Practical applications of three-dimensional printing for process improvement in the cytopathology laboratory.

With the increased availability of three-dimensional (3D) printers, innovative teaching and training materials have been created in medical fields. For pathology, the use of 3D printing has been largely limited to anatomic representations of disease processes or the development of supplies during the coronavirus disease 2019 pandemic. Herein, an institution's 3D printing laboratory and staff with expertise in additive manufacturing illustrate how this can address design issues in cytopathology specimen collection and processing. The authors' institutional 3D printing laboratory, along with students and trainees, used computer-aided design and 3D printers to iterate on design, create prototypes, and generate final usable materials using additive manufacturing. The program Microsoft Forms was used to solicit qualitative and quantitative feedback. The 3D-printed models were created to assist with cytopreparation, rapid on-site evaluation, and storage of materials in the preanalytical phase of processing. These parts provided better organization of materials for cytology specimen collection and staining, in addition to optimizing storage of specimens with multiple sized containers to optimize patient safety. The apparatus also allowed liquids to be stabilized in transport and removed faster at the time of rapid on-site evaluation. Rectangular boxes were also created to optimally organize all components of a specimen in cytopreparation to simplify and expedite the processes of accessioning and processing, which can minimize errors. These practical applications of 3D printing in the cytopathology laboratory demonstrate the utility of the design and printing process on improving aspects of the workflow in cytopathology laboratories to maximize efficiency, organization, and patient safety.

The State of Machine Learning in Spine Surgery: A Systematic Review.

STUDY DESIGN: This was a systematic review of existing literature. OBJECTIVE: The objective of this study was to evaluate the current state-of-the-art trends and utilization of machine learning in the field of spine surgery. SUMMARY OF BACKGROUND DATA: The past decade has seen a rise in the clinical use of machine learning in many fields including diagnostic radiology and oncology. While studies have been performed that specifically pertain to spinal surgery, there have been relatively few aggregate reviews of the existing scientific literature as applied to clinical spine surgery. METHODS: This study utilized Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to review the scientific literature from 2009 to 2019 with syntax specific for machine learning and spine surgery applications. Specific data was extracted from the available literature including algorithm application, algorithms tested, database type and size, algorithm training method, and outcome of interest. RESULTS: A total of 44 studies met inclusion criteria, of which the majority were level III evidence. Studies were grouped into 4 general types: diagnostic tools, clinical outcome prediction, surgical assessment tools, and decision support tools. Across studies, a wide swath of algorithms were used, which were trained across multiple disparate databases. There were no studies identified that assessed the ethical implementation or patient perceptions of machine learning in clinical care. CONCLUSIONS: The results reveal the broad range of clinical applications and methods used to create machine learning algorithms for use in the field of spine surgery. Notable disparities exist in algorithm choice, database characteristics, and training methods. Ongoing research is needed to make machine learning operational on a large scale.

Deep-learning-assisted analysis of echocardiographic videos improves predictions of all-cause mortality.

Machine learning promises to assist physicians with predictions of mortality and of other future clinical events by learning complex patterns from historical data, such as longitudinal electronic health records. Here we show that a convolutional neural network trained on raw pixel data in 812,278 echocardiographic videos from 34,362 individuals provides superior predictions of one-year all-cause mortality. The model's predictions outperformed the widely used pooled cohort equations, the Seattle Heart Failure score (measured in an independent dataset of 2,404 patients with heart failure who underwent 3,384 echocardiograms), and a machine learning model involving 58 human-derived variables from echocardiograms and 100 clinical variables derived from electronic health records. We also show that cardiologists assisted by the model substantially improved the sensitivity of their predictions of one-year all-cause mortality by 13% while maintaining prediction specificity. Large unstructured datasets may enable deep learning to improve a wide range of clinical prediction models.

Computational simulation to assess patient safety of uncompensated COVID-19 two-patient ventilator sharing using the Pulse Physiology Engine.

