1 2 3<!doctype html> 4<!-- 5 Minimal Mistakes Jekyll Theme 4.28.1 by Michael Rose 6 Copyright 2013-2026 Michael Rose - mademistakes.com | @mmistakes 7 Copyright 2024-2026 iBug - ibugone.com | @iBug 8 Free for personal and commercial use under the MIT license 9 https://github.com/mmistakes/minimal-mistakes/blob/master/LICENSE 10--> 11 12<html lang="en" class="no-js" dir="ltr"> 13 <head> 14 15<meta charset="utf-8"> 16 17 18<!-- begin _includes/seo.html --><title>CAVA Lab</title> 19<meta name="description" content="Clinical AI Value Alignment"> 20 21 22 23<meta property="og:type" content="website"> 24<meta property="og:locale" content="en_US"> 25<meta property="og:site_name" content="CAVA Lab"> 26<meta property="og:title" content="CAVA Lab"> 27<meta property="og:url" content="https://cavalab.github.io/"> 28 29 30 <meta property="og:description" content="Clinical AI Value Alignment"> 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45<link rel="canonical" href="https://cavalab.github.io/"> 46 47 48 49 50 51
51<script type="application/ld+json"> 52{ 53 "@context": "https://schema.org", 54 "@type": "Person", 55 "name": null, 56 "url": "https://cavalab.github.io/" 57} 58</script>
58 59 60 61 62 63 64 65 66 67 68<!-- end _includes/seo.html --> 69 70 71<meta name="viewport" content="width=device-width, initial-scale=1.0"> 72
73<script> 74 document.documentElement.className = document.documentElement.className.replace(/\bno-js\b/g, '') + ' js '; 75 76</script>
76 77 78<!-- For all browsers --> 79<link rel="stylesheet" href="/assets/css/main.css"> 80<link rel="preload" href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@latest/css/all.min.css" as="style" onload="this.onload=null;this.rel='stylesheet'"> 81<noscript><link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@latest/css/all.min.css"></noscript> 82 83 84 85 <!-- Load KaTeX for math rendering --> 86<!-- https://varunagrawal.github.io/2018/03/27/latex-jekyll/ --> 87<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/[email protected]/dist/katex.min.css" integrity="sha384-Xi8rHCmBmhbuyyhbI88391ZKP2dmfnOl4rT9ZfRI7mLTdk1wblIUnrIq35nqwEvC" crossorigin="anonymous"> 88 89<!-- The loading of KaTeX is deferred to speed up page rendering -->
90<script defer src="https://cdn.jsdelivr.net/npm/[email protected]/dist/katex.min.js" integrity="sha384-X/XCfMm41VSsqRNQgDerQczD69XqmjOOOwYQvr/uuC+j4OPoNhVgjdGFwhvN02Ja" crossorigin="anonymous"></script>
90 91 92<!-- To automatically render math in text elements, include the auto-render extension: -->
93<script defer src="https://cdn.jsdelivr.net/npm/[email protected]/dist/contrib/auto-render.min.js" integrity="sha384-+XBljXPPiv+OzfbB3cVmLHf4hdUFHlWNZN5spNQ7rmHTXpd7WvJum6fIACpNNfIR" crossorigin="anonymous" 94 onload="renderMathInElement(document.body);"></script>
94 95 96<!-- insert favicons. use https://realfavicongenerator.net/ --> 97 98<link rel="apple-touch-icon" sizes="180x180" href="/assets/images/apple-touch-icon.png"> 99<link rel="icon" type="image/png" sizes="32x32" href="/assets/images/favicon-32x32.png"> 100<link rel="icon" type="image/png" sizes="16x16" href="/assets/images/favicon-16x16.png"> 101<link rel="manifest" href="/assets/images/site.webmanifest"> 102<link rel="shortcut icon" href="/assets/images/favicon.ico"> 103<meta name="msapplication-TileColor" content="#da532c"> 104<meta name="msapplication-config" content="/assets/images/browserconfig.xml"> 105<meta name="theme-color" content="#ffffff"> 106 107 </head> 108 109 <body