecipitation sequencing (ChIP-seq) analysis, and multi-omics analysis; thus, it contributes to a deeper understanding of the characteristics of human diseases, especially cancer, and supports clinical applications. In this review, we present a comprehensive introduction to the implementation of machine learning techniques in medical research for single-cell analysis, and discuss their usefulness and future potential.