BACKGROUND: The COVID-19 pandemic is stretching medical resources internationally, sometimes creating ventilator shortages that complicate clinical and ethical situations. The possibility of needing to ventilate multiple patients with a single ventilator raises patient health and safety concerns in addition to clinical conditions needing treatment. Wherever ventilators are employed, additional tubing and splitting adaptors may be available. Adjustable flow-compensating resistance for differences in lung compliance on individual limbs may not be readily implementable. By exploring a number and range of possible contributing factors using computational simulation without risk of patient harm, this paper attempts to define useful bounds for ventilation parameters when compensatory resistance in limbs of a shared breathing circuit is not possible. This desperate approach to shared ventilation support would be a last resort when alternatives have been exhausted. METHODS: A whole-body computational physiology model (using lumped parameters) was used to simulate each patient being ventilated. The primary model of a single patient with a dedicated ventilator was augmented to model two patients sharing a single ventilator. In addition to lung mechanics or estimation of CO2 and pH expected for set ventilation parameters (considerations of lung physiology alone), full physiological simulation provides estimates of additional values for oxyhemoglobin saturation, arterial oxygen tension, and other patient parameters. A range of ventilator settings and patient characteristics were simulated for paired patients. FINDINGS: To be useful for clinicians, attention has been directed to clinically available parameters. These simulations show patient outcome during multi-patient ventilation is most closely correlated to lung compliance, oxygenation index, oxygen saturation index, and end-tidal carbon dioxide of individual patients. The simulated patient outcome metrics were satisfactory when the lung compliance difference between two patients was less than 12 mL/cmH2O, and the oxygen saturation index difference was less than 2 mmHg. INTERPRETATION: In resource-limited regions of the world, the COVID-19 pandemic will result in equipment shortages. While single-patient ventilation is preferable, if that option is unavailable and ventilator sharing using limbs without flow resistance compensation is the only available alternative, these simulations provide a conceptual framework and guidelines for clinical patient selection.

Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network.

The electrocardiogram (ECG) is a widely used medical test, consisting of voltage versus time traces collected from surface recordings over the heart1. Here we hypothesized that a deep neural network (DNN) can predict an important future clinical event, 1-year all-cause mortality, from ECG voltage-time traces. By using ECGs collected over a 34-year period in a large regional health system, we trained a DNN with 1,169,662 12-lead resting ECGs obtained from 253,397 patients, in which 99,371 events occurred. The model achieved an area under the curve (AUC) of 0.88 on a held-out test set of 168,914 patients, in which 14,207 events occurred. Even within the large subset of patients (n = 45,285) with ECGs interpreted as 'normal' by a physician, the performance of the model in predicting 1-year mortality remained high (AUC = 0.85). A blinded survey of cardiologists demonstrated that many of the discriminating features of these normal ECGs were not apparent to expert reviewers. Finally, a Cox proportional-hazard model revealed a hazard ratio of 9.5 (P < 0.005) for the two predicted groups (dead versus alive 1 year after ECG) over a 25-year follow-up period. These results show that deep learning can add substantial prognostic information to the interpretation of 12-lead resting ECGs, even in cases that are interpreted as normal by physicians.

Feasibility of blood testing combined with PET-CT to screen for cancer and guide intervention.

Cancer treatments are often more successful when the disease is detected early. We evaluated the feasibility and safety of multicancer blood testing coupled with positron emission tomography-computed tomography (PET-CT) imaging to detect cancer in a prospective, interventional study of 10,006 women not previously known to have cancer. Positive blood tests were independently confirmed by a diagnostic PET-CT, which also localized the cancer. Twenty-six cancers were detected by blood testing. Of these, 15 underwent PET-CT imaging and nine (60%) were surgically excised. Twenty-four additional cancers were detected by standard-of-care screening and 46 by neither approach. One percent of participants underwent PET-CT imaging based on false-positive blood tests, and 0.22% underwent a futile invasive diagnostic procedure. These data demonstrate that multicancer blood testing combined with PET-CT can be safely incorporated into routine clinical care, in some cases leading to surgery with intent to cure.

Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration.

