Evaluating and mitigating bias in machine learning models for cardiovascular disease prediction.

OBJECTIVE: The study aims to investigate whether machine learning-based predictive models for cardiovascular disease (CVD) risk assessment show equivalent performance across demographic groups (such as race and gender) and if bias mitigation methods can reduce any bias present in the models. This is important as systematic bias may be introduced when collecting and preprocessing health data, which could affect the performance of the models on certain demographic sub-cohorts. The study is to investigate this using electronic health records data and various machine learning models. METHODS: The study used large de-identified Electronic Health Records data from Vanderbilt University Medical Center. Machine learning (ML) algorithms including logistic regression, random forest, gradient-boosting trees, and long short-term memory were applied to build multiple predictive models. Model bias and fairness were evaluated using equal opportunity difference (EOD, 0 indicates fairness) and disparate impact (DI, 1 indicates fairness). In our study, we also evaluated the fairness of a non-ML baseline model, the American Heart Association (AHA) Pooled Cohort Risk Equations (PCEs). Moreover, we compared the performance of three different de-biasing methods: removing protected attributes (e.g., race and gender), resampling the imbalanced training dataset by sample size, and resampling by the proportion of people with CVD outcomes. RESULTS: The study cohort included 109,490 individuals (mean [SD] age 47.4 [14.7] years; 64.5% female; 86.3% White; 13.7% Black). The experimental results suggested that most ML models had smaller EOD and DI than PCEs. For ML models, the mean EOD ranged from -0.001 to 0.018 and the mean DI ranged from 1.037 to 1.094 across race groups. There was a larger EOD and DI across gender groups, with EOD ranging from 0.131 to 0.136 and DI ranging from 1.535 to 1.587. For debiasing methods, removing protected attributes didn't significantly reduced the bias for most ML models. Resampling by sample size also didn't consistently decrease bias. Resampling by case proportion reduced the EOD and DI for gender groups but slightly reduced accuracy in many cases. CONCLUSIONS: Among the VUMC cohort, both PCEs and ML models were biased against women, suggesting the need to investigate and correct gender disparities in CVD risk prediction. Resampling by proportion reduced the bias for gender groups but not for race groups.

Glacial isostatic adjustment: physical models and observational constraints.

By far the most prescient insights into the interior structure of the planet have been provided on the basis of elastic wave seismology. Analysis of the travel times of shear or compression wave phases excited by individual earthquakes, or through analysis of the elastic gravitational free oscillations that individual earthquakes of sufficiently large magnitude may excite, has been the central focus of Earth physics research for more than a century. Unfortunately, data provide no information that is directly relevant to understanding the solid state 'flow' of the polycrystalline outer 'mantle' shell of the planet that is involved in the thermally driven convective circulation that is responsible for powering the 'drift' of the continents and which controls the rate of planetary cooling on long timescales. For this reason, there has been an increasing focus on the understanding of physical phenomenology that is unambiguously associated with mantle flow processes that are distinct from those directly associated with the convective circulation itself. This paper reviews the past many decades of work that has been invested in understanding the most important of such processes, namely that which has come to be referred to as 'glacial isostatic adjustment' (GIA). This process concerns the response of the planet to the loading and unloading of the high latitude continents by the massive accumulations of glacial ice that have occurred with almost metronomic regularity over the most recent million years of Earth history. Forced by the impact of gravitationaln-body effects on the geometry of Earth's orbit around the Sun through the impact upon the terrestrial regime of received solar insolation, these surface mass loads on the continents have left indelible records of their occurrence in the 'Earth system' consisting of the oceans, continents, and the great polar ice sheets on Greenland and Antarctica themselves. Although this ice-age phenomenology has been clearly recognized since early in the last century, it was for over 50 years considered to be no more than an interesting curiosity, the understanding of which remained on the periphery of the theoretical physics of the Earth. This was the case in part because no globally applicable theory was available that could be applied to rigorously interpret the observations. Equally important to understanding the scientific lethargy that held back the understanding of this phenomenon involving mantle flow processes was the lack of appreciation of the wide range of observations that were in fact related to GIA physics. This paper is devoted to a review of the global theories of the GIA process that have since been developed as a means of interpreting the extensive variety of observations that are now recognized as being involved in the response of the planet to the loading and unloading of its surface by glacial ice. The paper will also provide examples of the further analyses of Earth physics and climate related processes that applications of the modern theoretical structures have enabled.

