MARLens: Understanding Multi-Agent Reinforcement Learning for Traffic Signal Control Via Visual Analytics.

The issue of traffic congestion poses a significant obstacle to the development of global cities. One promising solution to tackle this problem is intelligent traffic signal control (TSC). Recently, TSC strategies leveraging reinforcement learning (RL) have garnered attention among researchers. However, the evaluation of these models has primarily relied on fixed metrics like reward and queue length. This limited evaluation approach provides only a narrow view of the model's decision-making process, impeding its practical implementation. Moreover, effective TSC necessitates coordinated actions across multiple intersections. Existing visual analysis solutions fall short when applied in multi-agent settings. In this study, we delve into the challenge of interpretability in multi-agent reinforcement learning (MARL), particularly within the context of TSC. We propose MARLens, a visual analytics system tailored to understand MARL-based TSC. Our system serves as a versatile platform for both RL and TSC researchers. It empowers them to explore the model's features from various perspectives, revealing its decision-making processes and shedding light on interactions among different agents. To facilitate quick identification of critical states, we have devised multiple visualization views, complemented by a traffic simulation module that allows users to replay specific training scenarios. To validate the utility of our proposed system, we present three comprehensive case studies, incorporate insights from domain experts through interviews, and conduct a user study. These collective efforts underscore the feasibility and effectiveness of MARLens in enhancing our understanding of MARL-based TSC systems and pave the way for more informed and efficient traffic management strategies.

Decrease in lipid metabolic indexes in infants with neonatal respiratory distress syndrome.

Incomplete pulmonary function and insufficient production of pulmonary surfactant in premature infants may affect alveolar relaxation, inducing neonatal respiratory distress syndrome (NRDS). The present study was a retrospective comparison of lipid metabolism indexes and clinic information between NRDS and non-NRDS infants. Data on general information, pregnancy, clinical symptoms, family history as well as plasma biochemical and lipid metabolic indexes were retrospectively collected and statistically analyzed from 79 patients with NRDS and 44 non-NRDS infants. Infants in the NRDS group showed lower body weight (2,055 vs. 3,225 g) and gestation age (33.39 vs. 38.53 weeks) than those in the non-NRDS group (P<0.05). Baseline information was corrected by the inverse probability of treatment weighting (IPTW) analysis. The weighted adjusted median age was the same in both groups and there was no significant difference between two groups in birth weight. The IPTW analysis revealed that the levels of plasma triglyceride (TG), total cholesterol, low-density lipoprotein, free triiodothyronine, free thyroxine, glucose, calcium (Ca2+) and phosphorus in the NRDS infants were significantly lower compared with those in the non-NRDS infants. Additionally, NRDS infants had significantly higher incidence rates of pneumonia, sepsis, brain injury infection, preterm birth, patent foramen ovale, patent ductus arteriosus and premature rupture of membranes compared with the non-NRDS infants (P<0.05). Multivariate logistic analysis showed that TG and Ca2+ were risk factors associated with NRDS (P<0.05). Infants with NRDS have significantly lower levels of plasma lipid indexes. The results of the present study provide data to guide the clinical management of NRDS.

Fatal cytokine-release syndrome in a patient receiving toripalimab: a case report.

Immune checkpoint inhibitors, a type of immunotherapy, have demonstrated optimal treatment efficacy in inducing durable antitumor responses in various cancers. Cytokine-release syndrome is a rare immune-related adverse event induced by immune checkpoint inhibitors. In our case, a patient with hypopharyngeal squamous cell carcinoma received toripalimab combined with chemotherapy. On the fourth day post treatment, the patient developed fever and hypotension. Laboratory examination indicated myelosuppression, acute kidney injury and disseminated intravascular coagulation. Meanwhile, serum cytokine levels of IL-6, IL-8, IL-10, IL-1ß, IFN-γ and the level of hypersensitive C-reactive protein were markedly elevated. The patient was diagnosed with cytokine release syndrome, which progressed rapidly and led to the patient's demise on the fifth day post treatment.

Immune checkpoint inhibitors (ICIs) have shown revolutionary efficacy in the treatment of multiple cancers. Cytokine-release syndrome (CRS) is a common and lethally adverse event of chimeric antigen receptor T-cell therapy; however, this adverse effect is rare in ICI therapy. Presently, while ICI-associated CRS is reported almost exclusively in case reports, fatal outcomes are rarely observed. A patient with hypopharyngeal squamous cell carcinoma received toripalimab combined with chemotherapy. On the fourth day post treatment, the patient developed CRS, which progressed rapidly, and the patient died on the fifth day post treatment.