Intracranial hemorrhage (ICH) requires prompt diagnosis to optimize patient outcomes. We hypothesized that machine learning algorithms could automatically analyze computed tomography (CT) of the head, prioritize radiology worklists and reduce time to diagnosis of ICH. 46,583 head CTs (~2 million images) acquired from 2007-2017 were collected from several facilities across Geisinger. A deep convolutional neural network was trained on 37,074 studies and subsequently evaluated on 9499 unseen studies. The predictive model was implemented prospectively for 3 months to re-prioritize "routine" head CT studies as "stat" on realtime radiology worklists if an ICH was detected. Time to diagnosis was compared between the re-prioritized "stat" and "routine" studies. A neuroradiologist blinded to the study reviewed false positive studies to determine whether the dictating radiologist overlooked ICH. The model achieved an area under the ROC curve of 0.846 (0.837-0.856). During implementation, 94 of 347 "routine" studies were re-prioritized to "stat", and 60/94 had ICH identified by the radiologist. Five new cases of ICH were identified, and median time to diagnosis was significantly reduced (p < 0.0001) from 512 to 19 min. In particular, one outpatient with vague symptoms on anti-coagulation was found to have an ICH which was treated promptly with reversal of anticoagulation, resulting in a good clinical outcome. Of the 34 false positives, the blinded over-reader identified four probable ICH cases overlooked in original interpretation. In conclusion, an artificial intelligence algorithm can prioritize radiology worklists to reduce time to diagnosis of new outpatient ICH by 96% and may also identify subtle ICH overlooked by radiologists. This demonstrates the positive impact of advanced machine learning in radiology workflow optimization.

Bariatric Left Gastric Artery Embolization for the Treatment of Obesity: A Review of Gut Hormone Involvement in Energy Homeostasis.

OBJECTIVE: The global population is becoming more overweight and obese, leading to increases in associated morbidity and mortality rates. Advances in catheter-directed embolotherapy offer the potential for the interventional radiologist to make a contribution to weight loss. Left gastric artery embolization reduces the supply of blood to the gastric fundus and decreases serum levels of ghrelin. Early evidence suggests that this alteration in gut hormone balance leads to changes in energy homeostasis and weight reduction. The pathophysiologic findings and current evidence associated with the use of left gastric artery embolization are reviewed. CONCLUSION: The prevalence of obesity continues to increase at an alarming rate, and, thus far, advances in medical management have been relatively ineffective in slowing this trend. Lifestyle modifications such as diet and exercise are effective initially, but most patients regain the weight in the long term. Bariatric surgery is the most effective strategy for achieving long-term weight loss; however, as with all surgical procedures, it has potential complications.

Triple-lumen peripherally inserted central catheter in patients in the critical care unit: prospective evaluation.

PURPOSE: To prospectively evaluate outcomes associated with use of a triple-lumen (TL) peripherally inserted central catheter (PICC) in the intensive care unit (ICU) setting. MATERIALS AND METHODS: Patients were prospectively enrolled in this HIPAA-compliant, institutional review board-approved study. Informed consent was obtained. All patients were in one hospital's ICUs and needed intermediate-term central venous access requiring three lumina. A 6-F tapered TL PICC was placed by a bedside nursing-based team with backup from the Interventional Radiology department. Placement complications, as well as long-term complications, were recorded. At catheter removal, ultrasonography (US) of the veins containing the TL PICC was performed to detect occult venous thrombosis. Regardless of indication for removal, catheters were sent for culture to detect colonization. RESULTS: The study was stopped prematurely after 50 of a planned 167 patients were enrolled when a scheduled interim analysis detected a venous thrombosis rate that was considered unacceptably high by the study oversight committee (thrombosis was symptomatic in 20% of patients [10 of 50]). Venous thrombosis (symptomatic or asymptomatic) was detected in 26 of 45 patients (58%; 95% confidence interval [CI]: 43%, 72%) examined with US. Documented catheter-related bloodstream infection did not occur (0%; 95% CI: 0%, 7%); colonization was detected in three of 29 catheter tips sent for culture (10%; 95% CI: 2%, 27%). Catheter malfunction and dislodgment occurred in one patient each. CONCLUSION: The TL PICC design used in this study resulted in unacceptably high venous thrombosis rates. Even when used in a high-risk setting for infection (ie, the ICU), rates of clinically evident infection and colonization were absent and low, respectively.

Drainage of collections associated with hernia mesh: is it worthwhile?