Rapid pacing and high-frequency jet ventilation additively improve catheter stability during atrial fibrillation ablation.

INTRODUCTION: Catheter stability during atrial fibrillation ablation is associated with higher ablation success rates. Rapid cardiac pacing and high-frequency jet ventilation (HFJV) independently improve catheter stability. Simultaneous modulation of cardiac and respiratory motion has not been previously studied. The objective of this study was to determine the effect of simultaneous heart rate and respiratory rate modulation on catheter stability. METHODS: Forty patients undergoing paroxysmal atrial fibrillation ablation received ablation lesions at 15 prespecified locations (12 left atria, 3 right atria). Patients were randomly assigned to undergo rapid atrial pacing for either the first or the second half of each lesion. Within each group, half of the patients received HFJV and the other half standard ventilation. Contact force and ablation data for all lesions were compared among the study groups. Standard deviation of contact force was the primary endpoint defined to examine contact force variability. RESULTS: Lesions with no pacing and standard ventilation had the greatest contact force standard deviation (5.86 ± 3.08 g), compared to lesions with pacing and standard ventilation (5.45 ± 3.28 g; P < .01) or to lesions with no pacing and HFJV (4.92 ± 3.00 g; P < .01). Lesions with both pacing and HFJV had the greatest reduction in contact force standard deviation (4.35 ± 2.81 g; P < .01), confirming an additive benefit of each maneuver. Pacing and HFJV together was also associated with a reduction in the proportion of lesions with excessive maximum contact force (P < .001). DISCUSSION: Rapid pacing and HFJV additively improve catheter stability. Simultaneous pacing with HFJV further improves catheter stability over pacing or HFJV alone to optimize ablation lesions.

Acute kidney injury in patients undergoing endovascular therapy for critical limb ischemia.

BACKGROUND: Similar to coronary angiography and interventions, patients undergoing percutaneous treatment of lower extremity peripheral arterial disease are also at risk of acute kidney injury (AKI). The incidence, risk factors associations, need for dialysis and inhospital mortality related to AKI in patients with critical limb ischemia (CLI) following endovascular therapy is poorly defined. OBJECTIVES: The purpose of this study was to analyze data from the National Inpatient Sample (NIS) to determine the aforementioned outcomes in patients with CLI. METHODS: Using the full NIS admission dataset from 2003 through 2012, ICD-9 codes relevant to comorbid conditions, procedure codes, composite codes for AKI, and inhospital mortality were analyzed using multivariate models. RESULTS: A total of 273,624 patients were included with a mean age of 70.0 ± 27.4 years, 46.0% were female, 57.2% had diabetes, 43.4% had coronary artery disease (CAD), and 29.2% had chronic kidney disease (CKD). The overall rate of AKI was 10.4%, and there was a temporal rise over the analysis period in AKI incidence (p < .001). Age, diabetes, CKD, and heart failure were all associated with AKI (p < .0001). The inhospital mortality rate in the patients with AKI declined over time but was higher than in patients without AKI (6.0% vs. 1.4%), p < .0001. The mortality rate was substantially higher in patients with AKI requiring dialysis as compared to AKI not requiring dialysis (13.4% vs. 5.6%), p < .0001. CONCLUSIONS: AKI is associated with age, CKD, and heart failure. The incidence of AKI following endovascular therapy for CLI is rising and independently associated with inhospital mortality.

Detecting time-evolving phenotypic topics via tensor factorization on electronic health records: Cardiovascular disease case study.

