Citations

Clear

9383 citation(s) found for "Thomas, PS".

Prognostic value of aortic valve calcification in non-severe aortic stenosis with preserved ejection fraction
Ye, Zi , Gajjar, Rohan , Foley, Thomas A. , Clavel, Marie‐Annick , Miranda, William R. , Padang, Ratnasari , Michelena, Héctor I. , Gajjar, Rohan A, Foley, Thomas , Clavel, Marie-Annick , Luis, S Allen, Padang, Ratnasari , Michelena, Hector I , Enriquez-Sarano, Maurice , Scott, Christopher G. , Nkomo, Vuyisile T. , Luis, Sushil Allen , Pislaru, Sorin V. , Enriquez‐Sarano, Maurice

Mayo Clinic

European Heart Journal - Cardiovascular Imaging | June 3, 2024 | Volume: 25 | Issue: 10 | Pages: 1432-1440

10.1093/ehjci/jeae145 | PMID 38833585 Get It

Abstract Aims Aortic valve calcification (AVC) is prognostic in patients with aortic stenosis (AS). We assessed the AVC prognostic value in non-severe AS patients. Methods and results We conducted a retrospective study of 395 patients with non-severe AS, LVEF ≥ 50%. The Agatston method was used for CT AVC assessment. The log-rank test determined the best AVC cut-offs for survival under medical surveillance: 1185 arbitrary unit (AU) in men and 850 AU in women, lower than the established cut-offs for severe AS (2064 AU in men and 1274 AU in women). Patients were divided into 3 AVC groups based on these cut-offs: low (<1185 AU in men and <850 AU in women), sub-severe (1185–2064 AU in men and 850–1274 AU in women), and severe (>2064 AU in men and >1274 AU in women). Of 395 patients (mean age 73 ± 12 years, 60.5% men, aortic valve area 1.23 ± 0.30 cm2, mean pressure gradient 28 ± 8 mmHg), 218 underwent aortic valve intervention (AVI) and 158 deaths occurred during follow-up, 82 before AVI. Median survival time under medical surveillance was 2.1 (0.7–4.9) years. Compared with the low AVC group, both sub-severe and severe AVC groups had higher risk for all-cause death under medical surveillance after comprehensive adjustment including echocardiographic AS severity and coronary artery calcium score (all P ≤ 0.006); while mortality risk was similar between sub-severe and severe AVC groups (all P ≥ 0.2). This mortality risk pattern persisted in the overall survival analysis after adjustment for AVI. AVI was protective of all-cause death in the sub-severe and severe AVC (all P ≤ 0.01), but not in the low AVC groups. Conclusion Sub-severe AVC is a robust risk stratification parameter in patients with non-severe AS and may inform AVI timing.
Navigating Complexities: Vitamin D, Skin Pigmentation, and Race
Ospina, Naykky Singh , Diaz-Thomas, Alicia , Demay, Marie B. , York, E.L. , Lash, Robert W. , Brito, Juan P. , Murad, M. Hassan , Singh Ospina, Naykky , McDonnell, Marie E , Demay, Marie B , York, Elizabeth , Brito, Juan P , Murad, M Hassan , McCartney, Christopher R , McDonnell, Marie E. , Pittas, Anastassios G. , Corrigan, Maureen D. , McCartney, Christopher R.

Mayo Clinic

The Journal of Clinical Endocrinology & Metabolism | June 3, 2024 | Volume: 109 | Issue: 8 | Pages: 1955-1960