PURPOSE: Synthetic mesh has revolutionized abdominal wall hernia repair. However, mesh infections present a clinical problem because the standard practice of surgical excision is fraught with increased morbidity. Here, single-institutional outcomes in managing mesh-related collections via percutaneous drainage are retrospectively reviewed to assess its effectiveness. MATERIALS AND METHODS: A total of 21 patients underwent drainage of perimesh collections. Three types of mesh were employed: polytetrafluoroethylene (PTFE; n = 5), polypropylene (n = 14), and porcine dermal collagen (n = 3). One patient received both polypropylene and PTFE. Drainage was performed with ultrasound guidance (n = 19) or surgical drain exchange (n = 2). Mesh type, culture results, fluid collection size, and location were analyzed with respect to need for mesh excision. RESULTS: Sixteen of 21 patients (76%) were successfully treated with drainage. One required additional surgical capsulectomy; the mesh was salvaged. Four required mesh excision because of recurrent infection (n = 2) or lack of improvement of clinical course (n = 2). Recurrent infection occurred in six patients, with mesh salvage via conservative management or new drainage in four. Fluid cultures were positive in 68% of patients (n = 13), with Staphylococcus aureus the most common organism. Cultures did not predict mesh excision (P = .26). The PTFE excision rate trended higher compared with polypropylene (40% vs 14%; P = .27). No porcine dermal collagen mesh was excised. Neither fluid collection size nor location predicted mesh excision. Mean follow-up was 319 days (range, 6-1,406 d). CONCLUSIONS: Percutaneous drainage of suspected mesh-related abscess is effective. The use of PTFE mesh trended toward a higher excision rate.

Short-term infection in cuffed versus noncuffed small bore central catheters: a randomized trial.

PURPOSE: To determine if a polyester cuff offered benefit in jugular small-bore central catheters (SBCCs). MATERIALS AND METHODS: Eighty-four patients were randomly assigned to receive a 5-F single- or 6-F dual-lumen SBCC with (n = 42) or without (n = 42) a polyester cuff. Follow-up was performed at 2 weeks, 1 month, and 3 months or at catheter removal, whichever came first. At scheduled follow-up, catheter function, patient satisfaction, and infection were determined. At catheter removal, tip culture was performed to determine colonization and jugular vein patency was determined with ultrasonography (US). RESULTS: The overall infection rate was 0.4 per 1,000 catheter days. There was one clinical infection (noncuffed catheter). Colonization occurred in two noncuffed catheters and one cuffed catheter. There was one catheter dislodgment in the noncuffed group and none in the cuffed group. Cuffed catheters were no more difficult to insert but took slightly longer to remove (6 minutes +/- 4.7 vs 5 minutes +/- 3, P = .39) and often required local anesthesia for removal, whereas noncuffed catheters did not (41% vs 0%, P = .001). Partial (two cuffed, 0 noncuffed) or complete (two cuffed, one noncuffed) jugular thrombosis was seen on five of 58 completion US studies (8.6%). CONCLUSIONS: A polyester cuff on a SBCC confers no significant benefit in short-term colonization rates. Infection in SBCCs is uncommon. Despite their small diameters, SBCCs can result in jugular thrombosis, an important consideration in any patient requiring long-term venous access.

The case for primary placement of tunneled hemodialysis catheters in acute kidney injury.

PURPOSE: Nontunneled hemodialysis catheters (NTDCs) are widely used for initial hemodialysis access in new-onset renal failure. The National Kidney Foundation recommends NTDC use for hemodialysis duration of less than 1 week in acute kidney injury because of the increased infection risk compared with tunneled hemodialysis catheters (TDCs) with longer use. The present study was performed to determine whether primary placement of TDCs in this setting is more appropriate, and whether there are predictors of recovery of renal function in less than 1 week. MATERIALS AND METHODS: In the authors' practice, patients referred to the interventional radiology unit in whom no contraindications exist receive a TDC; 76 patients who received a primary TDC for acute kidney injury and who eventually recovered renal function were retrospectively reviewed herein. Causes of renal failure, various renal function parameters, and demographics were collected, as were TDC dwell times, in an effort to determine predictors of recovery and/or extended duration of use. RESULTS: Mean TDC dwell time in patients who eventually recovered from acute kidney injury was 34 days; only 15 of 76 (20%) recovered within 1 week. At TDC placement, there were no significant differences between patients who recovered in less than (vs greater than) 1 week. CONCLUSIONS: The present results support primary placement of TDCs in patients with acute kidney injury who require hemodialysis and in whom no contraindications exist, as no predictors of recovery of renal function in less than 1 week were identified.

