Control of ZIF-62 and ag ZIF-62 Film Thickness within Asymmetric Tubular Supports through Pressure and Dose Time Variation of Atomic Layer Deposition.

Thin-films of metal-organic frameworks (MOFs) have widespread potential applications, especially with the emergence of glass-forming MOFs, which remove the inherent issue of grain boundaries and allow coherent amorphous films to be produced. Herein, it is established that atomic layer deposition (ALD) of zinc oxide lends excellent control over the thickness and localization of resultant polycrystalline and glass zeolitic imidazole framework-62 (ZIF-62) thin-films within tubular α-alumina supports. Through the reduction of the chamber pressure and dose times during zinc oxide deposition, the resultant ZIF-62 films are reduced from 38 µm to 16 µm, while the presence of sporadic ZIF-62 (previously forming as far as 280 µm into the support) is prevented. Furthermore, the glass transformation shows a secondary reduction in film thickness from 16 to 2 µm.

Augmented Reality in Minimally Invasive Spinal Surgery: A Narrative Review of Available Technology.

INTRODUCTION: Spine surgery has undergone significant changes in approach and technique. With the adoption of intraoperative navigation, minimally invasive spinal surgery (MISS) has arguably become the gold standard. Augmented reality (AR) has now emerged as a front-runner in anatomical visualization and narrower operative corridors. In effect, AR is poised to revolutionize surgical training and operative outcomes. Our study examines the current literature on AR-assisted MISS, synthesizes findings, and creates a narrative highlighting the history and future of AR in spine surgery. MATERIAL AND METHODS: Relevant literature was gathered using the PubMed (Medline) database from 1975 to 2023. Pedicle screw placement models were the primary intervention in AR. These were compared to the outcomes of traditional MISS RESULTS: We found that AR devices on the market show promising clinical outcomes in preoperative training and intraoperative use. Three prominent systems were as follows: XVision, HoloLens, and ImmersiveTouch. In the studies, surgeons, residents, and medical students had opportunities to operate AR systems, showcasing their educational potential across each phase of learning. Specifically, one facet described training with cadaver models to gauge accuracy in pedicle screw placement. AR-MISS exceeded free-hand methods without unique complications or contraindications. CONCLUSIONS: While still in its infancy, AR has already proven beneficial for educational training and intraoperative MISS applications. We believe that with continued research and advancement of this technology, AR is poised to become a dominant player within the fundamentals of surgical education and MISS operative technique.

Cardiovascular Protection with a Long-Acting GLP-1 Receptor Agonist Liraglutide: An Experimental Update.

Angiotensin II (Ang II), a peptide hormone generated as part of the renin-angiotensin system, has been implicated in the pathophysiology of many cardiovascular diseases such as peripheral artery disease, heart failure, hypertension, coronary artery disease and other conditions. Liraglutide, known as an incretin mimetic, is one of the glucagon-like peptide-1 (GLP-1) receptor agonists, and has been proven to be effective in the treatment of cardiovascular disorders beyond adequate glycemic control. The objective of this review is to compile our recent experimental outcomes-based studies, and provide an overview the cardiovascular protection from liraglutide against Ang II- and pressure overload-mediated deleterious effects on the heart. In particular, the mechanisms of action underlying the inhibition of oxidative stress, vascular endothelial dysfunction, hypertension, cardiac fibrosis, left ventricular hypertrophy and heart failure with liraglutide are addressed. Thus, we support the notion that liraglutide continues to be a useful add-on therapy for the management of cardiovascular diseases.

Conglomeration of T- and B-Cell Matrix Responses Determines the Potency of Human Bone Marrow Mesenchymal Stromal Cells.