OBJECTIVE: Discovering subphenotypes of complex diseases can help characterize disease cohorts for investigative studies aimed at developing better diagnoses and treatments. Recent advances in unsupervised machine learning on electronic health record (EHR) data have enabled researchers to discover phenotypes without input from domain experts. However, most existing studies have ignored time and modeled diseases as discrete events. Uncovering the evolution of phenotypes - how they emerge, evolve and contribute to health outcomes - is essential to define more precise phenotypes and refine the understanding of disease progression. Our objective was to assess the benefits of an unsupervised approach that incorporates time to model diseases as dynamic processes in phenotype discovery. METHODS: In this study, we applied a constrained non-negative tensor-factorization approach to characterize the complexity of cardiovascular disease (CVD) patient cohort based on longitudinal EHR data. Through tensor-factorization, we identified a set of phenotypic topics (i.e., subphenotypes) that these patients established over the 10 years prior to the diagnosis of CVD, and showed the progress pattern. For each identified subphenotype, we examined its association with the risk for adverse cardiovascular outcomes estimated by the American College of Cardiology/American Heart Association Pooled Cohort Risk Equations, a conventional CVD-risk assessment tool frequently used in clinical practice. Furthermore, we compared the subsequent myocardial infarction (MI) rates among the six most prevalent subphenotypes using survival analysis. RESULTS: From a cohort of 12,380 adult CVD individuals with 1068 unique PheCodes, we successfully identified 14 subphenotypes. Through the association analysis with estimated CVD risk for each subtype, we found some phenotypic topics such as Vitamin D deficiency and depression, Urinary infections cannot be explained by the conventional risk factors. Through a survival analysis, we found markedly different risks of subsequent MI following the diagnosis of CVD among the six most prevalent topics (p < 0.0001), indicating these topics may capture clinically meaningful subphenotypes of CVD. CONCLUSION: This study demonstrates the potential benefits of using tensor-decomposition to model diseases as dynamic processes from longitudinal EHR data. Our results suggest that this data-driven approach may potentially help researchers identify complex and chronic disease subphenotypes in precision medicine research.

Accessory lacrimal gland secretion mimicking seidel positivity following complex cataract surgery: Case report.

Purpose: To describe the presentation of lacrimal gland secretions mimicking a positive Seidel test following combined complex cataract surgery and endocyclophotocoagulation (ECP). Observation: The patient presented with a posterior subcapsular cataract (PSC) most likely secondary to chronic steroid use for a history of chemical burns from a firework injury in 2019. This injury resulted in symblepharon formation and limbal stem cell deficiency. He also developed glaucoma secondary to steroid response and angle structure damage. On postoperative day 1 (POD 1) after combined cataract surgery and ECP, the patient's paracentesis was Seidel positive and aqueous suppression was started. On postoperative week 1 (POW 1), the paracentesis was Seidel negative; however, it was noted at this visit that there were 3 pinpoint areas in the superotemporal conjunctiva that were Seidel positive. Digital pressure did not worsen the leak. Ultrasound biomicroscopy (UBM) was performed at POW 2.5 and showed lacrimal gland ducts in the superotemporal conjunctiva. Given this, it is likely that the "Seidel positive" finding was not due to aqueous humor leakage, but secretions from lacrimal gland tissue that may have been dragged more anteriorly due to conjunctiva scarring, thus producing a false positive Seidel sign. Conclusion & importance: This case highlights a false positive Seidel sign in the context of an eye with a complex ocular history and recent surgery. Clinicians should recognize that a false positive Seidel sign is possible if normal lacrimal gland anatomy has been disturbed.

Variable domain mutational analysis to probe the molecular mechanisms of high viscosity of an IgG1 antibody.

Subcutaneous injection is the preferred route of administration for many antibody therapeutics for reasons that include its speed and convenience. However, the small volume limit (typically ≤2 mL) for subcutaneous delivery often necessitates antibody formulations at high concentrations (commonly ≥100 mg/mL), which may lead to physicochemical problems. For example, antibodies with large hydrophobic or charged patches can be prone to self-interaction giving rise to high viscosity. Here, we combined X-ray crystallography with computational modeling to predict regions of an anti-glucagon receptor (GCGR) IgG1 antibody prone to self-interaction. An extensive mutational analysis was undertaken of the complementarity-determining region residues residing in hydrophobic surface patches predicted by spatial aggregation propensity, in conjunction with residue-level solvent accessibility, averaged over conformational ensembles from molecular dynamics simulations. Dynamic light scattering (DLS) was used as a medium throughput screen for self-interaction of ~ 200 anti-GCGR IgG1 variants. A negative correlation was found between the viscosity determined at high concentration (180 mg/mL) and the DLS interaction parameter measured at low concentration (2-10 mg/mL). Additionally, anti-GCGR variants were readily identified with reduced viscosity and antigen-binding affinity within a few fold of the parent antibody, with no identified impact on overall developability. The methods described here may be useful in the optimization of other antibodies to facilitate their therapeutic administration at high concentration.

Nonclinical immunogenicity risk assessment for knobs-into-holes bispecific IgG1 antibodies.

