Background Heparin is one of the most commonly used medications in intensive care units. In clinical practice, the use of a weight-based heparin dosing nomogram is standard practice for the treatment of thrombosis. Recently, machine learning techniques have dramatically improved the ability of computers to provide clinical decision support and have allowed for the possibility of computer generated, algorithm-based heparin dosing recommendations. Objective The objective of this study was to predict the effects of heparin treatment using machine learning methods to optimize heparin dosing in intensive care units based on the predictions. Patient state predictions were based upon activated partial thromboplastin time in 3 different ranges: subtherapeutic, normal therapeutic, and supratherapeutic, respectively. Methods Retrospective data from 2 intensive care unit research databases (Multiparameter Intelligent Monitoring in Intensive Care III, MIMIC-III; e–Intensive Care Unit Collaborative Research Database, eICU) were used for the analysis. Candidate machine learning models (random forest, support vector machine, adaptive boosting, extreme gradient boosting, and shallow neural network) were compared in 3 patient groups to evaluate the classification performance for predicting the subtherapeutic, normal therapeutic, and supratherapeutic patient states. The model results were evaluated using precision, recall, F1 score, and accuracy. Results Data from the MIMIC-III database (n=2789 patients) and from the eICU database (n=575 patients) were used. In 3-class classification, the shallow neural network algorithm performed the best (F1 scores of 87.26%, 85.98%, and 87.55% for data set 1, 2, and 3, respectively). The shallow neural network algorithm achieved the highest F1 scores within the patient therapeutic state groups: subtherapeutic (data set 1: 79.35%; data set 2: 83.67%; data set 3: 83.33%), normal therapeutic (data set 1: 93.15%; data set 2: 87.76%; data set 3: 84.62%), and supratherapeutic (data set 1: 88.00%; data set 2: 86.54%; data set 3: 95.45%) therapeutic ranges, respectively. Conclusions The most appropriate model for predicting the effects of heparin treatment was found by comparing multiple machine learning models and can be used to further guide optimal heparin dosing. Using multicenter intensive care unit data, our study demonstrates the feasibility of predicting the outcomes of heparin treatment using data-driven methods, and thus, how machine learning–based models can be used to optimize and personalize heparin dosing to improve patient safety. Manual analysis and validation suggested that the model outperformed standard practice heparin treatment dosing.

Background Although protective mechanical ventilation (MV) has been used in a variety of applications, lung injury may occur in both patients with and without acute respiratory distress syndrome (ARDS). The purpose of this study is to use machine learning to identify clinical phenotypes for critically ill patients with MV in intensive care units (ICUs). Methods A retrospective cohort study was conducted with 5013 patients who had undergone MV and treatment in the Department of Critical Care Medicine, Peking Union Medical College Hospital. Statistical and machine learning methods were used. All the data used in this study, including demographics, vital signs, circulation parameters and mechanical ventilator parameters, etc., were automatically extracted from the electronic health record (EHR) system. An external database, Medical Information Mart for Intensive Care III (MIMIC III), was used for validation. Results Phenotypes were derived from a total of 4009 patients who underwent MV using a latent profile analysis of 22 variables. The associations between the phenotypes and disease severity and clinical outcomes were assessed. Another 1004 patients in the database were enrolled for validation. Of the five derived phenotypes, phenotype I was the most common subgroup (n = 2174; 54.2%) and was mostly composed of the postoperative population. Phenotype II (n = 480; 12.0%) led to the most severe conditions. Phenotype III (n = 241; 6.01%) was associated with high positive end-expiratory pressure (PEEP) and low mean airway pressure. Phenotype IV (n = 368; 9.18%) was associated with high driving pressure, and younger patients comprised a large proportion of the phenotype V group (n = 746; 18.6%). In addition, we found that the mortality rate of Phenotype IV was significantly higher than that of the other phenotypes. In this subgroup, the number of patients in the sequential organ failure assessment (SOFA) score segment (9,22] was 198, the number of deaths was 88, and the mortality rate was higher than 44%. However, the cumulative 28-day mortality of Phenotypes IV and II, which were 101 of 368 (27.4%) and 87 of 480 (18.1%) unique patients, respectively, was significantly higher than those of the other phenotypes. There were consistent phenotype distributions and differences in biomarker patterns by phenotype in the validation cohort, and external verification with MIMIC III further generated supportive results. Conclusions Five clinical phenotypes were correlated with different disease severities and clinical outcomes, which suggested that these phenotypes may help in understanding heterogeneity in MV treatment effects.