Cell manufacturing facilities need to define the potency of mesenchymal stromal cells (MSCs) as cellular therapeutics in advanced clinical trials or marketing approval. Since MSCs' mechanism of action in humans is not well defined, more than a single functional property of MSCs needs to be captured as a surrogate measure of potency utilizing assay matrix technologies. However, the current limitation is the sole investigation of MSC-mediated T-cell suppression as a surrogate measure of potency. We investigated the effect of MSCs on B-cell matrix responses to be incorporated into the assay matrix potency analytical system. Our results demonstrate that MSCs inhibit B-cell differentiation and block pan-antibody secretion upon activation of B cells in the PBMCs. In contrast, MSCs are inferior in blocking B-cell matrix responses when purified B cells are used. Mechanistic analysis has demonstrated that MSC-mediated inhibition of B-cell matrix responses is non-contact dependent and Tryptophan metabolic pathway plays a major role, akin to the mechanism of MSC-mediated T-cell suppression. MSCs also inhibit both T-cell and B-cell responses when both of these lymphoid populations are concurrently activated in the PBMCs. Secretome analysis of MSC and T/B cell-activated PBMC cocultures identified direct and inverse correlative matrix signatures between humoral antibody isotypes and secretory molecules. The current analysis of the combined and concomitant investigation of T-cell and B-cell matrix responses fulfills the potency assay matrix strategy by incorporating MSCs' interaction with more than a single inflammatory immune responder.

Safety and Effectiveness of Mechanical Thrombectomy for Acute Ischemic Stroke Using Single Plane Angiography.

OBJECTIVES: Nearly all data on mechanical thrombectomy for acute ischemic stroke is based on procedures performed on biplane angiography systems. However, thrombectomy may be performed on single-plane systems in situations of triage or limited resources. We present the first US study comparing the safety and effectiveness of mechanical thrombectomy performed on single-plane vs. biplane systems. METHODS AND METHODS: A retrospective review of a prospectively maintained database identified all patients treated with thrombectomy between July 2020 and July 2021 by a high-volume practice. Patients were dichotomized into those treated on single plane and biplane systems. Demographic, procedural, clinical and follow-up characteristics were compared. RESULTS: Of the 246 patients treated with mechanical thrombectomy, 70 (33%) and 141 (66%) patients were treated on SP and BP systems, respectively. No significant differences were detected in follow-up 'good functional outcome' (mRS ≤ 2; SP 51% vs BP 43%, p = 0.14), successful recanalization (SP 87% vs BP 88%, p = 0.72), intra-procedural vascular injury (SP 3% vs BP 2%, p = 0.96), or time from groin puncture to reperfusion (SP 24 min vs BP 26 min, p = 0.58). Additionally, no significant differences were detected in peri-procedural complications, fluoroscopy times or total radiation. Patients treated on single plane systems required significantly more contrast. CONCLUSIONS: Mechanical thrombectomy for acute ischemic stroke performed on single plane angiography systems is as safe and efficacious as when performed on biplane systems. Our results may have implications for increasing stroke care access, both domestically in underserved/rural areas and internationally when considering requirements for stroke care in lower-income countries.

Impact of Cryopreservation and Freeze-Thawing on Therapeutic Properties of Mesenchymal Stromal/Stem Cells and Other Common Cellular Therapeutics.

Purpose of Review: Cryopreservation and its associated freezing and thawing procedures-short "freeze-thawing"-are among the final steps in economically viable manufacturing and clinical application of diverse cellular therapeutics. Translation from preclinical proof-of-concept studies to larger clinical trials has indicated that these processes may potentially present an Achilles heel to optimal cell product safety and particularly efficacy in clinical trials and routine use. Recent Findings: We review the current state of the literature on how cryopreservation of cellular therapies has evolved and how the application of this technique to different cell types is interlinked with their ability to engraft and function upon transfer in vivo, in particular for hematopoietic stem and progenitor cells (HSPCs), their progeny, and therapeutic cell products derived thereof. We also discuss pros and cons how this may differ for non-hematopoietic mesenchymal stromal/stem cell (MSC) therapeutics. We present different avenues that may be crucial for cell therapy optimization, both, for hematopoietic (e.g., effector, regulatory, and chimeric antigen receptor (CAR)-modified T and NK cell based products) and for non-hematopoietic products, such as MSCs and induced pluripotent stem cells (iPSCs), to achieve optimal viability, recovery, effective cell dose, and functionality of the cryorecovered cells. Summary: Targeted research into optimizing the cryopreservation and freeze-thawing routines and the adjunct manufacturing process design may provide crucial advantages to increase both the safety and efficacy of cellular therapeutics in clinical use and to enable effective market deployment strategies to become economically viable and sustainable medicines.

Clinical outcomes associated with guideline-discordant management of asymptomatic bacteriuria and urinary tract infection in hospitalized patients with neurogenic bladder.