10.1210/clinem/dgae314 | PMID 38828960 Get It

Abstract Vitamin D plays a critical role in many physiological functions, including calcium metabolism and musculoskeletal health. This commentary aims to explore the intricate relationships among skin complexion, race, and 25-hydroxyvitamin D (25[OH]D) levels, focusing on challenges the Endocrine Society encountered during clinical practice guideline development. Given that increased melanin content reduces 25(OH)D production in the skin in response to UV light, the guideline development panel addressed the potential role for 25(OH)D screening in individuals with dark skin complexion. The panel discovered that no randomized clinical trials have directly assessed vitamin D related patient-important outcomes based on participants' skin pigmentation, although race and ethnicity often served as presumed proxies for skin pigmentation in the literature. In their deliberations, guideline panel members and selected Endocrine Society leaders underscored the critical need to distinguish between skin pigmentation as a biological variable and race and ethnicity as socially determined constructs. This differentiation is vital to maximize scientific rigor and, thus, the validity of resulting recommendations. Lessons learned from the guideline development process emphasize the necessity of clarity when incorporating race and ethnicity into clinical guidelines. Such clarity is an essential step toward improving health outcomes and ensuring equitable healthcare practices.
Examining Changes in Shoulder Strength, Lower Body Power, and Body Composition among Collegiate Baseball Players after Completion of a Summer Baseball League Season
Merfeld, Brandon , Rowley, Matthew , Luedke, Joel, Erickson, Jacob L. , Jones, Margaret T. , Fields, Jennifer B. , Szymanski, Elijah, Jagim, Andrew R. , Jones, Margaret T , Jagim, Andrew R , Rowley, Matthew, Almonroeder, Thomas Gus

Mayo Clinic

Journal of Functional Morphology and Kinesiology | June 3, 2024 | Volume: 9 | Issue: 2 | Pages: 98

10.3390/jfmk9020098 | PMID 38921634 Get It

The strength of the shoulder musculature involved with internal rotation and arm extension plays an important role in the overhead throwing motion for baseball athletes, both for throwing-related performance and injury risk. The maintenance of shoulder strength is a high priority for baseball athletes throughout a season; however, little is known in regards to the expected changes in strength throughout a season. To examine pre-post changes in shoulder strength, lower body power, and body composition among collegiate baseball players after the completion of a summer baseball league season. Amateur baseball players (n = 12; age: 20.9 ± 1.0 years.; height: 181.6 ± 5.6 cm; body mass: 86.4 ± 11.1 kg; BMI: 26.0 ± 2.6 kg/m2) participated in the current study. Pre- and post-competitive season, the participants completed shoulder strength assessments and body composition and countermovement vertical jump (CMJ) tests. An upper-body isometric test (athletic shoulder [ASH] test) was used to evaluate shoulder strength for each arm. Each subject completed maximal isometric contractions for both the throwing and non-throwing arms at four separate angles of abduction (180°, ‘I’; 135°, ‘Y’; 90°, ‘T’; and −180°, ‘A’) while lying in a prone position. For shoulder strength, the primary dependent variable of interest was a composite measure that represented the average of the forces produced across all four positions of the ASH test (I, Y, T, A). For the ASH test composite measure, there was a trend toward a significant arm-by-time interaction effect (p = 0.08), as shoulder strength decreased by 9.03% for the throwing arm (ES = 0.72; 95% CI = [−0.27, −0.01]), compared to only 2.03% for the non-throwing arm (ES = 0.15; 95% CI = [−0.16, 0.09]), over the course of the season. The main effects of time (p = 0.16) and arm (p = 0.58) were not significant for the ASH test composite measure. There was no relationship between lower body power and throwing arm strength at baseline (r = 0.20, p = 0.56), and only a non-significant weak relationship at post-test (r = 0.28, p = 0.41). Throughout a season, baseball players may experience reductions in shoulder strength of the throwing arm with minimal changes in shoulder strength in the non-throwing arm.
Adjunctive Statistical Standardization of Adjuvant Estrogen Receptor and Progesterone Receptor in Canadian Cancer Trials Group MA.27 Postmenopausal Breast Cancer Trial of Exemestane Versus Anastrozole
Chapman, Judith‐Anne W. , Bayani, Jane , Sengupta, Sandip , Bartlett, John M.S. , Quintayo, Mary Anne , Virk, Shakeel , Goss, Paul E., Ingle, James N. , Ellis, Matthew J. , Budd, G. Thomas , Ansari, Rafat , Tozer, Richard , D’Souza, David , Chalchal, Haji , Spadafora, Silvana , Stearns, Vered , Perez, Edith A. , Whelan, Timothy J., Elliott, Catherine, Shepherd, Lois E. , Taylor, Karen J. , Whelan, Timothy J. , Ingle, J , Virk, Shakeel , Ellis, Matthew J , Sledge, George W , Budd, G Thomas , Rabaglio-Poretti, Manuela , Stearns, Vered , Perez, Edith A , Gelmon, Karen A , Whelan, Timothy J , Shepherd, LE , Chen, Bingshu E , Taylor, Karen J , Piper, Tammy , Sledge, George W. , Rabaglio, Manuela , Gelmon, Karen A. , Chen, Bingshu E. , Whelan, Timothy J