class="layout--home standard"> 110 111<nav class="skip-links" aria-label="Skip links"> 112 <ul> 113 <li><a href="#site-nav" class="screen-reader-shortcut">Skip to primary navigation</a></li> 114 <li><a href="#main" class="screen-reader-shortcut">Skip to content</a></li> 115 <li><a href="#footer" class="screen-reader-shortcut">Skip to footer</a></li> 116 </ul> 117</nav> 118 119 120 121 122<div class="masthead"> 123 <div class="masthead__inner-wrap"> 124 <div class="masthead__menu"> 125 <nav id="site-nav" class="greedy-nav" aria-label="Primary navigation"> 126 127 <a class="site-title" href="/"> 128 CAVA Lab 129 <span class="site-subtitle">Clinical AI Value Alignment</span> 130 </a> 131 <ul class="visible-links"><li class="masthead__menu-item"> 132 <a 133 href="/members" 134 135 136 >Members</a> 137 </li><li class="masthead__menu-item"> 138 <a 139 href="/research" 140 141 142 >Research</a> 143 </li><li class="masthead__menu-item"> 144 <a 145 href="/papers" 146 147 148 >Papers</a> 149 </li><li class="masthead__menu-item"> 150 <a 151 href="/posts" 152 153 154 >Posts</a> 155 </li><li class="masthead__menu-item"> 156 <a 157 href="/join" 158 159 160 >Join</a> 161 </li></ul> 162 163 <button class="greedy-nav__toggle hidden" type="button"> 164 <span class="visually-hidden">Toggle menu</span> 165 <div class="navicon"></div> 166 </button> 167 <ul class="hidden-links hidden"></ul> 168 </nav> 169 </div> 170 </div> 171</div> 172 173 174 <div class="initial-content"> 175 176 177 178 179 180 181<div id="main" role="main"> 182 183 184 <div class="sidebar sticky"> 185 186 187 188 189<div itemscope itemtype="https://schema.org/Person" class="h-card"> 190 191 192 <div class="author__avatar"> 193 <a href="https://cavalab.github.io/"> 194 <img src="/assets/images/space_bot3.jpg" alt="" itemprop="image" class="u-photo"> 195 </a> 196 </div> 197 198 199 <div class="author__content"> 200 <h3 class="author__name p-name" itemprop="name"> 201 <a class="u-url" rel="me" href="https://cavalab.github.io/" itemprop="url"></a> 202 </h3> 203 204 </div> 205 206 <div class="author__urls-wrapper"> 207 <button class="btn btn--inverse">Follow</button> 208 <ul class="author__urls social-icons"> 209 210 <li itemprop="homeLocation" itemscope itemtype="https://schema.org/Place"> 211 <i class="fas fa-fw fa-location-dot" aria-hidden="true"></i> <span itemprop="name" class="p-locality">Boston, MA</span> 212 </li> 213 214 215 216 217 218 <li><a href="mailto:[email protected]" rel="nofollow noopener noreferrer me"><i class="fas fa-fw fa-envelope" aria-hidden="true"></i><span class="label">Email</span></a></li> 219 220 221 222 <li><a href="https://github.com/cavalab" rel="nofollow noopener noreferrer me" itemprop="sameAs"><i class="fab fa-fw fa-github" aria-hidden="true"></i><span class="label">GitHub</span></a></li> 223 224 225 226 <li><a href="https://scholar.google.com/citations?user=iZB7inEAAAAJ&hl=en" rel="nofollow noopener noreferrer me" itemprop="sameAs"><i class="fas fa-graduation-cap" aria-hidden="true"></i><span class="label">Google Scholar</span></a></li> 227 228 229 230 <li><a href="https://connects.catalyst.harvard.edu/Profiles/display/Person/200560" rel="nofollow noopener noreferrer me" itemprop="sameAs"><i class="fas fa-project-diagram" aria-hidden="true"></i><span class="label">Harvard Catalyst</span></a></li> 231 232 233 234 <li><a href="http://chip.org" rel="nofollow noopener noreferrer me" itemprop="sameAs"><i class="fa fa-heartbeat" aria-hidden="true"></i><span class="label">CHIP</span></a></li> 235 236 237 238 <li><a href="https://www.childrenshospital.org/" rel="nofollow noopener noreferrer me" itemprop="sameAs"><i class="fa fa-medkit" aria-hidden="true"></i><span class="label">Boston Children's Hospital</span></a></li> 239 240 241 242 <li><a href="https://hms.harvard.edu/" rel="nofollow noopener noreferrer me" itemprop="sameAs"><i class="fa fa-university" aria-hidden="true"></i><span class="label">