Incidence and management of percutaneous transluminal angioplasty-induced venous rupture in the "fistula first" era.

PURPOSE: Percutaneous transluminal angioplasty (PTA)-induced venous rupture is a common complication of hemodialysis access interventions. The authors sought to determine if venous rupture rates and management differed between grafts and fistulas, and in the fistula subset, between transposed and nontransposed fistulas. MATERIALS AND METHODS: Patients experiencing venous rupture during hemodialysis PTA over a 5-year period were identified. Of 1,985 hemodialysis interventions, 75 ruptures occurred in 69 patients (46 women) with a mean age of 63 years (range, 31-88 y). Rupture rates, proportion of successful treatments, and treatment type and number (ie, balloon tamponade, stent, covered stent) were determined. RESULTS: Rupture was more common in fistulas overall (5.6%, 39 of 693) compared with grafts (2.8%, 36 of 1,292; P = .002), in transposed (10.7%, 20 of 187) compared with nontransposed fistulas (3.8%, 19 of 506; P = .001), and in transposed fistulas compared with grafts (P = .0001). There was no significant difference between nontransposed fistulas and grafts. Treatment success (ie, resolution of extravasation) was the same among groups: 69% (27 of 39) in fistulas overall, 70% (14 of 20) in transposed fistulas, 68% (13 of 19) in nontransposed fistulas, and 72% (26 of 36) in grafts. There was a greater need for stents in grafts (38.9%, 14 of 36) compared with fistulas (12.8%, five of 39; P = .003). CONCLUSIONS: PTA-induced rupture is more common in fistulas than grafts, and this effect seems nearly entirely driven by transposed fistulas. Although rupture treatment in fistulas of all types yielded similar success to grafts, and graft ruptures were more difficult to treat than fistula ruptures, the high rupture rates in transposed fistulas attest to the increased difficulty of treating this subset of fistulas.

Preoperative mapping venography in patients who require hemodialysis access: imaging findings and contribution to management.

PURPOSE: To analyze the use of preoperative venographic mapping in patients who require permanent hemodialysis access. MATERIALS AND METHODS: Ninety-one patients underwent 108 preoperative studies. Sixty-eight (75%) were documented to have ongoing or previous hemodialysis at the time of the study. A total of 154 arms were assessed with venograms (75 right, 79 left); 74 of the patients (81%) had previous access. Venographic mapping was not performed in patients with clearly usable veins as determined by the referring surgeon. RESULTS: A total of 170 veins were suitable for access creation (ie, continuous vein of suitable caliber). Of these, 78 were used (40 fistulas [51%] and 38 grafts [49%]), and 87% of accesses were successfully used for dialysis (73% primarily, 14% after additional intervention). Anatomic variants included early brachial-basilic confluence (44%), double terminal cephalic arch (4%), and brachial-basilic "ladders" (7%). Significant central venous stenosis was found in 10% of studies, limiting the ability to use the affected side for access. There were significant associations between (i) the number of previous accesses and access type created (P = .002, Fisher exact test) and (ii) the number of veins visualized and access type created (P < .001, Fisher exact test). A greater number of previous access attempts correlated with graft rather than fistula placement for permanent access, and increased numbers of veins seen on venography correlated with an increased chance of permanent access placement. CONCLUSIONS: Venography may identify clinically occult veins usable for hemodialysis access. Anatomic variants are common and may affect choice of access site.

Large or small bore, push or pull: a comparison of three classes of percutaneous fluoroscopic gastrostomy catheters.