Mayo Clinic

Journal of Clinical Oncology | June 2, 2024 | Volume: 42 | Issue: 24 | Pages: 2887-2898

10.1200/jco.24.00835 | PMID 38824432 Get It

PURPOSE ASCO/College of American Pathologists guidelines recommend reporting estrogen receptor (ER) and progesterone receptor (PgR) as positive with (1%-100%) staining. Statistically standardized quantitated positivity could indicate differential associations of positivity with breast cancer outcomes. METHODS MA.27 (ClinicalTrials.gov identifier: NCT00066573 ) was a phase III adjuvant trial of exemestane versus anastrozole in postmenopausal women with early-stage breast cancer. Immunochemistry ER and PgR HSCORE and % positivity (%+) were centrally assessed by machine image quantitation and statistically standardized to mean 0 and standard deviation (SD) 1 after Box-Cox variance stabilization transformations of square for ER; for PgR, (1) natural logarithm (0.1 added to 0 HSCOREs and 0%+) and (2) square root. Our primary end point was MA.27 distant disease-free survival (DDFS) at a median 4.1-year follow-up, and secondary end point was event-free survival (EFS). Univariate survival with cut points at SDs about a mean of 0 (≤–1; (–1, 0]; (0, 1]; >1) was described with Kaplan-Meier plots and examined with Wilcoxon (Peto-Prentice) test statistic. Adjusted Cox multivariable regressions had two-sided Wald tests and nominal significance P < .05. RESULTS Of 7,576 women accrued, 3,048 women's tumors had machine-quantitated image analysis results: 2,900 (95%) for ER, 2,726 (89%) for PgR, and 2,582 (85% of 3,048) with both ER and PgR. Higher statistically standardized ER and PgR HSCORE and %+ were associated with better univariate DDFS and EFS ( P < .001). In multivariable assessments, ER HSCORE and %+ were not significantly associated ( P = .52-.88) with DDFS in models with PgR, whereas higher PgR HSCORE and %+ were significantly associated with better DDFS ( P = .001) in models with ER. CONCLUSION Adjunctive statistical standardization differentiated quantitated levels of ER and PgR. Patients with higher ER- and PgR-standardized units had superior DDFS compared with those with HSCOREs and %+ ≤–1.
Symptom‐Free Intervals Following Laser Wedge Excision for Recurrent Idiopathic Subglottic Stenosis
Xie, Katherine , O’Byrne, Thomas J., Wallerius, Katherine P. , Aden, Aisha A. , Bayan, Semirra L. , Edell, Eric S. , Vassallo, Robert , Kasperbauer, Jan L. , Ekbom, Dale C. , O'Byrne, Thomas J, Awadallah, Andrew S. , Vassallo, Robert , Bayan, Semirra , Bowen, Andrew J.

