Profiling lung adenocarcinoma by liquid biopsy: can one size fit all?

Prognosis of recurrence after complete resection in early-stage lung adenocarcinoma based on molecular alterations: a systematic review and meta-analysis

Molecular biomarkers have the potential to predict the recurrence risk of early-stage lung adenocarcinoma (LUAD) after complete resection, but the study results are controversial. We aimed to clarify the association of molecular alterations with disease-free survival (DFS) and recurrence-free survival (RFS) in early-stage LUAD with R0 resection. Comprehensive searches were conducted in PubMed/MEDLINE, Web of Science, and Cochrane Library for this systematic review and meta-analysis with date restrictions from 2012 to 2022. In the 18 included studies, data from a total of 7417 participants in 11 studies and 4167 participants in 9 studies were collected for the EGFR and KRAS meta-analyses, respectively. Two studies were assessed as having a moderate risk of bias, and the others were all assessed as having a high individual risk of bias. The molecular alterations in KRAS rather than EGFR, were associated with a high risk of recurrence for early-stage LUAD patients suffering from R0 resection, especially for those in pStage I, the pooled hazard ratios (HRs) of KRAS were 2.71 (95% CI, 1.81-4.06; I2 = 22%; P < 0.00001) and 1.95 (95% CI, 1.25-3.20; I2 = 57%; P = 0.003) with small interstudy heterogeneity in univariate and multivariate analyses, respectively. This finding suggests that molecular alterations in KRAS that could be detected by polymerase chain reaction techniques would provide new insight into stratifying risk and personalizing patient postoperative follow-up.

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

Identification of Common and Subtype-Specific Mutated Sub-Pathways for a Cancer

The heterogeneity of cancer is a big obstacle for cancer diagnosis and treatment. Prioritizing combinations of driver genes that mutate in most patients of a specific cancer or a subtype of this cancer is a promising way to tackle this problem. Here, we developed an empirical algorithm, named PathMG, to identify common and subtype-specific mutated sub-pathways for a cancer. By analyzing mutation data of 408 samples (Lung-data1) for lung cancer, three sub-pathways each covering at least 90% of samples were identified as the common sub-pathways of lung cancer. These sub-pathways were enriched with mutated cancer genes and drug targets and were validated in two independent datasets (Lung-data2 and Lung-data3). Especially, applying PathMG to analyze two major subtypes of lung cancer, lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LSCC), we identified 13 subtype-specific sub-pathways with at least 0.25 mutation frequency difference between LUAD and LSCC samples in Lung-data1, and 12 of the 13 sub-pathways were reproducible in Lung-data2 and Lung-data3. Similar analyses were done for colorectal cancer. Together, PathMG provides us a novel tool to identify potential common and subtype-specific sub-pathways for a cancer, which can provide candidates for cancer diagnoses and sub-pathway targeted treatments.