Bispecific antibodies, including bispecific IgG, are emerging as an important new class of antibody therapeutics. As a result, we, as well as others, have developed engineering strategies designed to facilitate the efficient production of bispecific IgG for clinical development. For example, we have extensively used knobs-into-holes (KIH) mutations to facilitate the heterodimerization of antibody heavy chains and more recently Fab mutations to promote cognate heavy/light chain pairing for efficient in vivo assembly of bispecific IgG in single host cells. A panel of related monospecific and bispecific IgG1 antibodies was constructed and assessed for immunogenicity risk by comparison with benchmark antibodies with known low (Avastin and Herceptin) or high (bococizumab and ATR-107) clinical incidence of anti-drug antibodies. Assay methods used include dendritic cell internalization, T cell proliferation, and T cell epitope identification by in silico prediction and MHC-associated peptide proteomics. Data from each method were considered independently and then together for an overall integrated immunogenicity risk assessment. In toto, these data suggest that the KIH mutations and in vitro assembly of half antibodies do not represent a major risk for immunogenicity of bispecific IgG1, nor do the Fab mutations used for efficient in vivo assembly of bispecifics in single host cells. Comparable or slightly higher immunogenicity risk assessment data were obtained for research-grade preparations of trastuzumab and bevacizumab versus Herceptin and Avastin, respectively. These data provide experimental support for the common practice of using research-grade preparations of IgG1 as surrogates for immunogenicity risk assessment of their corresponding pharmaceutical counterparts.

A Rare Case of Primary Anorectal Hodgkin Lymphoma in an HIV-Positive Patient: A Case Report and Literature Review.

Lymphoma is a well-known complication related to HIV infection; of these, non-Hodgkin lymphoma (NHL) is the most common subtype with Hodgkin lymphoma (HL) occurring less frequently. We present a rare case of a 35-year-old male with a history of HIV/AIDS well-controlled on antiretroviral therapy (ART) with an atypical HL presentation. He arrived at the emergency department with rectal bleeding, 30-pound unintentional weight loss, and subjective fever. CT scan of the abdomen and pelvis showed a circumferential mass extending from the mid-rectum to the anus, with extensive local lymphadenopathy. He underwent multiple biopsies of the mass and adjacent lymph nodes. The pathology report showed EBV-positive lymphoma with features of classical Hodgkin lymphoma (cHL) (positive for EBV-EBER by in-situ hybridization). He was started on A+AVD (brentuximab plus doxorubicin, vinblastine and dacarbazine). The patient tolerated the chemotherapy well without significant complications. We want to encourage physicians and providers to include anorectal HL in their differential diagnosis for HIV/AIDS patients with atypical rectal malignancy presentations and subsequent reporting of these cases.

Evaluating Predictive Value of Surgical Resected Proximal Bone Margins in Diabetic Foot Osteomyelitis With Clinical Outcomes at 1 Year.

Background: Osteomyelitis of the diabetic foot remains a significant complication that may result in the need for amputation. Proximal surgical margin histopathology after limb-sparing amputation could be used to guide antimicrobial duration and prognostic management but remains debatable. Here we evaluate if negative proximal bone margins predict outcomes of diabetic foot osteomyelitis at 1 year. Methods: A retrospective study assessed adults with diabetes undergoing limb-sparing foot amputations from September 2016 to September 2019. Patients required histopathology confirmation of osteomyelitis, proximal margin histopathology report, and documented electronic medical record follow-up through 12 months. The primary outcome evaluated if no further amputation at the same site was required in the following 12 months. Results: Of 92 patients, 57 (61.9%) had pathology-confirmed negative margins for osteomyelitis. Patients with negative margins required less frequent subsequent amputations at the same site within 12 months compared to positive margins (86.0% vs 65.7%; P = .003). Antibiotic duration was shorter in patients with negative margins (mean, 18 vs 30 days; P = .001). Negative-margin patients also noted lower rates of readmission at 12 months (26.3% vs 51.4%; P = .015) for site-specific complications. Staphylococcus aureus was more predominant in patients with positive versus negative margins (57.1% vs 29.8%; P = .017). Conclusions: Negative proximal bone margin by histopathology was associated with lower frequency of further amputations at the index surgical site within 12 months. This group also received shorter courses of antibiotic therapy. It was also associated with lower rates of readmission at 12 months for surgical-site complications. Proximal margin histopathology results potentially can be integrated to guide antimicrobial duration and decrease the frequency of further amputation at the original site.