Objectives: To give a comprehensive review of the literature comparing perioperative outcomes and long-term survival with robotic-assisted minimally invasive esophagectomy (RAMIE) versus minimally invasive esophagectomy (MIE) for esophageal cancer. Background: Curative minimally invasive surgical treatment for esophageal cancer includes RAMIE and conventional MIE. It remains controversial whether RAMIE is comparable to MIE. Methods: This review was registered at the International Prospective Register of Systematic Reviews (CRD42021260963). A systematic search of databases was conducted. Perioperative outcomes and long-term survival were analyzed and subgroup analysis was conducted. Cumulative meta-analysis was performed to track therapeutic effectiveness. Results: Eighteen studies were included and a total of 2932 patients (92.88% squamous cell carcinoma, 29.83% neoadjuvant therapy, and 38.93% stage III-IV), 1418 underwent RAMIE and 1514 underwent MIE, were analyzed. The number of total lymph nodes (LNs) [23.35 (95% CI: 21.41–25.29) vs 21.98 (95% CI: 20.31–23.65); mean difference (MD) = 1.18; 95% CI: 0.06–2.30; P=0.04], abdominal LNs [9.05 (95% CI: 8.16–9.94) vs 7.75 (95% CI: 6.62–8.88); MD = 1.04; 95% CI: 0.19–1.89; P=0.02] and LNs along the left recurrent laryngeal nerve [1.74 (95% CI: 1.04–2.43) vs 1.34 (95% CI: 0.32–2.35); MD = 0.22; 95% CI: 0.09–0.35; P <0.001] were significantly higher in the RAMIE group. RAMIE is associated with a lower incidence of pneumonia [9.61% (95% CI: 7.38%–11.84%) vs 14.74% (95% CI: 11.62%–18.15%); odds ratio = 0.73; 95% CI: 0.58-0.93; P=0.01]. Meanwhile, other perioperative outcomes, such as operative time, blood loss, length of hospital stay, 30/90-day mortality, and R0 resection, showed no significant difference between the two groups. Regarding long-term survival, the 3-year overall survival was similar in the two groups, whereas patients undergoing RAMIE had a higher rate of 3-year disease-free survival compared with the MIE group [77.98% (95% CI: 72.77%–82.43%) vs 70.65% (95% CI: 63.87%–77.00%); odds ratio = 1.42; 95% CI: 1.11–1.83; P=0.006]. A cumulative meta-analysis conducted for each outcome demonstrated relatively stable effects in the two groups. Analyses of each subgroup showed similar overall outcomes. Conclusions: RAMIE is a safe and feasible alternative to MIE in the treatment of resectable esophageal cancer with comparable perioperative outcomes and seems to indicate a possible superiority in LNs dissection in the abdominal cavity, and LNs dissected along the left recurrent laryngeal nerve and 3-year disease-free survival in particular in esophageal squamous cell carcinoma. Further randomized studies are needed to better evaluate the long-term benefits of RAMIE compared with MIE.

Background Unfractionated heparin is widely used in the intensive care unit as an anticoagulant. However, weight-based heparin dosing has been shown to be suboptimal and may place patients at unnecessary risk during their intensive care unit stay. Objective In this study, we intended to develop and validate a machine learning–based model to predict heparin treatment outcomes and to provide dosage recommendations to clinicians. Methods A shallow neural network model was adopted in a retrospective cohort of patients from the Multiparameter Intelligent Monitoring in Intensive Care III (MIMIC III) database and patients admitted to the Peking Union Medical College Hospital (PUMCH). We modeled the subtherapeutic, normal, and supratherapeutic activated partial thromboplastin time (aPTT) as the outcomes of heparin treatment and used a group of clinical features for modeling. Our model classifies patients into 3 different therapeutic states. We tested the prediction ability of our model and evaluated its performance by using accuracy, the kappa coefficient, precision, recall, and the F1 score. Furthermore, a dosage recommendation module was designed and evaluated for clinical decision support. Results A total of 3607 patients selected from MIMIC III and 1549 patients admitted to the PUMCH who met our criteria were included in this study. The shallow neural network model showed results of F1 scores 0.887 (MIMIC III) and 0.925 (PUMCH). When compared with the actual dosage prescribed, our model recommended increasing the dosage for 72.2% (MIMIC III, 1240/1718) and 64.7% (PUMCH, 281/434) of the subtherapeutic patients and decreasing the dosage for 80.9% (MIMIC III, 504/623) and 76.7% (PUMCH, 277/361) of the supratherapeutic patients, suggesting that the recommendations can contribute to clinical improvements and that they may effectively reduce the time to optimal dosage in the clinical setting. Conclusions The evaluation of our model for predicting heparin treatment outcomes demonstrated that the developed model is potentially applicable for reducing the misdosage of heparin and for providing appropriate decision recommendations to clinicians.

Patients undergoing lobectomy are at significantly increased risk of lung injury. One-lung ventilation is the most commonly used technique to maintain ventilation and oxygenation during the operation. It is a challenge to choose an appropriate mechanical ventilation strategy to minimize the lung injury and other adverse clinical outcomes. In order to understand the available evidence, a systematic review was conducted including the following topics: (I) protective ventilation (PV); (II) mode of mechanical ventilation [e.g., volume controlled (VCV) versus pressure controlled (PCV)]; (III) use of therapeutic hypercapnia; (IV) use of alveolar recruitment (open-lung) strategy; (V) pre-and post-operative application of positive end expiratory pressure (PEEP); (VI) Inspired Oxygen concentration; (VII) Non-intubated thoracoscopic lobectomy; and (VIII) adjuvant pharmacologic options. The recommendations of class II are non-intubated thoracoscopic lobectomy may be an alternative to conventional one-lung ventilation in selected patients. The recommendations of class IIa are: (I) Therapeutic hypercapnia to maintain a partial pressure of carbon dioxide at 50-70 mmHg is reasonable for patients undergoing pulmonary lobectomy with one-lung ventilation; (II) PV with a tidal volume of 6 mL/kg and PEEP of 5 cmHO are reasonable methods, based on current evidence; (III) alveolar recruitment [open lung ventilation (OLV)] may be beneficial in patients undergoing lobectomy with one-lung ventilation; (IV) PCV is recommended over VCV for patients undergoing lung resection; (V) pre- and post-operative CPAP can improve short-term oxygenation in patients undergoing lobectomy with one-lung ventilation; (VI) controlled mechanical ventilation with I:E ratio of 1:1 is reasonable in patients undergoing one-lung ventilation; (VII) use of lowest inspired oxygen concentration to maintain satisfactory arterial oxygen saturation is reasonable based on physiologic principles; (VIII) Adjuvant drugs such as nebulized budesonide, intravenous sivelestat and ulinastatin are reasonable and can be used to attenuate inflammatory response.