Objective: To compare clinical outcomes associated with appropriate and inappropriate management of asymptomatic bacteriuria (ASB) and urinary tract infection (UTI) among inpatients with neurogenic bladder (NB). Design: Multicenter, retrospective cohort. Setting: The study was conducted across 4 Veterans' Affairs hospitals. Participants: The study included veterans with NB due to spinal cord injury or disorder (SCI/D), multiple sclerosis (MS), or Parkinson's disease (PD) hospitalized between January 1, 2017, and December 31, 2018, with diagnosis of ASB or UTI. Interventions: In a medical record review, we classified ASB and UTI diagnoses and treatments as appropriate or inappropriate based on national guidelines. Main outcome measures: Frequencies of Clostridioides difficile infection, acute kidney injury, 90-day hospital readmission, postculture length-of-stay (LOS), and multidrug-resistant organisms in subsequent urine cultures were compared between those who received appropriate and inappropriate management. Results: We included 170 encounters with ASB (30%) or UTI (70%) diagnoses occurring for 166 patients. Overall, 86.1% patients were male, 47.6% had SCI/D and 77.6% used bladder catheters. All ASB encounters had appropriate diagnoses, and 96.1% had appropriate treatment. In contrast, 37 UTI encounters (31.1%) had inappropriate diagnoses and 61 (51.3%) had inappropriate treatment, including 30 encounters with true ASB. Among patients with SCI/D or MS, appropriate ASB or UTI diagnosis was associated with a longer postculture LOS (median, 14 vs 7.5 days; P = .02). We did not detect any significant associations between appropriate versus inappropriate diagnosis and treatment and other outcomes. Conclusions: Almost one-third of UTI diagnoses and half of treatments in hospitalized patients with NB are inappropriate. Opportunities exist to improve ASB and UTI management in patients with NB to minimize inappropriate antibiotic use.

Entrainment of Network Activity by Closed-Loop Microstimulation in Healthy Ambulatory Rats.

As our understanding of volitional motor function increases, it is clear that complex movements are the result of the interactions of multiple cortical regions rather than just the output properties of primary motor cortex. However, our understanding of the interactions among these regions is limited. In this study, we used the activity-dependent stimulation (ADS) technique to determine the short/long-term effects on network activity and neuroplasticity of intracortical connections. ADS uses the intrinsic neural activity of one region to trigger stimulations in a separate region of the brain and can manipulate neuronal connectivity in vivo. Our aim was to compare single-unit neuronal activity within premotor cortex (rostral forelimb area, [RFA] in rats) in response to ADS (triggered from RFA) and randomly-generated stimulation in the somatosensory area (S1) within single sessions and across 21 consecutive days of stimulation. We examined firing rate and correlation between spikes and stimuli in chronically-implanted healthy ambulatory rats during spontaneous and evoked activity. At the end of the treatment, we evaluated changes of synaptophysin expression. Our results demonstrated the ability of ADS to modulate RFA firing properties and to promote synaptogenesis in S1, strengthening the idea that this Hebbian-inspired protocol can be used to modulate cortical connectivity.

Use of Machine Learning to Screen for Acute Respiratory Distress Syndrome Using Raw Ventilator Waveform Data.

To develop and characterize a machine learning algorithm to discriminate acute respiratory distress syndrome from other causes of respiratory failure using only ventilator waveform data. DESIGN: Retrospective, observational cohort study. SETTING: Academic medical center ICU. PATIENTS: Adults admitted to the ICU requiring invasive mechanical ventilation, including 50 patients with acute respiratory distress syndrome and 50 patients with primary indications for mechanical ventilation other than hypoxemic respiratory failure. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Pressure and flow time series data from mechanical ventilation during the first 24-hours after meeting acute respiratory distress syndrome criteria (or first 24-hr of mechanical ventilation for non-acute respiratory distress syndrome patients) were processed to extract nine physiologic features. A random forest machine learning algorithm was trained to discriminate between the patients with and without acute respiratory distress syndrome. Model performance was assessed using the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value. Analyses examined performance when the model was trained using data from the first 24 hours and tested using withheld data from either the first 24 hours (24/24 model) or 6 hours (24/6 model). Area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value were 0.88, 0.90, 0.71, 0.77, and 0.90 (24/24); and 0.89, 0.90, 0.75, 0.83, and 0.83 (24/6). CONCLUSIONS: Use of machine learning and physiologic information derived from raw ventilator waveform data may enable acute respiratory distress syndrome screening at early time points after intubation. This approach, combined with traditional diagnostic criteria, could improve timely acute respiratory distress syndrome recognition and enable automated clinical decision support, especially in settings with limited availability of conventional diagnostic tests and electronic health records.