Mayo Clinic

Otolaryngology–Head and Neck Surgery | June 1, 2024 | Volume: 171 | Issue: 3 | Pages: 799-807

10.1002/ohn.831 | PMID 38822766 Get It

AbstractObjectiveAnalyze the duration of symptom‐free intervals following laser wedge excision (LWE) for recurrent idiopathic subglottic stenosis (iSGS). Secondary aim includes evaluating the influence of patient‐related or disease factors.Study DesignRetrospective review.SettingTertiary center.MethodsReview of iSGS patients who underwent LWE between 2002 and 2021. LWE patients without prior airway surgery were labeled LWE primary (LWEP) and those with prior history of dilation were labeled LWE secondary (LWES). A conditional frailty repeated events model was used to analyze the median time to recurrence (MTR) for each nth recurrence. Secondary analysis included stratification by use of medical therapy and initial preoperative characteristics of scar (Myer‐Cotton grade, distance between the glottis and superior‐most aspect of scar, DGS; length of scar, DL).ResultsTwo hundred and ten iSGS patients underwent LWE (131 LWEP, 79 LWES). The proportion of patients experiencing at least 1, 3, 6, and 12 recurrences, respectively, was 68.0% (n = 143), 40.7% (n = 85), 20.0% (n = 42), and 5.2% (n = 11). There was exponential time‐shortening from the 1st to 12th recurrence (P < .0001). While MTR was 4.1 years after the first LWE, this fell to 2.8, 1.7, 1.0, and 0.7 years for the 2nd, 3rd, 6th, and 12th recurrences. Furthermore, LWEP patients experienced longer MTR than LWES counterparts within the first 6 recurrences (P < .01). There was no significant relationship between intersurgical interval and medication adherence, DL, DGS, or grade for recurrences beyond the first (P = .207, P = .20, P = .43, P = .16).ConclusionSymptom‐free intervals in iSGS shorten with each subsequent recurrence and LWE. The difference in MTR between LWEP and LWES groups was significant within the first 6 recurrences with LWEP having longer MTR.Level of Evidence3.
Management of failed flow diversion for intracranial aneurysm beyond the first 6 months of follow-up: an international Delphi consensus
Chintapalli, Renuka , Nguyen, Sarah, Dammann, Philipp , Raygor, Kunal P. , Ogilvy, Christopher S. , Linfante, Italo , Almefty, Rami O. , Burkhardt, Jan‐Karl , Jankowitz, Brian T. , Starke, Robert M. , Gross, Bradley A. , Kan, Peter, Coulthard, Alan , Dabus, Guilherme , Raper, Daniel , Kilburg, Craig , Abla, Adib A. , Abla, Adib , Ogilvy, Christopher S , Burkhardt, Jan‐Karl , Nguyen, Sarah E. , Taussky, Philipp , Grandhi, Ramesh , Tonetti, Daniel A. , Andersson, Tommy , White, Phil , Chapot, René , Fox, W Christopher , Tawk, Rabih G. , Lanzino, Giuseppe , Hanel, Ricardó A. , Jadhav, Ashutosh P. , Hassan, Ameer E , Mascitelli, Justin R , Fargen, Kyle M , Levitt, Michael R. , Jabbour, Pascal , Gross, Bradley , Killer-Oberpfalzer, Monika , Rautio, Riitta , Dmytriw, Adam A. , Dabus, Guilherme C. , Deuschl, Cornelius , Budohoski, Karol P.

Mayo Clinic

Journal of Neurosurgery | June 1, 2024 | Volume: 141 | Issue: 5 | Pages: 1225-1234