242Harvard Medical School</span></a></li> 243 244 245 246 <li><a href="https://bsky.app/profile/lacava.bsky.social" rel="nofollow noopener noreferrer me" itemprop="sameAs"><i class="far fa-comment" aria-hidden="true"></i><span class="label">Bluesky</span></a></li> 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 <!-- 300 <li> 301 <a href="http://link-to-whatever-social-network.com/user/" itemprop="sameAs" rel="nofollow noopener noreferrer me"> 302 <i class="fas fa-fw" aria-hidden="true"></i> Custom Social Profile Link 303 </a> 304 </li> 305--> 306 </ul> 307 </div> 308</div> 309 310 311 312 </div> 313 314 315 316 <div class="archive"> 317 318 <h1 id="page-title" class="page__title"></h1> 319 320 <figure style="width: 150px" class="align-right"> 321 <img src="assets/images/Cava_Lab_logo.png" alt="" /> 322</figure> 323 324<p>The Clinical AI Value Alignment lab studies artificial intelligence (AI) used in healthcare settings. 325We focus on algorithmic notions of interpretability, fairness, accuracy, and robustness in medical applications of AI.</p> 326 327<p>The lab is part of the <a href="http://www.chip.org">Computational Health Informatics Program</a> at Boston Childrenâs Hospital, affiliated with Harvard Medical School.</p> 328 329 330 331<h2 class="archive__subtitle">Recent Papers</h2> 332 333<div class="entries-"> 334 335 336 337 338 339 340 341 342 343 344 345<div class="pubitem"> 346 <div class="pubtitle" id="aldeiaguilhermeDeepTimetoEventModels"> 347 Deep Time-to-Event Models for Intrapartum Fetal Monitoring 348 </div> 349 <div class="pubauthors"> 350 351 352 353 354 355 356 Guilherme S. Imai Aldeia, 357 358 359 360 Helena Coggan, 361 362 363 364 Yuting Yang, 365 366 367 368 Lisa Levine, 369 370 371 372 Jennifer A. McCoy, 373 374 375 376 William G. La Cava 377 378 (2026) 379 </div> 380 381 382 383 384 385 <div class=pubinfo> 386 Preprint 387 </div> 388 389 <div class="publinks"> 390 391 392 393 394 395 396 397 398 399 400 401 402 <a href="/assets/papers/Aldeia et al. - 2026 - Deep Time-to-Event Models for Intrapartum Fetal Mo.pdf">pdf</a> 403 404 405 </div> 406</div> 407 408 409 410 411<div class="pubitem"> 412 <div class="pubtitle" id="huPretrainFinetuneFramework2026"> 413 A pre-train and fine-tune framework for adaptive boosting of pre-trained polygenic risk scores 414 </div> 415 <div class="pubauthors"> 416 417 418 419 420 421 422 Jie Hu, 423 424 425 426 Raelynn Chen, 427 428 429 430 Maxwell Salvatore, 431 432 433 434 Olivia Wu, 435 436 437 438 Okan Bilge Ozdemir, 439 440 441 442 Yiwen Lu, 443 444 445 446 Shawn N. Murphy, 447 448 449 450 Elizabeth W. Karlson, 451 452 453 454 Atlas Khan, 455 456 457 458 Krzysztof Kiryluk, 459 460 461 462 Iftikhar J. Kullo, 463 464 465 466 Johanna L. Smith, 467 468 469 470 Eimear E. Kenny, 471 472 473 474 Yuan Luo, 475 476 477 478 Zaldy S. Tan, 479 480 481 482 William G. La Cava, 483 484 485 486 Marylyn D. Ritchie, 487 488 489 490 Yong Chen, 491 492 493 494 Ruowang Li 495 496 (2026) 497 </div> 498 499 500 501 502 503 <div class=pubjournal> 504 Nature Communications 505 </div> 506 507 <div class="publinks"> 508 509 510 511 512 513 <a href="https://www.nature.com/articles/s41467-026-77128-5"><i class="fas fa-external-link-alt"></i> nature.com </a> 514 515 516 517 518 519 520 521 522 | 523 524 <a href="/assets/papers/Hu et al. - 2026 - A pre-train and fine-tune framework for adaptive b.pdf">pdf</a> 525 526 527 </div> 528</div> 529 530 531 532 533<div class="pubitem"> 534 <div class="pubtitle" id="aldeiaFoundationmodelApproachPediatric2026"> 535 A foundation-model approach to pediatric headache classification from rs-fMRI 536 </div> 537 <div class="pubauthors"> 538 539 540 541 542 543 544 Guilherme S. Imai Aldeia, 545 546 547 548 Clara Moon, 549 550 551 552 Julie Shulman, 553 554 555 556 Navil Sethna, 557 558 559 560 Allison Smith, 561 562 563 564 Alyssa Lebel, 565 566 567 568 William G. La Cava, 569 570 571 572 Scott Holmes 573 574 (2026) 575 </div> 576 577 578 579 580 581 <div class=pubjournal> 582 Machine Learning for Healthcare Conference 583 </div> 584 585 <div class="publinks"> 586 587 588 589 590 591 <a href="http://arxiv.org/abs/2608.07287"><i class="fas fa-external-link-alt"></i> arxiv.org </a> 592 593 594 595 596 597 598 599 600 | 601 602 <a href="/assets/papers/Aldeia et al. - 2026 - A foundation-model approach to pediatric headache.pdf">pdf</a> 603 604 605 606 607 608 609 610 611 | In press 612 613 614 615 </div> 616</div> 617 618</div> 619 620<h2 class="archive__subtitle">Recent Posts</h2> 621 622 623 624
625<div class="entries-list"> 626 627 628 629 630 631<div class="list__item"> 632 <article class="archive__item" itemscope itemtype="https://schema.org/CreativeWork"> 633 634 <div class="archive__item-title no_toc" itemprop="headline"> 635 <b> 636 637 <a href="/2025/10/24/ed-admissions.html" rel="permalink">What Drives Disparities in Emergency Admissions? 638</a> 639 640 </b> 641 </div> 642 643 644 645 <p class="page__meta"> 646 647 648 649 650 651 652 653 654 <span class="page__meta-readtime"> 655 <i class="far fa-clock" aria-hidden="true"></i> 656 657 7 minute read 658 659 </span> 660 661 </p> 662 663 664 <p class="archive__item-excerpt" itemprop="description">Understanding unwarranted variations in emergency care 665</p> 666 </article> 667</div> 668 669 670 671 672 673<div class="list__item"> 674 <article class="archive__item" itemscope itemtype="https://schema.org/CreativeWork"> 675 676 <div class="archive__item-title no_toc" itemprop="headline"> 677 <b> 678 679 <a href="/2025/02/14/ecg-survival.html" rel="permalink">Benchmarking mortality risk prediction from electrocardiograms 680</a> 681 682 </b> 683 </div> 684 685 686 687 <p class="page__meta"> 688 689 690 691 692 693 694 695 696 <span class="page__meta-readtime"> 697 <i class="far fa-clock" aria-hidden="true"></i> 698 699 4 minute read 700 701 </span> 702 703 </p> 704 705 706 <p class="archive__item-excerpt" itemprop="description">Taking a closer look at survival modeling with ECGs 707</p> 708 </article> 709</div> 710 711 712 713 714 715<div class="list__item"> 716 <article class="archive__item" itemscope itemtype="https://schema.org/CreativeWork"> 717 718 <div class="archive__item-title no_toc" itemprop="headline"> 719 <b> 720 721 <a href="/2024/04/14/inexact-simplification.html" rel="permalink">Simplifying symbolic regression models without simplification rules 722</a> 723 724 </b> 725 </div> 726 727 728 729 <p class="page__meta"> 730 731 732 733 734 735 736 737 738 <span class="page__meta-readtime"> 739 <i class="far fa-clock" aria-hidden="true"></i> 740 741 6 minute read 742 743 </span> 744 745 </p> 746 747 748 <p class="archive__item-excerpt" itemprop="description">Relaxing the definition of equivalent mathematical expressions to get simpler and more interpretable models 749</p> 750 </article> 751</div> 752 753</div> 754 755 756 757 758 </div> 759</div> 760 761 762 </div> 763 764 765 766 <div id="footer" class="page__footer"> 767 <footer> 768 <!-- Parse the Latex divs with Katex--> 769<!-- https://varunagrawal.github.io/2018/03/27/latex-jekyll/ -->