Hepatitis C: A Rare Cause of Subacute Paralysis.

The effects of the hepatitis C virus (HCV) on the nervous system have been primarily reported with a pathology of the peripheral nervous system through the involvement of a vasculitic process via cryoglobulinemia. A review of the recent literature reinforced the likely association between chronic HCV infection and transverse myelitis (TM), but the causal relationship remains elusive. Here, we present a rare case of acute TM developing over the course of days from symptom onset and a concomitant new diagnosis of HCV infection. A 31-year-old male with a medical history of stimulant use disorder with intravenous methamphetamine use presented to the hospital for acute bilateral leg weakness. The weakness was predominantly in his thighs and later progressed to his calves over the course of days. He denied urinary or fecal incontinence; however, on hospital day two, he developed acute urinary retention requiring the insertion of a Foley catheter. An initial MRI of the spine revealed an intramedullary T2 hyperintense signal at the lower thoracic cord concerning for TM, multiple sclerosis, ischemia, or neoplasm. MRI of the brain was unremarkable. Lumbar puncture results also displayed no abnormalities. HCV screening should be considered in all patients who develop acute neurological deficits that are not otherwise explained, such as TM, given the significant morbidity associated with delayed treatment.

Intravenous fluids cause systemic bias in a conductivity-based point-of-care hematocrit meter.

BACKGROUND: Point-of-care (POC) devices measuring hematocrit rely on determination of electrical conductivity of whole blood. We hypothesized that some frequently administered IV fluids independently alter blood conductivity and confound hematocrit determination. METHODS: Whole human blood was diluted to predetermined hematocrit values with normal saline, lactated Ringer solution, hetastarch, or plasma. Electrical conductivity and hematocrit (i-STAT® and spun methods) were measured at each dilution. In separate experiments, the effects of propofol and heparin were noted on these variables. RESULTS: Greater dilution significantly increased conductivity irrespective of diluent type. The magnitude of the conductivity slopes increased in order for plasma, hetastarch, lactated Ringer solution, and normal saline dilution. Moreover, each slope varied from every other slope (all P < 0.0001), and 94.2% of hematocrit values measured by i-STAT (n = 211 of 224) were less than those for the spun method. Dilution with plasma, normal saline, lactated Ringer solution, and hetastarch caused bias (Bland-Altman limits of agreement) of -2.7% (-6.9/1.4), -4.6% (-7.3/-2.0), -4.8% (-7.8/-1.7), and -2.0% (-5.6/1.9), respectively. The Cohen κ agreement values (5th-95th confidence interval) for a transfusion trigger of 30% were 0.90 (all values, 0.85-0.95), 0.25 (hematocrit <30%, 0.02-0.48), and 0.21 (hematocrit 18%-30%, 0.01-0.42). Clinically relevant concentrations of propofol and heparin had minimal effects on electrical conductivity or hematocrit determination. CONCLUSIONS: Dilution of blood with frequently used IV solutions affects whole blood conductivity determinations and thereby decreases hematocrits measured by a POC device relying on this method as compared with spun hematocrit. Conductivity-based hematocrit POC devices should be cautiously interpreted when hemodilution is present.

Staphylococcus hominis Infective Endocarditis Presenting with Embolic Splenic and Renal Infarcts and Spinal Discitis.

Staphylococcus hominis (S. hominis) is a Gram-positive, coagulase-negative bacteria that occurs as a normal commensal organism on the skin and may rarely cause native valve endocarditis (NVE). We present a 62-year-old male with type 2 diabetes mellitus, coronary artery disease, and hypertension presenting with fever and abdominal pain. CT (computerized tomography) of the abdomen revealed splenic and renal infarcts; further imaging with MRI (magnetic resonance imaging) revealed enhancements consistent with discitis in T5-6 and L1-2. Three sets of blood cultures were positive for S. hominis sensitive to methicillin on antimicrobial susceptibility tests, and echocardiogram showed posterior mitral valve vegetation. The patient was initially treated with 10 weeks of nafcillin IV (intravenous) 2 g q4 hours. He had recurrent bouts of S. hominis bacteremia that was treated with IV vancomycin. His clinical course was complicated by new-onset atrial fibrillation with rapid ventricular response and congestive heart failure. Once bacteremia was cleared, his infective endocarditis was successfully definitively treated with mitral valve replacement and tricuspid repair.