10.3171/2024.3.jns2499 | PMID 38820616 Get It

OBJECTIVE The placement of flow-diverting devices has become a common method of treating unruptured intracranial aneurysms of the internal carotid artery. The progressive improvement of aneurysm occlusion after treatment—with low complication and rupture rates—has led to a dilemma regarding the management of aneurysms in which occlusion has not occurred within 6–24 months. The authors aimed to identify clinical consensus regarding management of intracranial aneurysms displaying persistent filling 6–24 months after flow diversion and to ascertain questions that may drive future investigation. METHODS An international panel of 67 experts was invited to participate in a multistep Delphi consensus process on the treatment of intracranial aneurysms after failed flow diversion. RESULTS Of the 67 experts invited, 23 (34%) participated. Qualitative analysis of an initial survey with open-ended questions resulted in 51 statements regarding management of aneurysms showing persistent filling after flow diversion. The statements were grouped into 8 categories, and in the second round, respondents rated the degree of their agreement with each statement on a 5-point Likert scale. Flow diverters with surface modifiers did not influence administration of dual-antiplatelet therapy according to 83%. Consensus was also reached regarding the definition of treatment failure at specific time points, including at 6 months if there is aneurysm growth or persistent rapid flow through the entirety of the aneurysm (96%), at 12 months if there is aneurysm growth or symptom onset (78%), and at 24 months if there is persistent filling regardless of size and filling characteristics (74%). Although experts agreed that the degree of intimal hyperplasia or in-device stenosis could not be ascertained by noninvasive imaging alone (83%), only 65% chose digital subtraction angiography as the preferred modality. At 6 and 12 months, retreatment is preferred if there is persistent filling with aneurysm growth (96%, 96%), device malposition (48%, 87%), or a history of subarachnoid hemorrhage (65%, 70%), respectively, and at 24 months if there is persistent filling without reduction in aneurysm size (74%). Experts favored treatment with an additional flow diverter (87%) over aneurysm clipping, applying the same principles for follow-up (83%) and treatment failure (91%) as for the first flow diverter. CONCLUSIONS The authors present the consensus practices of experts in the management of intracranial aneurysms without occlusion 6–24 months after treatment with a flow-diverting device.
Randomized study of induction with bendamustine-rituximab ± bortezomib and maintenance with rituximab ± lenalidomide for MCL
Smith, Mitchell R. , Jegede, Opeyemi A. , Parekh, Samir , Yang, David T. , Hsi, Eric D. , Witzig, Thomas E. , Davé, Sandeep S. , Scott, David W. , Hanson, Curtis A. , Shields, Lale Kostakoglu, Abdel‐Samad, Nizar, Baghdadi, Tareq Al, Blum, Kristie A. , Romer, Mark D., Inwards, David J. , Lerner, Rachel E. , Little, Richard F. , Friedberg, Jonathan W. , Leonard, John P. , Witzig, T.E. , Yang, David , Hsi, Eric D , Scott, David W , Hanson, Curtis, Casulo, Carla , Wagner, Lynne , Little, Richard F , Kahl, Brad S , Jagede, Opeyemi A. , Parekh, Samir , Baghdadi, Tareq Al , Martin, Peter, Till, Brian G. , Casulo, Carla , Bartlett, Nancy L. , Caimi, Paolo F. , Wagner, Lynne I. , Kahl, Brad S.