770<script type="text/javascript"> 771 $("script[type='math/tex']").replaceWith( 772 function(){ 773 var tex = $(this).text(); 774 return katex.renderToString(tex, {displayMode: false}); 775 }); 776 777 $("script[type='math/tex; mode=display']").replaceWith( 778 function(){ 779 var tex = $(this).text(); 780 return katex.renderToString(tex.replace(/%.*/g, ''), {displayMode: true}); 781 }); 782</script>
782 783 784 785 786 787<div class="page__footer-follow"> 788 <ul class="social-icons"> 789 790 791 792 793 794 <li><a href="mailto:[email protected]" rel="nofollow noopener noreferrer"><i class="fas fa-fw fa-envelope" aria-hidden="true"></i> Email</a></li> 795 796 797 798 <li><a href="https://github.com/cavalab" rel="nofollow noopener noreferrer"><i class="fab fa-fw fa-github" aria-hidden="true"></i> GitHub</a></li> 799 800 801 802 <li><a href="https://scholar.google.com/citations?user=iZB7inEAAAAJ&hl=en" rel="nofollow noopener noreferrer"><i class="fas fa-graduation-cap" aria-hidden="true"></i> Google Scholar</a></li> 803 804 805 806 <li><a href="https://connects.catalyst.harvard.edu/Profiles/display/Person/200560" rel="nofollow noopener noreferrer"><i class="fas fa-project-diagram" aria-hidden="true"></i> Harvard Catalyst</a></li> 807 808 809 810 <li><a href="http://chip.org" rel="nofollow noopener noreferrer"><i class="fa fa-heartbeat" aria-hidden="true"></i> CHIP</a></li> 811 812 813 814 <li><a href="https://www.childrenshospital.org/" rel="nofollow noopener noreferrer"><i class="fa fa-medkit" aria-hidden="true"></i> Boston Children's Hospital</a></li> 815 816 817 818 <li><a href="https://hms.harvard.edu/" rel="nofollow noopener noreferrer"><i class="fa fa-university" aria-hidden="true"></i> Harvard Medical School</a></li> 819 820 821 822 <li><a href="https://bsky.app/profile/lacava.bsky.social" rel="nofollow noopener noreferrer"><i class="far fa-comment" aria-hidden="true"></i> Bluesky</a></li> 823 824 825 826 827 828 </ul> 829</div> 830 831 832<div class="page__footer-copyright">© 2026 <a href="https://cavalab.github.io">CAVA Lab</a>. Powered by <a href="https://jekyllrb.com" rel="nofollow">Jekyll</a> & <a href="https://mademistakes.com/work/jekyll-themes/minimal-mistakes/" rel="nofollow">Minimal Mistakes</a>.</div> 833 834 </footer> 835 </div> 836 837 838 839
839<script src="/assets/js/main.min.js"></script>
839 840 841 842 843 844 845 846 847 <!-- Global site tag (gtag.js) - Google Analytics -->
vendor: 64 bytes, lines 847-848
847 848<script async src="https://www.googletagmanager.com/gtag/js?id=
848G-8CVW0XBQDT
vendor: 12 bytes, line 848
848"></script>
849<script> 850
vendor: 134 bytes, lines 850-854
850window.dataLayer = window.dataLayer || []; 851 function gtag(){dataLayer.push(arguments);} 852 gtag('js', new Date()); 853 854 gtag('config', '
854G-8CVW0XBQDT
vendor: 29 bytes, line 854
854', { 'anonymize_ip': true});
855</script>
855 856 857 858 859 860 861 862 863 864 865 </body> 866</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.