Cause-specific mortality of type B aortic dissection and assessment of competing risks of mortality.

OBJECTIVE: Natural history studies of type B aortic dissection (TBAD) commonly report all-cause mortality. Our aim was to determine cause-specific mortality in TBAD and to evaluate the clinical characteristics associated with aorta-related and nonaorta-related mortality. METHODS: Clinical and administrative records were reviewed for patients with acute TBAD between 1995 and 2017. Demographics, comorbidities, presentation, and initial imaging findings were abstracted. Cause of death was ascertained through a multimodality approach using electronic health records, obituaries, social media, Social Security Death Index, and state mortality records. Causes of death were classified as aorta related, nonaorta related, or unknown. A Fine-Gray multivariate competing risk regression model for subdistribution hazard ratio was employed to analyze the association of clinical characteristics with aorta-related and nonaorta-related mortality. RESULTS: A total of 275 individuals met inclusion criteria (61.1 ± 13.7 years, 70.9% male, 68% white). Mean survival after discharge was 6.3 ± 4.7 years. Completeness of follow-up Clark C index was 0.87. All-cause mortality was 50.2% (n = 138; mean age, 70.1 ± 14.6 years) including an in-hospital mortality of 8.4%. Cause-specific mortality was aorta related, nonaorta related, and unknown in 51%, 43%, and 6%, respectively. Compared with patients with nonaorta-related mortality, patients with aorta-related mortality were younger at acute TBAD (69.5 ± 11.2 years vs 61.6 ± 15.5 years; P = .001), underwent more descending thoracic aortic repairs (19.4% vs 45.8%; P = .002), and had a shorter survival duration (5.7 ± 3.9 vs 3.4 ± 4.5 years; P = .002). There was clear variation in cause of death by each decade of life, with higher aorta-related mortality among those younger than 50 years and older than 70 years and a stepwise increase in nonaorta-related mortality with each increasing decade (P < .001). All-cause mortality at 1 year, 3 years, and 10 years was 15%, 24%, and 57%, respectively. After accounting for competing risks, the cumulative incidence of aorta-related mortality at 1 year, 3 years, and 10 years was 8.9%, 16.5%, and 27.2%, respectively, and that of nonaorta-related mortality was 2.7%, 7.2%, and 29%, respectively. A maximum descending thoracic aortic diameter >4 cm was associated with an increase in hazard of aorta-related mortality by 84% (subdistribution hazard ratio, 1.84; 95% confidence interval, 1.03-3.28) on multivariate competing risk regression analysis. CONCLUSIONS: TBAD is associated with high 10-year mortality. Those at risk for aorta-related mortality have a clinical phenotype different from that of individuals at risk for nonaorta-related mortality. This information is important for building risk prediction models that account for competing mortality risks and to direct optimal and individualized surgical and medical management of TBAD.

Novel tonometer device distinguishes brain stiffness in epilepsy surgery.

Complete surgical resection of abnormal brain tissue is the most important predictor of seizure freedom following surgery for cortical dysplasia. While lesional tissue is often visually indiscernible from normal brain, anecdotally, it is subjectively stiffer. We report the first experience of the use of a digital tonometer to understand the biomechanical properties of epilepsy tissue and to guide the conduct of epilepsy surgery. Consecutive epilepsy surgery patients (n = 24) from UCLA Mattel Children's Hospital were recruited to undergo intraoperative brain tonometry at the time of open craniotomy for epilepsy surgery. Brain stiffness measurements were corrected with abnormalities on neuroimaging and histopathology using mixed-effects multivariable linear regression. We collected 249 measurements across 30 operations involving 24 patients through the pediatric epilepsy surgery program at UCLA Mattel Children's Hospital. On multivariable mixed-effects regression, brain stiffness was significantly associated with the presence of MRI lesion (ß = 32.3, 95%CI 16.3-48.2; p < 0.001), severity of cortical disorganization (ß = 19.8, 95%CI 9.4-30.2; p = 0.001), and recent subdural grid implantation (ß = 42.8, 95%CI 11.8-73.8; p = 0.009). Brain tonometry offers the potential of real-time intraoperative feedback to identify abnormal brain tissue with millimeter spatial resolution. We present the first experience with this novel intraoperative tool for the conduct of epilepsy surgery. A carefully designed prospective study is required to elucidate whether the clinical application of brain tonometry during resective procedures could guide the area of resection and improve seizure outcomes.