Mayo Clinic

Blood | May 31, 2024 | Volume: 144 | Issue: 10 | Pages: 1083-1092

10.1182/blood.2024023962 | PMID 38820500 Get It

Abstract Although initial therapy of mantle cell lymphoma (MCL) is not standardized, bendamustine plus rituximab (BR) is commonly used in older patients. Rituximab (R) maintenance after induction is often used. Thus, the open-label, randomized phase 2 ECOG-ACRIN Cancer Research Group E1411 trial was designed to test 2 questions: (1) does addition of bortezomib to BR induction (BVR) and/or (2) addition of lenalidomide to rituximab (LR) maintenance improve progression-free survival (PFS) in patients with treatment-naïve MCL? From 2012 to 2016, 373 previously untreated patients, 87% aged ≥60 years, were enrolled in this trial. At a median follow-up of 7.5 years, there is no difference in the median PFS of BR compared with BVR (5.5 vs 6.4 years; hazard ratio [HR], 0.90; 90% confidence interval [CI], 0.70-1.16). There were no unexpected additional toxicities with BVR treatment compared with BR, with no impact on total dose/duration of treatment received. Independent of the induction treatment, addition of lenalidomide did not significantly improve PFS, with median PFS in R vs LR (5.9 vs 7.2 years; HR, 0.84; 90% CI, 0.62-1.15). Most patients completed the planned 24 cycles of LR at the scheduled dose. In summary, adding bortezomib to BR induction does not prolong PFS in treatment-naïve MCL, and LR maintenance was not associated with longer PFS compared with R alone after BR. Nonetheless, the &gt;5-year median PFS outcomes in this prospective cooperative group trial indicate the efficacy of BR followed by R maintenance as highly effective initial therapy for older patients with MCL. This trial was registered at www.clinicaltrials.gov as #NCT01415752.
Safety and efficacy of luspatercept for the treatment of anemia in patients with myelofibrosis
Gerds, Aaron T. , Harrison, Claire , Mesa, Ruben A. , Vannucchi, Alessandro M. , Komrokji, Rami S. , Bose, Prithviraj , Kremyanskaya, Marina , Mead, Adam J. , Rose, Shelonitda, Sanabria, Fabián , Marsousi, Niloufar , Giuseppi, Ana Carolina, Jiang, Huijing, Palmer, Jeanne , McCaul, Kelly, Mesa, Ruben , Vannucchi, Alessandro M , Komrokji, Rami S , Bose, Prithviraj , Palmer, Jeanne M , Gerds, Aaron T , Mead, Adam J , Kiladjian, Jean‐Jacques , Gotlib, Jason , Sanabria, Fabian, Ribrag, Vincent , Passamonti, Francesco

Mayo Clinic

Blood Advances | May 31, 2024 | Volume: 8 | Issue: 17 | Pages: 4511-4522

10.1182/bloodadvances.2024012939 | PMID 38820422 Get It

Abstract The ACE-536-MF-001 trial enrolled patients with myelofibrosis (n = 95) into 4 cohorts: patients in cohorts 1 and 3A were non–transfusion dependent (NTD) and had anemia; patients in cohorts 2 and 3B were transfusion dependent (TD); and patients in cohort 3A/3B had stable ruxolitinib treatment before and during the study. All patients received luspatercept (1.0-1.75 mg/kg, 21-day cycles). Treatment was extended if clinical benefit was observed at day 169. The primary end point was anemia response rate (NTD, ≥1.5 g/dL hemoglobin increase from baseline; TD, transfusion-independence) over any 12-week period during the primary treatment period (weeks 1-24). Overall, 14% of patients in cohorts 1 and 3A, 10% in cohort 2, and 26% in cohort 3B met the primary end point. In cohorts 1 and 3A (NTD), 27% and 50% of patients, respectively, had mean hemoglobin increase of ≥1.5 g/dL from baseline. Among TD patients, ∼50% had ≥50% reduction in transfusion burden. Reduction in total symptom score was observed in all cohorts, with the greatest response rate seen in cohort 3A. Overall, 94% of patients had ≥1 adverse event (AE); 47% had ≥1 treatment-related AE (TRAE; 11% grade ≥3), most frequently hypertension (18%), managed with medical intervention. One patient had a serious TRAE leading to luspatercept discontinuation. Nine patients died on treatment (unrelated to study drug). In most patients, ruxolitinib dose and spleen size remained stable. In patients with myelofibrosis, luspatercept improved anemia and transfusion burden across cohorts; the safety profile was consistent with previous studies. This trial was registered at www.ClinicalTrials.gov as #NCT03194542.
Corticosteroid Injections and Risk of Fracture
Sytsma, Terin T. , Thomas, S. Craig, Greenlund, Laura S. , Thomas, Shannon, Fischer, Karen M.

