{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:23:18Z","timestamp":1793042598348,"version":"4.5.0"},"reference-count":36,"publisher":"SLACK, Inc.","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Refract Surg"],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose:<\/jats:title>\n                    <jats:p>To frame aspheric laser refractive planning as the supervised prediction of console-programmable inputs (Defocus, Astigmatism, and Q-factor) and to benchmark competing regression models; this is a translational methods proof-of-concept, not a clinical effectiveness study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>\n                      An anonymized, retrospective, single-platform dataset of 2,448 complete-case treatments was analyzed. Multi-output regressors (linear and nonlinear) were trained and compared using prespecified metrics (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      , MAE\/MSE) and residual-distribution visualization\/calibration. Actuator\u2013response checks related programmed inputs to changes in Defocus (Z\n                      <jats:sub>2<\/jats:sub>\n                      <jats:sup>0<\/jats:sup>\n                      ) and primary spherical aberration (Z\n                      <jats:sub>4<\/jats:sub>\n                      <jats:sup>0<\/jats:sup>\n                      ). External validation used a temporally later, device-shift cohort (n = 147).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>\n                      Linear regression predicted Defocus and astigmatism well (eg, Defocus\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>\n                        <jats:italic toggle=\"yes\">2<\/jats:italic>\n                      <\/jats:sup>\n                      = 0.98) but degraded for Q-factor (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.47), whereas nonlinear models improved Q-factor error and calibration. Actuator\u2013response analyses showed strong coupling for Defocus input (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.97), moderate coupling of Q-factor to \u0394Z\n                      <jats:sub>4<\/jats:sub>\n                      <jats:sup>0<\/jats:sup>\n                      (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.51), and a weak Q\u2192Defocus cross-effect (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.12). On external validation, the best model generalized: Defocus MAE 0.22 D (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.98) and Q-factor MAE 0.21 (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.81).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>Supervised nonlinear multi-output models achieve lower error and better calibration for Q-factor than linear baselines, supporting a metric-driven pathway toward more reliable control of low-order refractive targets and primary asphericity. Potential clinical implications include tissue sparing, improved contrast, and near-vision gains. Prospective, human-in-the-loop evaluation with safety and patient-reported endpoints is warranted.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3928\/1081597x-20260415-02","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T11:31:42Z","timestamp":1783683102000},"source":"Crossref","is-referenced-by-count":1,"title":["Machine Learning\u2013Based Prediction of LASIK Console Inputs for Aspheric Planning (Q-factor, Defocus, Astigmatism): A Translational Methods Study"],"prefix":"10.3928","volume":"42","author":[{"given":"Steven","family":"Garnier","sequence":"first","affiliation":[{"name":"Laser Vision Bourgogne, Chalon sur Sa\u00f4ne, France."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2308","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/srep26094"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.021"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Bavikadi D Agarwal A Ganta S . Machine learning driven biomarker selection for medical diagnosis. arXiv. 2024;arX-iv:2405.10345. 10.48550\/arXiv.2405.10345","DOI":"10.48550\/arXiv.2405.10345"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2025.02.022"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2024.02.037"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40662-022-00312-3"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20141021-10"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20160810-01"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20120518-04"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.08608"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12081"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1974.tb00994.x"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20090422-06"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1097\/OPX.0000000000001107"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-9235.1997.tb04707.x"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0886-3350(00)00797-5"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018054314350"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1505.05424"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Cipolla R Gal Y Kendall A. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics52018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2018:7482\u20137491. 10.1109\/CVPR.2018.00781","DOI":"10.1109\/CVPR.2018.00781"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.103.3.411"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Ling T Kang BH Johns DP Walls J Bindoff I. Expert-driven knowledge discovery. In: Fifth International Conference on Information Technology: New Generations (ITNG 2008). 2008:174\u2013178. 10.1109\/ITNG.2008.194","DOI":"10.1109\/ITNG.2008.194"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"e_1_3_2_27_2","volume-title":"Exploratory Data Analysis","author":"Tukey JW","year":"1977","unstructured":"Tukey JW. Exploratory Data Analysis. Addison-Wesley; 1977."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.2.3.292"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0886-3350(98)80043-6"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20170616-03"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2019.10.015"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-021-00867-7"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20241030-01"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20240611-05"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrs.2015.10.054"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.17940"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2009.36"}],"container-title":["Journal of Refractive Surgery"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:14:20Z","timestamp":1783692860000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.healio.com\/doi\/10.3928\/1081597X-20260415-02"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":36,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,1]]}},"alternative-id":["10.3928\/1081597X-20260415-02"],"URL":"https:\/\/doi.org\/10.3928\/1081597x-20260415-02","relation":{},"ISSN":["1081-597X"],"issn-type":[{"value":"1081-597X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7,1]]}}}