Scalp EEG interictal high frequency oscillations as an objective biomarker of infantile spasms.

OBJECTIVE: To investigate the diagnostic utility of high frequency oscillations (HFOs) via scalp electroencephalogram (EEG) in infantile spasms. METHODS: We retrospectively analyzed interictal slow-wave sleep EEGs sampled at 2,000 Hz recorded from 30 consecutive patients who were suspected of having infantile spasms. We measured the rate of HFOs (80-500 Hz) and the strength of the cross-frequency coupling between HFOs and slow-wave activity (SWA) at 3-4 Hz and 0.5-1 Hz as quantified with modulation indices (MIs). RESULTS: Twenty-three patients (77%) exhibited active spasms during the overnight EEG recording. Although the HFOs were detected in all children, increased HFO rate and MIs correlated with the presence of active spasms (p < 0.001 by HFO rate; p < 0.01 by MIs at 3-4 Hz; p = 0.02 by MIs at 0.5-1 Hz). The presence of active spasms was predicted by the logistic regression models incorporating HFO-related metrics (AUC: 0.80-0.98) better than that incorporating hypsarrhythmia (AUC: 0.61). The predictive performance of the best model remained favorable (87.5% accuracy) after a cross-validation procedure. CONCLUSIONS: Increased rate of HFOs and coupling between HFOs and SWA are associated with active epileptic spasms. SIGNIFICANCE: Scalp-recorded HFOs may serve as an objective EEG biomarker for active epileptic spasms.

Color Space Transformation-Based Algorithm for Evaluation of Thermochromic Behavior of Cholesteric Liquid Crystals Using Polarized Light Microscopy.

Cholesteryl ester liquid crystals exhibit thermochromic properties related to the existence of a twisted nematic phase. When used in applications such as thermal mapping, a color change is often monitored by video cameras. Thus, quantitative methods to evaluate thermochromic behavior (e.g., blue-start, red-start, red-end, color play and bandwidth) from video analysis are desirable. However, obtaining quantitative color measurements from digital images remains a significant technical challenge, especially for highly reflective samples such as liquid crystals (for which ultraviolet-visible (UV-vis) reflectance spectroscopy is typically used). We developed a method to determine thermochromic properties from videos of liquid crystal cooling under polarized light microscopy. We relate observed color transitions to quantifiable changes in the cumulative color difference in the International Commission on Illumination (CIE) L*a*b* color space and validate this method with UV-vis reflectance spectroscopy. The measured thermochromic behavior and associated measurement uncertainties (coefficient of variations) were comparable to UV-vis reflectance measurements.

Thermochromic Fibers via Electrospinning.

Cholesteryl ester liquid crystals exhibit thermochromic properties related to the existence of a twisted nematic phase. We formulate ternary mixtures of cholesteryl benzoate (CB), cholesteryl pelargonate (CP), and cholesteryl oleyl carbonate (COC) to achieve thermochromic behavior. We aim to achieve thermochromic fibers by incorporating the liquid crystal formulations into electrospun fibers. Two methods of incorporating the liquid crystal (LC) are compared: (1) blend electrospinning and (2) coaxial electrospinning using the same solvent system for the liquid crystal. For blend electrospinning, intermolecular interactions seem to be important in facilitating fiber formation since addition of LC can suppress bead formation. Coaxial electrospinning produces fibers with higher nominal fiber production rates (g/hr) and with higher nominal LC content in the fiber (wt. LC/wt. polymer assuming all of the solvent evaporates) but larger fiber size distributions as quantified by the coefficient of variation in fiber diameter than blend electrospinning with a single nozzle. Importantly, our proof-of-concept experiments demonstrate that coaxially electrospinning with LC and solvent in the core preserves the thermochromic properties of the LC so that thermochromic fibers are achieved.

Effects of Patent Ductus Arteriosus on Organ Blood Flow in Infants Born Very Preterm: A Prospective Study with Serial Echocardiography.