PURPOSE: To compare the tube performance and complication rates of small-bore, large-bore push-type, and large-bore pull-type gastrostomy catheters. MATERIALS AND METHODS: A total of 160 patients (74 men, 86 women; mean age, 66.9 years, range, 22-95 y) underwent percutaneous fluoroscopic gastrostomy placement between January 2004 and March 2006. Choice of catheter was based on the preference of the attending radiologist. Data were collected retrospectively with institutional review board approval. Radiology reports provided information on the catheter, indication for gastrostomy, technical success, and immediate outcome. Chart review provided data on medical history, postprocedural complications, progress to feeding goal, and clinical outcomes. Statistical analysis was performed to compare the three classes of gastrostomy catheters. RESULTS: All 160 catheters were placed successfully. Patients who received small-bore catheters (14 F; n = 88) had significantly more tube complications (17% vs 5.6%) and were less likely to meet their feeding goal (P = .035) compared with patients with large-bore catheters (20 F; n = 72). No difference was observed in terms of major or minor complications. Large-bore push-type (n = 14) and pull-type catheters (n = 58) were similar in terms of complication rates. Patients who received large-bore push-type catheters achieved their feeding goals in significantly less time than those with large-bore pull-type catheters (average, 3.8 days vs 6.0 days; P = .04). CONCLUSIONS: Patients who received small-bore gastrostomy catheters are significantly more prone to tube dysfunction. Large-bore catheters should be preferentially used, with push-type catheters performing better with regard to the time to achieve feeding goal.

Tunneled infusion catheter breakage: frequency and repair kit outcomes.

PURPOSE: To determine the frequency of tunneled infusion catheter breakage and the durability of a repair kit used to repair damage to the external catheter segment, avoiding catheter replacement. MATERIALS AND METHODS: With use of a quality assurance database, 724 silicone tunneled infusion catheters placed between July 2002 and September 2005 were identified. The repair kit outcomes portion of the study focused on 10-F triple-lumen catheters (n = 433), the type placed most frequently in our practice and that with the most repairs available for analysis. To compare durability, nonrepaired catheters and those requiring repair were compared by using Cox proportion hazard regression. RESULTS: Breakage occurred in 53 of 443 (12%) 10-F triple-lumen catheters, three of 64 (5%) 10-F dual-lumen catheters, four of 159 (3%) 11-F triple-lumen catheters, four of 12 (33%) 9.6-F single-lumen catheters, and eight of 56 (14%) 9-F double-lumen catheters. In the 10-F subset, the mean time to catheter breakage was 60 days. The mean catheter days for the nonrepaired group (143 days) and the repaired group (145 days) were not significantly different (chi2, 0.071; hazard ratio, 1.07; P = .79). Mean catheter dwell after repair was 79 days. The failure rate for the repair kit was 14% (seven of 51 attempts). CONCLUSIONS: Tunneled infusion catheter breakage is common. Given the high breakage rates observed for many catheter designs, the development of more durable catheters should be a priority for catheter manufacturers. Until more durable catheters are developed, the catheter repair kit studied is an easy, effective, durable, and relatively inexpensive solution for the repair of external segment damage in tunneled infusion catheters.

Comparison of physician-rated performance characteristics of hydrophilic-coated guide wires.

PURPOSE: The present study was undertaken to determine whether hydrophilic-coated guide wires differed significantly according to physician-rated performance. MATERIALS AND METHODS: In this single-blinded, randomized prospective trial, three standard-shaft, 3-cm, angled-tip hydrophilic-coated guide wires were compared: the ZIPwire, HiWire, and Glidewire. Physicians rated performance characteristics on a five-point scale. RESULTS: The Glidewire had significantly greater physician-rated tip radiopacity (3.3 +/- 0.5 vs. 3.0 +/- 0.6; P = .04), wire radiopacity (3.3 +/- 0.5 vs. 3.0 +/- 0.6; P = .04), and "lubricity" (3.3 +/- 0.6 vs. 2.6 +/- 1.0; P < .01) compared with the ZIPwire. The HiWire and Glidewire did not differ significantly in any of these characteristics. Compared with the ZIPwire (2.4 +/- 1.2), the HiWire (3.0 +/- 0.7; P = .02) and Glidewire (3.2 +/- 0.6; P < .01) had significantly higher-rated lubricity retention. There were no differences in torque response, ability to navigate tortuous vessels, or tip shape retention among the three devices. The Glidewire received a significantly higher rating for overall balance of properties (3.3 +/- 0.6) compared with the HiWire (3.0 +/- 0.7; P = .01) and ZIPwire (2.7 +/- 0.8; P < .01). Overall, operators stated that the Glidewire met their expectations in 95.0% of cases compared with 75.0% for the HiWire (P < .01) and 62.5% for the ZIPwire (P < .01). CONCLUSIONS: In addition to the highest-rated overall balance of properties, the Glidewire had significantly higher-rated lubricity and radiopacity characteristics compared with the ZIPwire.