Mayo Clinic

JAMA Network Open | May 31, 2024 | Volume: 7 | Issue: 5 | Pages: e2414316

10.1001/jamanetworkopen.2024.14316 | PMID 38819820 Get It

ImportanceCorticosteroid injections (CSIs) are an important tool for pain relief in many musculoskeletal conditions, but the longitudinal effects of these treatments on bone health and fracture risk are unknown.ObjectiveTo determine whether cumulative doses of corticosteroid injections are associated with higher risk of subsequent osteoporotic and nonosteoporotic fractures.Design, Setting, and ParticipantsThis cohort study included adult patients receiving any CSI from May 1, 2018, through July 1, 2022. Eligible patients resided in Olmsted County, Minnesota, and were empaneled to receive primary care within the Mayo Clinic. Cox proportional hazards regression models were used to evaluate risk of fracture based on cumulative injected corticosteroid dose.ExposureReceipt of any CSI during the study period.Main Outcomes and MeasuresThe primary outcome was risk of fracture by total triamcinolone equivalents received. Secondary outcomes consisted of risks of fracture based on triamcinolone equivalents received in subgroups of patients not at high risk for fracture and patients with osteoporosis.ResultsA total of 7197 patients were included in the study (mean [SD] age, 64.4 [14.6] years; 4435 [61.6%] women; 183 [2.5%] Black and 6667 [92.6%] White), and 346 (4.8%) had a new fracture during the study period. Of these fractures, 149 (43.1%) were considered osteoporotic. In the adjusted Cox proportional hazards regression model, there was no association of higher fracture risk based on cumulative CSI dose (adjusted hazard ratio [HR], 1.04 [95% CI, 0.96-1.11]). There was also no associated higher risk of fracture in the non–high-risk (adjusted HR, 1.11 [95% CI, 0.98-1.26]) or osteoporosis (adjusted HR, 1.01 [95% CI, 0.90-1.11]) subgroups. Age, Charleson Comorbidity Index, and previous fracture were the only factors that were associated with higher fracture risk.Conclusions and RelevanceIn this cohort study of cumulative injected corticosteroid dose and risk of subsequent fracture, no association was observed, including in patients with a preexisting diagnosis of osteoporosis. Treatment of painful conditions with CSI should not be withheld or delayed owing to concern about fracture risk.
A practical guide to the implementation of AI in orthopaedic research, Part 6: How to evaluate the performance of AI research?
Oettl, Felix C. , Pareek, Ayoosh , Winkler, Philipp W. , Zsidai, Bálint , Pruneski, James A. , Senorski, Eric Hamrin , Kopf, Sebastian , Herbst, Elmar , Oeding, Jacob F. , Hirschmann, Michael T. , Musahl, Volker , Samuelsson, Kristian , Tischer, Thomas , Group, ESSKA Artificial Intelligence Working, Oettl, Felix C. , Herbst, Elmar , Oeding, Jacob F , Hirschmann, Michael T , Musahl, Volker , Samuelsson, Kristian , Feldt, Robert , Hamrin Senorski, Eric , Ley, Christophe , Grassi, Alberto , Feldt, Robert , Group, ESSKA Artificial Intelligence Working

Mayo Clinic

Journal of Experimental Orthopaedics | May 31, 2024 | Volume: 11 | Issue: 3 | Pages: No page available

10.1002/jeo2.12039 | PMID 38826500 Get It

AbstractArtificial intelligence's (AI) accelerating progress demands rigorous evaluation standards to ensure safe, effective integration into healthcare's high‐stakes decisions. As AI increasingly enables prediction, analysis and judgement capabilities relevant to medicine, proper evaluation and interpretation are indispensable. Erroneous AI could endanger patients; thus, developing, validating and deploying medical AI demands adhering to strict, transparent standards centred on safety, ethics and responsible oversight. Core considerations include assessing performance on diverse real‐world data, collaborating with domain experts, confirming model reliability and limitations, and advancing interpretability. Thoughtful selection of evaluation metrics suited to the clinical context along with testing on diverse data sets representing different populations improves generalisability. Partnering software engineers, data scientists and medical practitioners ground assessment in real needs. Journals must uphold reporting standards matching AI's societal impacts. With rigorous, holistic evaluation frameworks, AI can progress towards expanding healthcare access and quality.Level of EvidenceLevel V.