Management of Renal Angiomyolipomas in Tuberous Sclerosis Complex: A Case Report and Literature Review.

We report a case of misdiagnosed tuberous sclerosis complex (TSC) in a patient without TSC gene variant presenting with bilateral renal angiomyolipomas and seizures in the context of strong family history of polycystic kidney disease. Clinical diagnosis of tuberous sclerosis complex was made and treatment with everolimus reduced size of renal angiomyolipomas. In this case, report we discuss the association between tuberous sclerosis complex and polycystic kidney disease and novel treatment for TSC.

Integrating gene expression and clinical data to identify drug repurposing candidates for hyperlipidemia and hypertension.

Discovering novel uses for existing drugs, through drug repurposing, can reduce the time, costs, and risk of failure associated with new drug development. However, prioritizing drug repurposing candidates for downstream studies remains challenging. Here, we present a high-throughput approach to identify and validate drug repurposing candidates. This approach integrates human gene expression, drug perturbation, and clinical data from publicly available resources. We apply this approach to find drug repurposing candidates for two diseases, hyperlipidemia and hypertension. We screen >21,000 compounds and replicate ten approved drugs. We also identify 25 (seven for hyperlipidemia, eighteen for hypertension) drugs approved for other indications with therapeutic effects on clinically relevant biomarkers. For five of these drugs, the therapeutic effects are replicated in the All of Us Research Program database. We anticipate our approach will enable researchers to integrate multiple publicly available datasets to identify high priority drug repurposing opportunities for human diseases.

Chondrogenic priming adipose-mesenchymal stem cells for cartilage tissue regeneration.

PURPOSE: Chondrocytes lose their ability to produce cartilaginous matrix during multiplication in culture through repeated passages, resulting in inferior tissue phenotype. To overcome the limited amount of primary chondrocytes, we aimed to determine the optimal culture condition for in vitro/in vivo cartilage regeneration using human adipose-derived mesenchymal stem cells (AMSCs). METHODS: To evaluate the effects exerted by the chondrocytic culture condition on AMSC, we utilized chondrocyte conditioned medium (CM) and/or co-culture methods to prime and differentiate AMSCs. We evaluated ultimate in vivo engineered cartilage with primed AMSCs with that of chondrocytes. To examine the link between conditioned factors and proliferation/differentiation, cell cycle progression of AMSCs were examined using 5-ethynyl-2'-deoxyuridine (EdU), and gene expression was monitored. RESULTS: We report that AMSCs can be stimulated to become chondrogenic cells when expanded with chondrocyte CM. Polymeric scaffolds co-seeded with CM- expanded AMSCs and primary chondrocytes resulted in in vivo cartilaginous tissues with similar biochemical content to constructs seeded with chondrocytes alone. CONCLUSION: These results indicate that chondrocyte CM consists of suitable morphogenetic factors that induce the chondrogenic priming of AMSCs for cartilage tissue engineering.

Sequence2Script: A Web-Based Tool for Translation of Pharmacogenetic Data Into Evidence-Based Prescribing Recommendations.

Pharmacogenomic (PGx) testing has emerged as an effective strategy for informing drug selection and dosing. This has led to an increase in the use of PGx testing in the clinic and has catalyzed the emergence of a burgeoning commercial PGx testing industry. However, not all PGx tests are equivalent in their approach to translating testing results into prescribing recommendations, due to an absence of regulatory standards. As such, those generating and using PGx data require tools for ensuring the prescribing recommendations they are provided align with current peer-reviewed PGx-based prescribing guidelines developed by expert groups or approved product labels. Herein, we present Sequence2Script (sequence2script.com), a simple, free, and transparent web-based tool to assist in the efficient translation of PGx testing results into evidence-based prescribing recommendations. The tool was designed with a wide-range of user groups (e.g., healthcare providers, laboratory staff, researchers) in mind. The tool supports 97 gene-drug pairs with evidence-based prescribing guidelines, allows users to adjust recommendations for concomitant inhibitors and inducers, and generates a clinical report summarizing the patient's genotype, inferred phenotype, phenoconverted phenotype (if applicable), and corresponding prescribing recommendations. In this paper, we describe each of the tool's features, provide use case examples, and discuss limitations of and future development plans for the tool. Although we recognize that Sequecnce2Script may not meet the needs of every user, the hope is that this novel tool will facilitate more standardized use of PGx testing results and reduce barriers to implementing these results into practice.