OBJECTIVE: To characterize the effects of a patent ductus arteriosus (PDA) on different organ blood flows in infants born preterm. STUDY DESIGN: Infants born preterm at ≤30 weeks of gestational age had daily echocardiography and Doppler assessments of middle cerebral artery, celiac artery, superior mesenteric (SMA), and renal arteries (RA) during the first postnatal week. Abnormal organ blood flow was defined as either reverse or absent diastolic flow, abnormally low mean or systolic velocities, or abnormally high pulsatility or resistance index. RESULTS: Twenty-five infants born very preterm (gestational age 27.0 ± 2.1 weeks) were enrolled. PDA presence at time of measurement increased the risk of abnormal organ blood flows (39% vs 8%, P < .001). Ductal diameter and left atrium-to-aortic root (LA/Ao) ratio correlated positively with resistance index (celiac artery, SMA, RA), and negatively with mean velocity (ductal diameter: SMA, RA; LA/Ao ratio: RA). A PDA >2.0 mm, LA/Ao ratio >1.4, and their combination were associated with 8.0 (95% CI 1.6-39.4)-, 6.7 (1.3-34.7)-, and 38.2 (3.2-455.5)-fold increase in risk of abnormal organ blood flow index, respectively. Abnormal descending aorta flow was detected in only 2% of measurements. CONCLUSIONS: Ductal size >2.0 mm and LA/Ao >1.4, especially in combination, are associated with a greater risk of abnormal organ blood flows. We suggest that Doppler assessment of the renal and superior mesenteric arteries are more likely to detect systemic hypoperfusion than the descending aorta.

Introducing a nursing maintenance bundle for patients with pulmonary arterial catheters.

We undertook a quality improvement project to address challenges with pulmonary artery catheter (PAC) line maintenance in a setting of low-baseline central-line infection rates. We observed a subsequent reduction in Staphylococcal PAC line infections and a trend toward a reduction in overall PAC infection rates over 1 year.

Prospective observational study: Fast ripple localization delineates the epileptogenic zone.

OBJECTIVE: To investigate spatial correlation between interictal HFOs and neuroimaging abnormalities, and to determine if complete removal of prospectively identified interictal HFOs correlates with post-surgical seizure-freedom. METHODS: Interictal fast ripples (FRs: 250-500 Hz) in 19 consecutive children with pharmacoresistant focal epilepsy who underwent extra-operative electrocorticography (ECoG) recording were prospectively analyzed. The interictal FRs were sampled at 2000 Hz and were visually identified during 10 min of slow wave sleep. Interictal FRs, MRI and FDG-PET were delineated on patient-specific reconstructed three-dimensional brain MRI. RESULTS: Interictal FRs were observed in all patients except one. Thirteen out of 18 patients (72%) exhibited FRs beyond the extent of neuroimaging abnormalities. Fifteen of 19 children underwent resective surgery, and survival analysis with log-rank test demonstrated that complete resection of cortical sites showing interictal FRs correlated with longer post-operative seizure-freedom (p < 0.01). Complete resection of seizure onset zones (SOZ) also correlated with longer post-operative seizure-freedom (p = 0.01), yet complete resection of neuroimaging abnormalities did not (p = 0.43). CONCLUSIONS: Prospective visual analysis of interictal FRs was feasible, and it seemed to accurately localize epileptogenic zones. SIGNIFICANCE: Topological extent of epileptogenic region may exceed what is discernible by multimodal neuroimaging.

Improving Mechanical Ventilator Clinical Decision Support Systems with a Machine Learning Classifier for Determining Ventilator Mode.

Clinical decision support systems (CDSS) will play increasing role in improving quality of medical care for critically ill patients. However, due to limitations in current informatics infrastructure, CDSS do not always have complete information on state of supporting physiologic monitoring devices, which can limit input data available to CDSS. This is especially true in use case of mechanical ventilation (MV), where current CDSS have no knowledge of critical ventilation settings, such as ventilation mode. To enable MV CDSS make accurate recommendations related to ventilator mode, we developed a highly performant machine learning model that is able to perform per-breath classification of five of most widely used ventilation modes in USA with average F1-score of 97.52%. We also show how our approach makes methodologic improvements over previous work and is highly robust to missing data caused by software/sensor error.